Sequence-to-Sequence (seq2seq) & Dialog Systems 2016


Wikipedia:

References:

See also:

Neural Conversation Models 2016 | Neural Network & Dialog Systems 2016


A network-based end-to-end trainable task-oriented dialogue system
TH Wen, D Vandyke, N Mrksic, M Gasic… – arXiv preprint arXiv: …, 2016 – arxiv.org
… with neural networks for reinforcement learning in spoken dialogue systems. In Interspeech, 2015. [17] S. Sukhbaatar, A. Szlam, J. Weston, and R. Fergus. End-to-end memory networks. In NIPS, 2015. [18] I. Sutskever, O. Vinyals, and QV Le. Sequence to sequence learning with …

Deep reinforcement learning for dialogue generation
J Li, W Monroe, A Ritter, M Galley, J Gao… – arXiv preprint arXiv: …, 2016 – arxiv.org
… The LSTM sequence-to-sequence (SEQ2SEQ) model (Sutskever et al., 2014) is one type of neural … order to reduce the proportion of generic responses produced by SEQ2SEQ systems. … other line of statistical research focuses on building task-oriented dialogue systems to solve …

A persona-based neural conversation model
J Li, M Galley, C Brockett, GP Spithourakis… – arXiv preprint arXiv: …, 2016 – arxiv.org
… Since generating meaningful re- sponses in an open-domain scenario is intrinsi- cally difficult in conventional dialog systems, ex- isting models … The present work, by contrast, is in the vein of the SEQ2SEQ models of Vinyals and Le (2015) and … 3 Sequence-to-Sequence Models …

Sequence-to-sequence learning as beam-search optimization
S Wiseman, AM Rush – arXiv preprint arXiv:1606.02960, 2016 – arxiv.org
… Sequence-to-Sequence learning with deep neural networks (herein, seq2seq) (Sutskever et al … the same model and training have also proven to be useful for sen- tence compression (Filippova et al., 2015), parsing (Vinyals et al., 2015), and dialogue systems (Ser- ban …

Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings
O Dušek, F Jur?í?ek – arXiv preprint arXiv:1606.05491, 2016 – arxiv.org
… In spoken dialogue systems (SDS), the task of nat- ural language generation (NLG) is to convert a meaning representation (MR … Our generator is based on the sequence-to- sequence (seq2seq) generation technique (Cho et al., 2014; Sutskever et al., 2014), combined with beam …

Conditional generation and snapshot learning in neural dialogue systems
TH Wen, M Gasic, N Mrksic… – arXiv preprint arXiv: …, 2016 – arxiv.org
… The testbed for this work is a neural network-based task-oriented dialogue system proposed by Wen et al. (2016a). The model casts dialogue as a source to target sequence transduction problem (modelled by a sequence-to-sequence architecture (Sutskever et al., 2014 …

Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation
L Mou, Y Song, R Yan, G Li, L Zhang, Z Jin – arXiv preprint arXiv: …, 2016 – arxiv.org
… In these studies, researchers leverage sequence-to-sequence (seq2seq) models to encode a query (user-issued utterance … new utterances; results in the literature also show the superiority of seq2seq to phrase-based machine translation for dialogue systems (Shang et al …

Dialog state tracking with attention-based sequence-to-sequence learning
T Hori, H Wang, C Hori, S Watanabe… – … (SLT), 2016 IEEE, 2016 – ieeexplore.ieee.org
… Index Terms— Dialog state tracking, attention model, sequence- to-sequence learning, encoder-decoder, long short-term memory 1. INTRODUCTION Recently, spoken dialog systems have been widely used for many human-machine interfaces such as smart phones and car …

A sequence-to-sequence model for user simulation in spoken dialogue systems
LE Asri, J He, K Suleman – arXiv preprint arXiv:1607.00070, 2016 – arxiv.org
Abstract: User simulation is essential for generating enough data to train a statistical spoken dialogue system. Previous models for user simulation suffer from several drawbacks, such as the inability to take dialogue history into account, the need of rigid structure to ensure

CFGs-2-NLU: Sequence-to-sequence learning for mapping utterances to semantics and pragmatics
AJ Summerville, J Ryan, M Mateas… – arXiv preprint arXiv: …, 2016 – arxiv.org
… our knowledge, this is the first usage of seq2seq learning for … understanding · conversational agent · chatbot · machine learning · neural network · sequence-to-sequence · lstm · context … But while service dialogue systems have become common, general conversational agents are …

A context-aware natural language generator for dialogue systems
O Dušek, F Jur?í?ek – arXiv preprint arXiv:1608.07076, 2016 – arxiv.org
… In spoken dialogue systems (SDS), users were reported to entrain to system prompts (Parent and Eskenazi, 2010 … 1). Our system is an extension of Dušek and Jurc?cek (2016b)’s generator based on sequence-to-sequence (seq2seq) models with at- tention (Bahdanau et al., 2015 …

Two are Better than One: An Ensemble of Retrieval-and Generation-Based Dialog Systems
Y Song, R Yan, X Li, D Zhao, M Zhang – arXiv preprint arXiv:1610.07149, 2016 – arxiv.org
… The query, along with the candidate reply, is then fed to an utterance generator based on the “bi-sequence to sequence” (biseq2seq) model [30]. … That being said, previous studies indicate seq2seq has its own shortcoming for dialog systems. …

Learning to Start for Sequence to Sequence Architecture
Q Zhu, W Zhang, L Zhou, T Liu – arXiv preprint arXiv:1608.05554, 2016 – arxiv.org
… 6.2 Sequence to sequence in Response Generation … (2015) used this type of data on the Seq2Seq to build a short … (2016), who came up with the Hierarchical Nerual Network model, aiming to model the utterances and interactive structure to build a multi-round dialogue system. …

Translating player dialogue into meaning representations using LSTMs
J Ryan, AJ Summerville, M Mateas… – … Conference on Intelligent …, 2016 – Springer
… approach to natural language understanding that utilizes context-free grammars (CFGs) in conjunction with sequence-to-sequence (seq2seq) deep learning. … In service dialogue systems, interaction is constrained and highly structured, lending well to rule-based approaches to …

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
IV Serban, T Klinger, G Tesauro… – arXiv preprint arXiv: …, 2016 – arxiv.org
… Instead, we pursue a complimentary research direction aimed at generalizing the sequence-to-sequence framework to … different types: goal-driven dialogue systems and non-goal-driven dialogue systems [27]. … 20] (LSTM), which at test time is similar to the Seq2Seq …

Recurrent Neural Networks for Dialogue State Tracking
O Plátek, P B?lohlávek, V Hude?ek… – arXiv preprint arXiv: …, 2016 – arxiv.org
… We cast the slot predictions problem as a sequence-to- sequence predictions task and we use a encoder … 6We modified code from the TensorFlow ‘seq2seq’ module. … The data for the DSTC2 test set were collected using a different spoken dialogue system configuration than the …

Does IR Need Deep Learning?
H Li – 2016 – hangli-hl.com
“… Our Work on Generation-based Question Answering • Neural Responding Machine: generation-based single turn dialogue system using deep learning • Model: sequence-to- sequence learning (encoder decoder framework) • Encoding message into representation and …

Mutual information and diverse decoding improve neural machine translation
J Li, D Jurafsky – arXiv preprint arXiv:1601.00372, 2016 – arxiv.org
… Sequence-to-sequence models for machine transla- tion (SEQ2SEQ) (Sutskever et al., 2014; Bahdanau et al., 2014; Cho et al., 2014; Kalchbrenner and Blunsom, 2013; Sennrich et al., 2015a; Sennrich et al., 2015b; Gulcehre et al., 2015) are of growing interest for their capacity …

Sequence-to-Sequence Learning for End-to-End Dialogue Systems
J Van Landeghem – 2016 – researchgate.net
“There is strong evidence that over the next few years, dialogue research will quickly move towards large-scale data-driven model approaches, in particular in the form of end-to-end trainable systems as is the case for other language-related applications such as speech

Generative Deep Neural Networks for Dialogue: A Short Review
IV Serban, R Lowe, L Charlin, J Pineau – arXiv preprint arXiv:1611.06216, 2016 – arxiv.org
… Researchers have recently started investigating sequence-to-sequence (Seq2Seq) models for dialogue applications. … Researchers have mainly explored two types of Seq2Seq models. … neural networks to the different components of a standard dialogue system, including natural …

Online Sequence-to-Sequence Reinforcement Learning for Open-Domain Conversational Agents
N Asghar, P Poupart, J Xin, H Li – arXiv preprint arXiv:1612.03929, 2016 – arxiv.org
… Yin et al., 2015], and context-based response generation in both open- domain and task-oriented dialogue systems [Le et al … Many of these pro- posed models use LSTM encoder-decoder architectures, such as the sequence-to-sequence (Seq2Seq) framework [Sutskever et al …

Using phone features to improve dialogue state tracking generalisation to unseen states
I Casanueva, T Hain, M Nicolao… – Proceeding of SIGDIAL …, 2016 – eprints.whiterose.ac.uk
… 1In a slot based dialogue system the dialogue states are defined as the set of possible value combinations for each slot. … Sequence to sequence models (aka seq2seq models, RNN encoder-decoders), can be used to perform such a task. …

End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager
X Yang, YN Chen, D Hakkani-Tur, P Crook, X Li… – arXiv preprint arXiv: …, 2016 – arxiv.org
… Index Terms— language understanding, spoken dialogue systems, end-to-end, dialogue manager, deep learning 1. INTRODUCTION … Intents Intents Fig. 3: Proposed End-to-End Joint Model of sequence to sequence model (Seq2Seq) is to estimate the conditional …

Sequence Generation & Dialogue Evaluation
R Lowe – cs.mcgill.ca
“… Corpora for Building Data-Driven Dialogue Systems.” 2016. Serban, Sordoni, Lowe, Pineau, Courville, Bengio. “A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues.” AAAI, 2017. Sutskever, Vinyals, Le. “Sequence-to-sequence Learning with Neural …

LSTM ENCODER–DECODER FOR DIALOGUE RESPONSE GENERATION
Z Yu, C Yuan, X Wang, G Yang – workshop.colips.org
… Furthermore, we focus on models which can exploit dialog histories to generate fluent, more human-like utterances for spoken dialogue systems. 3. MODEL Our approach works like a language model based on the sequence to sequence framework described in [2, 14], which …

Non-sentential Question Resolution using Sequence to Sequence Learning
V Kumar, S Joshi – aclweb.org
… Pineau. 2016. Building end- to-end dialogue systems using generative hierarchical neural network models. In AAAI. Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In …

Deep Learning for Natural Language Processing-Research at Noah’s Ark Lab
H Li – 2016 – hangli-hl.com
“… Meng et al., ACL 2015 Page 23. Deep Memory • For sequence to sequence learning • Stack of Neural Turing Machines • Transformation of … management Alan Turing Page 27. Natural Language Dialogue System – Retrieval based Approach index of messages and responses …

Short Text Conversation (STC)
L Shanga, T Sakaib, Z Lua, H Lia, R Higashinakac… – research.nii.ac.jp
… The First Step at NTCIR-12 – Take it as an IR problem – Build a useful dialogue system that can interact naturally with humans 7 Page 8. … syntactic features 1 ICL00 semantic features (CNN, seq2seq) 3 Splab, USTC,ITNLP learning from some raw features by NN 1 ITNLP 16 …

TEXT NORMALIZATION FOR AUTOMATIC SPEECH RECOGNITION SYSTEMS
AF VASILE, T BORO? – ISSN 1843-911X – consilr.info.uaic.ro
… the text is extremely important for automatic machine translation (MT), speech-to-speech translation, information extraction, dialogue systems, etc … et al., 2015; Lai et al., 2015), sentiment analysis (Zhang et al., 2015), machine translation (sequence to sequence models)(Sutskever …

Visual Dialog
A Das, S Kottur, K Gupta, A Singh, D Yadav… – arXiv preprint arXiv: …, 2016 – arxiv.org
… pairs. Finally, the focus of Geman et al. [13] is a statistical templated-question gener- ator and not an actual visual dialog system. We … often. 4.4. VisDial Evaluation Protocol One fundamental challenge in dialog systems is evaluation. If …

Topic Aware Neural Response Generation
C Xing, W Wu, Y Wu, J Liu, Y Huang, M Zhou… – arXiv preprint arXiv: …, 2016 – arxiv.org
… Although previous re- search focused on dialog systems, recently, with the large amount of conversation data available on the … Sequence- to-sequence (Seq2Seq) with attention (Bahdanau, Cho, and Bengio 2014; Cho, Courville, and Bengio 2015) represents the state-of-the-art …

A Dataset of Operator-client Dialogues Aligned with Database Queries for End-to-end Training
O Plátek, F Jur?í?ek – workshop.colips.org
… 1. Dušek, O., Jur?í?ek, F.: Sequence-to-sequence generation for spoken dialogue via deep syntax trees and strings. arXiv preprint arXiv:1606.05491 (2016) 2. Dušek, O., Plátek, O., Žilka, L., Jurcícek, F.: Alex: Bootstrapping a spoken dialogue system for a new domain by real …

Coherent Dialogue with Attention-based Language Models
H Mei, M Bansal, MR Walter – arXiv preprint arXiv:1611.06997, 2016 – arxiv.org
… Wen et al. (2015) and Wen et al. (2016) improve spoken dialog systems via multi-domain and semantically … RNN Seq2Seq and Language Models Recurrent neural networks have been successfully used both in sequence-to-sequence models (RNN- Seq2Seq, Fig. …

Selection method of an appropriate response in chat-oriented dialogue systems
H Mori, M Araki – 17th Annual Meeting of the Special Interest Group on …, 2016 – aclweb.org
… In the architecture, we used the following three chat dialogue systems: • Rule-based system: This chat system is based on the ELIZA type system (Weizenbaum, 1966). … Topic transition-oriented system: This one is implemented with a sequence-to-sequence model (Sutskever et …

Neural Discourse Modeling of Conversations
JM Pierre, M Butler, J Portnoff, L Aguilar – arXiv preprint arXiv:1607.04576, 2016 – arxiv.org
… By applying multi-task sequence to sequence learning techniques as in [16] we may be able to combine the conversational modeling task with other … seq2seq+A Nseq2seq+A … The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. …

1 Situation Intelligence Framework
Z Yu – cs.cmu.edu
“… Two dialog system frameworks were developed for computer science education and research (used in tutorials and courses), and … design; and proposed conversation strategies and system responses (generated using an ensemble of sequence-to-sequence neural models [7 …

Bootstrapping incremental dialogue systems: using linguistic knowledge to learn from minimal data
D Kalatzis, A Eshghi, O Lemon – arXiv preprint arXiv:1612.00347, 2016 – arxiv.org
… Recent data-driven machine learning approaches treat dialogue as a sequence-to-sequence generation problem, and train their models from … can be combined with machine learning methods, where linguistic knowledge is used to bootstrap new dialogue systems from very …

Reference-Aware Language Models
Z Yang, P Blunsom, C Dyer, W Ling – arXiv preprint arXiv:1611.01628, 2016 – arxiv.org
… Table 2: Fragment of database for dialogue system. We can observe from this example, users get recommendations of restaurants based on queries that specify the area, price and food type of the restaurant. … Figure 2: Hierarchical RNN Seq2Seq model …

A User Simulator for Task-Completion Dialogues
X Li, ZC Lipton, B Dhingra, L Li, J Gao… – arXiv preprint arXiv: …, 2016 – arxiv.org
… References [1] Layla El Asri, Jing He, and Kaheer Suleman. A sequence-to-sequence model for user simulation in spoken dialogue systems. arXiv:1607.00070, 2016. [2] Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, and Hiroshi Shimodaira. …

An Attentional Neural Conversation Model with Improved Specificity
K Yao, B Peng, G Zweig, KF Wong – arXiv preprint arXiv:1606.01292, 2016 – arxiv.org
… 4.4 Performance as a generation model 4.4.1 Comparison with other methods We compared the AWI model with the sequence- to-sequence (Seq2Seq) (Vinyals and Le, 2015) and the hierarchical recurrent encoder-decoder (HRED) (Serban et al., 2015a) models. …

A step beyond local observations with a dialog aware bidirectional GRU network for Spoken Language Understanding
V Vukotic, C Raymond, G Gravier – Interspeech, 2016 – hal.inria.fr
… MEDIA The research project MEDIA [13] evaluates different SLU mod- els of spoken dialogue systems dedicated to provide tourist in … successfully used in spoken language understanding, either by themselves [4] or as encoder- decoder (sequence to sequence) architectures [5 …

CNTK: Microsoft’s Open-Source Deep-Learning Toolkit
F Seide, A Agarwal – Proceedings of the 22nd ACM SIGKDD …, 2016 – dl.acm.org
… SGD API o C++ usage o Python usage • Hands-on examples, including o ResNet image recognition o Sequence-to-sequence modeling … and worked on a broad range of topics and components of automatic speech recognition, including spoken-dialogue systems, recognition …

Conversational Recommendation System with Unsupervised Learning
Y Sun, Y Zhang, Y Chen, R Jin – … of the 10th ACM Conference on …, 2016 – dl.acm.org
… IMPLEMENTATION Our system has several major components, as shown in Figure 1. Most of the components are similar to a typical dialogue system, except that … The second solution is based on a deep learning model (ie a sequence to sequence language generation model). …

Recent Advances on Human-Computer Dialogues
X Wang, C Yuan – CAAI Transactions on Intelligence Technology, 2016 – Elsevier
… It is attractive to jointly model all subtasks of a dialogue system, from NLU, DM to NLG. … With the recent advances of sequence-to-sequence models in machine translation, some sequence-to-sequence models for non-goal-driven dialogue were also proposed. …

LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues
P Le, M Dymetman, JM Renders – arXiv preprint arXiv:1605.01652, 2016 – arxiv.org
… The ap- proach is reminiscent of seq2seq models for ma- chine translation such as (Sutskever et al., 2014), where the role of “source sentence” is played by the dialogue prefix, and that of “target … Spoken Dialogue Systems. … Sequence to sequence learning with neural networks. …

Multi-domain joint semantic frame parsing using bi-directional RNN-LSTM
D Hakkani-Tür, G Tur, A Celikyilmaz… – Proceedings of The …, 2016 – csie.ntu.edu.tw
… [34] I. Sutskever, O. Vinyals, and QV Le, “Sequence to sequence learning with neural … [40] T.-H. Wen, M. Gasic, N. Mrksic, P.-H. Su, D. Vandyke, and S. Young, “Semantically conditioned LSTM-based natural lan- guage generation for spoken dialogue systems,” arXiv preprint …

The DialPort Portal: Grouping Diverse Types of Spoken Dialog Systems
T Zhao, K Lee, M Eskenazi – workshop.colips.org
… In: Natural Language Dialog Systems and Intelligent Assistants, pp. 53–61. Springer (2015) 15. Sutskever, I., Vinyals, O., Le, QV: Sequence to sequence learning with neural networks. In: Advances in neural information processing systems. pp. 3104–3112 (2014) 16. …

Incorporating Loose-Structured Knowledge into LSTM with Recall Gate for Conversation Modeling
Z Xu, B Liu, B Wang, C Sun, X Wang – arXiv preprint arXiv:1605.05110, 2016 – arxiv.org
… the con- versation as a sequence of short texts, some stud- ies introduce Neural Network based Sequence-to- Sequence (S2S) framework to … users’ context-aware queries and further select best answers based on the conversation his- tory, for building automatic dialog systems. …

USTC at NTCIR-12 STC Task
J Zhang, J Hou, S Zhang, L Dai – research.nii.ac.jp
… To build a traditional dialogue system which contains several components[1], a lot of related technologies have been de- veloped such as dialogue state … 2.2.1 EncDec-Forward and EncDec-Reverse model Seq2seq model is a well-known end-to-end neural network model[9, …

Automatic Correction of ASR outputs by Using Machine Translation
LF D’Haro, RE Banchs – 2016 – researchgate.net
… [7] Morbini, F., Audhkhasi, K., Sagae, K., Artstein, R., Can, D., Georgiou, P., & Traum, D. (2013). Which ASR should I choose for my dialogue system? Proc. SIGDIAL, August. … [13] Sutskever, I., Vinyals, O., & Le, QV (2014). Sequence to sequence learning with neural networks. …

Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
G Barzdins, S Renals, D Gosko – arXiv preprint arXiv:1604.01221, 2016 – arxiv.org
… mechanism with the sliding-window mechanism and operate the sequence to sequence neural translation … words automatically disables also the sampled softmax functionality of seq2seq improving the … networks, which is already applied in the neural dialogue systems such as …

Neural Networks for Natural Language Processing
L Mou – sei.pku.edu.cn
“… [22] Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. “”Sequence to sequence learning with … corpus) ? Predicting phrase: X, Y, and Z are those generated by RNN ? Seq2seq model is essentially an LM (of XYZ) conditioned on … In a dialogue system, “The nature of of opendomain …

Personified Autoresponder
A Mahendra – cs224d.stanford.edu
“… in [Kum+15]. Unlike Seq2Seq model [Cho+14], Kumar et al. … 2014. [SVL14] Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. “Sequence to Sequence Learning with Neural Networks”. … “Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models”. …

Cuni system for wmt16 automatic post-editing and multimodal translation tasks
J Libovický, J Helcl, M Tlustý, P Pecina… – arXiv preprint arXiv: …, 2016 – arxiv.org
… [Sutskeveretal.2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. … 2015. Semantically conditioned lstm-based natural language generation for spoken dialogue systems. …

Chinese poetry generation with planning based neural network
Z Wang, W He, H Wu, H Wu, W Li, H Wang… – arXiv preprint arXiv: …, 2016 – arxiv.org
… considered as a sequence-to-sequence mapping problem with a slight difference that the input consists of two different kinds of sequences: the … How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. …

Generating Paraphrases from DBPedia using Deep Learning
A Sleimi, C Gardent – WebNLG 2016, 2016 – webnlg2016.sciencesconf.org
… 3 Learning To learn a sequence-to-sequence model that can generate sentences from RDF data, we use the neural model described in (Sutskever et al., 2011) and the code … 2015. Semantically conditioned ltsm-base natural lan- guage generation for spoken dialogue systems. …

1 Adaptability: Trainable end-to-end Natural Language Generation systems
I Konstas – ikonstas.net
“… An interesting approach would be to introduce to the original sequence to sequence architecture an 4 … Existing dialogue systems currently fall under two extremes: (a) they are either confined to very small domains, eg, booking hotels or giving directions and recommendations, (b …

Assisting discussion forum users using deep recurrent neural networks
JHP Suorra, O Mogren – Proceedings of the 1st Workshop on …, 2016 – aclweb.org
… 2016. Building end-to-end dialogue systems using gener- ative hierarchical neural network models. In Dale Schuurmans and Michael P. Wellman, editors, AAAI, pages 3776–3784. AAAI Press. … 2014. Sequence to sequence learning with neural net- works. …

RACAI Entry for the IWSLT 2016 Shared Task
S Pipa, AF Vasile, I Ionascu… – Proceedings of the …, 2016 – workshop2016.iwslt.org
… is extremely important for automatic machine translation (MT), speech-to-speech translation, information extraction, dialog systems, etc. … Kusner et al., 2015; Lai et al., 2015), sentiment analysis (Zhang et al., 2015), machine translation (sequence to sequence models) (Sutskever …

Natural Language Generation through Character-Based RNNs with Finite-State Prior Knowledge
R Goyal, M Dymetman, E Gaussier, U LIG – pdfs.semanticscholar.org
… (2015) in the context of a dialog system, where the input semantic … 3To emphasize this point, let us note that, in standard word-based seq2seq RNNs, the input and output vocabularies are totally disjoint. … 2014. Sequence to sequence learning with neural networks. …

“A Simple, Fast Diverse Decoding Algorithm for Neural Generation”
J Li, W Monroe, D Jurafsky – arXiv preprint arXiv:1611.08562, 2016 – arxiv.org
… 11log p(Y |X) is trained in a similar way as standard SEQ2SEQ models with only sources and targets being swapped. … We trained neural SEQ2SEQ models (Sutskever et al., 2014) with atten- tion (Luong et al., 2015; Cho et al., 2014). …

Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
B Liu, I Lane – arXiv preprint arXiv:1609.01462, 2016 – arxiv.org
… proposed joint model can be further extended for belief track- ing in dialogue systems when considering the dia- logue history beyond the current utterance. More- over, it can be used as the RNN decoder in an end-to-end trainable sequence-to-sequence speech recognition …

Controlling output length in neural encoder-decoders
Y Kikuchi, G Neubig, R Sasano, H Takamura… – arXiv preprint arXiv: …, 2016 – arxiv.org
… tailored them to the sentence sum- marization task. Rush et al. (2015) were the first to pose sentence summarization as a new target task for neural sequence-to- sequence learning. Several studies have used this task as one …

Assisting Discussion Forum Users using Deep Recurrent Neural Networks
J Suorra Hagstedt P, O Mogren – Proceedings of the …, 2016 – publications.lib.chalmers.se
… 2016. Building end-to-end dialogue systems using gener- ative hierarchical neural network models. In Dale Schuurmans and Michael P. Wellman, editors, AAAI, pages 3776–3784. AAAI Press. … 2014. Sequence to sequence learning with neural net- works. …

Context-aware Natural Language Generation for Spoken Dialogue Systems
H Zhou, M Huang, X Zhu – aclweb.org
… While these methods are not suitable for task-solving scenarios (for instance, dialogue systems for restaurant and hotel reservation), which … The Context-Aware LSTM (CA-LSTM) is built on the general encoder-decoder framework for sequence-to-sequence learning (Sutskever …

Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling
G Kurata, B Xiang, B Zhou, M Yu – arXiv preprint arXiv:1601.01530, 2016 – arxiv.org
… 2015. Deep contextual language under- standing in spoken dialogue systems. In Proc. INTER- SPEECH, pages 120–124. … 2016. Abstractive text summarization using sequence-to-sequence RNNs and beyond. In Proc. CoNLL. …

DialPort: Connecting the Spoken Dialog Research Community to Real User Data
T Zhao, K Lee, M Eskenazi – arXiv preprint arXiv:1606.02562, 2016 – arxiv.org
… outlook. In Natural Language Dialog Systems and Intelligent Assistants, pages 53–61. Springer. [Sutskeveretal.2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learn- ing with neural networks. …

Visual Fashion-Product Search at SK Planet
T Kim, S Kim, S Na, H Kim, M Kim, BK Jeon – arXiv preprint arXiv: …, 2016 – arxiv.org
… Building end-to-end dialogue systems using generative hierarchical neural network models. … CoRR, abs/1409.1556, 2014. Sutskever, Ilya, Vinyals, Oriol, and Le, Quoc V. Sequence to sequence learning with neural networks. …

RNN-based Encoder-decoder Approach with Word Frequency Estimation
J Suzuki, M Nagata – arXiv preprint arXiv:1701.00138, 2016 – arxiv.org
… [2014] question answering Xu et al. [2015], dialogue system Vinyals and Le [2015], Shang et al. … We leave this as our future work. 7. https://github.com/harvardnlp/seq2seq-attn … Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. Sequence to Sequence Learning with Neural Networks. …

Learning distributed representations of sentences from unlabelled data
F Hill, K Cho, A Korhonen – arXiv preprint arXiv:1602.03483, 2016 – arxiv.org
… Examples include machine translation (Sutskever et al., 2014), image captioning (Mao et al., 2015) and dialogue systems (Serban et al., 2015). … As with all sequence-to-sequence models, in train- ing the source sentence is ‘encoded’ by a Recurrent Neural Network (RNN) (with …

Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning
T Zhao, M Eskenazi – arXiv preprint arXiv:1606.02560, 2016 – arxiv.org
… at- tempts to develop end-to-end chat-oriented dialog systems that can directly map from the history of a conversation to the next system response (Vinyals and Le, 2015; Serban et al., 2015; Shang et al., 2015). These methods train sequence-to-sequence models (Sutskever et …

Neural Paraphrase Generation with Stacked Residual LSTM Networks
A Prakash, SA Hasan, K Lee, V Datla, A Qadir… – arXiv preprint arXiv: …, 2016 – arxiv.org
… Recently, techniques like sequence to sequence learning (Sutskever et al., 2014) have been applied to various NLP tasks with promising results, for … et al., 2015), speech recognition (Li and Wu, 2015), language modeling (Vinyals et al., 2015), and dialogue systems (Serban et al …

Strategy and policy learning for non-task-oriented conversational systems
Z Yu, Z Xu, AW Black, AI Rudnicky – 17th Annual Meeting of the Special …, 2016 – aclweb.org
… such as machine translation (Ritter et al., 2011), retrieval-based response se- lection (Banchs and Li, 2012), and sequence-to- sequence recurrent neural … In a stochastic envi- ronment, a dialog system’s actions are system ut- terances, and the state is represented by the dialog …

Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
R Al-Rfou, M Pickett, J Snaider, Y Sung… – arXiv preprint arXiv: …, 2016 – arxiv.org
… such as games (Narasimhan et al., 2015) and restaurants (Wen et al., 2016; Cuayáhuitl, 2016) Personalizing dialogue systems requires sufficient … With the introduction of the sequence-to- sequence framework (Sutskever et al., 2014), many recent learning systems have used …

Sequence-level knowledge distillation
Y Kim, AM Rush – arXiv preprint arXiv:1606.07947, 2016 – arxiv.org
… model. We have released all the code for the models described in this paper.2 1https://github.com/harvardnlp/nmt-android 2https://github.com/harvardnlp/seq2seq- attn 2 Background 2.1 Sequence-to-Sequence with Attention Let …

Natural language generation in dialogue using lexicalized and delexicalized data
S Sharma, J He, K Suleman, H Schulz… – arXiv preprint arXiv: …, 2016 – arxiv.org
… “Trainable Sentence Planning for Complex In- formation Presentations in Spoken Dialog Systems”. In: ACL, pp. 79–86. Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le (2014). “Sequence to Sequence Learning with Neural Net- works”. In: NIPS, pp. 3104–3112. …

Recurrent Memory Addressing for describing videos
KK Agrawal, AK Jain, A Agarwalla, P Mitra – arXiv preprint arXiv: …, 2016 – arxiv.org
… storing information ex- plicitly. In this paper, we generalize Key-Value Memory Networks to a multimodal setting, introducing a novel key- addressing mechanism to deal with sequence-to-sequence models. The advantages of …

Definition Modeling: Learning to define word embeddings in natural language
T Noraset, C Liang, L Birnbaum, D Downey – arXiv preprint arXiv: …, 2016 – arxiv.org
… Wen et al. 2015a) are also re- lated to our work, in that a sequence of words is gener- ated from a single input vector. Our model architectures are inspired by sequence-to-sequence models (Cho et al. 2014; Sutskever, Vinyals …

Implicit distortion and fertility models for attention-based encoder-decoder NMT model
S Feng, S Liu, M Li, M Zhou – arXiv preprint arXiv:1601.03317, 2016 – arxiv.org
… The decoder will stop once a special symbol denot- ing the end of the sentence is generated. This encoder-decoder framework can be used on gen- eral sequence-to-sequence tasks (Sutskever et al., †Work done while Shi was an intern at Microsoft Re- search. …

Controlling the voice of a sentence in japanese-to-english neural machine translation
H Yamagishi, S Kanouchi, T Sato… – Proceedings of the 3rd …, 2016 – aclweb.org
… The proposed method can be adapted to any sequence-to-sequence model because it does not depend on the network structure. … For example, one may prefer a polite expression for generating conversation in a dialog system. …

Coupling Distributed and Symbolic Execution for Natural Language Queries
L Mou, Z Lu, H Li, Z Jin – arXiv preprint arXiv:1612.02741, 2016 – arxiv.org
… [2016] apply sequence- to-sequence (seq2seq) neural models to generate a … However, seq2seq models need strong supervision of groundtruth logic forms, which are … A network-based end-to-end trainable task- oriented dialogue system. arXiv preprint arXiv:1604.04562, 2016. …

Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
J Kabbara, JCK Cheung – EMNLP 2016, 2016 – aclweb.org
… 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems, pages 3104–3112. … 2015. Seman- tically conditioned lstm-based natural language gener- ation for spoken dialogue systems. …

Length bias in Encoder Decoder Models and a Case for Global Conditioning
P Sountsov, S Sarawagi – arXiv preprint arXiv:1606.03402, 2016 – arxiv.org
… We use y1,…,yn to denote the tokens in a sequence y. Each yi is a discrete symbol from a finite dictionary V of size m. Typically, m is large. The length n of a se- quence is allowed to vary from sequence to sequence even for the same input x. A special token EOS ? V …

Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation
S Feng, S Liu, N Yang, M Li, M Zhou, KQ Zhu – aclweb.org
… 2014. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems, pages 3104–3112. … 2015. Se- mantically conditioned lstm-based natural language generation for spoken dialogue systems. arXiv preprint arXiv:1508.01745. …

Video paragraph captioning using hierarchical recurrent neural networks
H Yu, J Wang, Z Huang, Y Yang… – Proceedings of the IEEE …, 2016 – cv-foundation.org
… handled by a video captioning method. The overall structure of an image captioner (instance-to- sequence) is also usually simpler than that of a video cap- tioner (sequence-to-sequence). Some other methods, such as Park …

Study on Optimal Spoken Dialogue System for Robust Information Search in the Real World
?? – 2016 – eprints.lib.hokudai.ac.jp
“… Latent Dirichlet Allocation for modeling text documents topics [18] • Sequence-to-sequence models for machine translation [19] 2.2.3 Dialogue Management … Page 26. Chapter 2. Key Technologies of Spoken Dialogue Systems and Related Works 13 …

DeepSoft: A vision for a deep model of software
HK Dam, T Tran, J Grundy, A Ghose – Proceedings of the 2016 24th ACM …, 2016 – dl.acm.org
… Given the recent successes in NLP [5] (machine translation, question answering, and dialog systems) and vi- sion [4] (image/video captioning/story telling and more re- cently, visual question answering), it is expected that the … Sequence to sequence learning with neural networks …

End-to-end memory networks with knowledge carryover for multi-turn spoken language understanding
YN Chen, D Hakkani-Tür, G Tur, J Gao… – Proceedings of …, 2016 – microsoft.com
… In the past decades, goal-oriented spoken dialogue systems (SDS) are being incorporated in various devices and allow users to speak to systems in order to finish tasks more efficiently, for example … [32] I. Sutskever, O. Vinyals, and QV Le, “Sequence to sequence learning with …

Neural Dialog State Tracker for Large Ontologies by Attention Mechanism
Y Jang, J Ham, BJ Lee, Y Chang… – IEEE Workshop on …, 2016 – ailab.kaist.ac.kr
… networks for multi-topic dialog state tracking,” in Pro- ceedings of the 7th International Workshop on Spoken Dialogue Systems (IWSDS), 2016 … 14] Jiatao Gu, Zhengdong Lu, Hang Li, and Victor OK Li, “Incorporating copying mechanism in sequence-to- sequence learning,” CoRR …

Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
B Liu, I Lane – arXiv preprint arXiv:1609.01454, 2016 – arxiv.org
… Using a joint model for the two SLU tasks simplifies the dialog system, as only one model needs to be trained and deployed. … IEEE, 2013, pp. 78–83. [10] I. Sutskever, O. Vinyals, and QV Le, “Sequence to sequence learning with neural networks,” in Advances in neural …

Few-Shot Object Recognition from Machine-Labeled Web Images
Z Xu, L Zhu, Y Yang – arXiv preprint arXiv:1612.06152, 2016 – arxiv.org
… LSTMs have resurged due to the success of sequence to sequence modeling [33] on machine translation [3], image caption- ing [39, 20, 42], video classification [43], video caption- ing [35, 28], etc. Following the notations of Zaremba et al. [44] and Xu et al. [42] and assuming xt …

Shall I Be Your Chat Companion?: Towards an Online Human-Computer Conversation System
R Yan, Y Song, X Zhou, H Wu – … of the 25th ACM International on …, 2016 – dl.acm.org
… Recently, with the fast development of deep learning techniques, efforts are devoted in the neural network-based conversation sys- tems. A neural conversation model is proposed using a sequence- to-sequence manner [33]. …

Context-Sensitive and Role-Dependent Spoken Language Understanding using Bidirectional and Attention LSTMs
C Hori, T Hori, S Watanabe, JR Hershey – Interspeech 2016, 2016 – merl.com
… Spoken language under- standing (SLU) technologies in dialog systems have been inten- sively investigated to estimate the intention of user utterances obtained from an automatic speech … [10] I. Sutskever, O. Vinyals, and QV Le, “Sequence to sequence learning with neural …

“China Brain Project: basic neuroscience, brain diseases, and brain-inspired computing”
M Poo, J Du, NY Ip, ZQ Xiong, B Xu, T Tan – Neuron, 2016 – Elsevier
… In natural langue processing, an LSTM-based sequence-to-sequence model for machine translation almost reaches the human interpreter level … meet great challenges for more open and ill-defined tasks like natural language understanding, human dialog system, general visual …

Deep Reinforcement Learning for Multi-Domain Dialogue Systems
H Cuayáhuitl, S Yu, A Williamson, J Carse – arXiv preprint arXiv: …, 2016 – arxiv.org
… 20] trains RNN-based classifiers for predicting dialogue success in multi-domain dialogue systems, which can … Other neural-based conversational agents have been applied to text prediction using the sequence-to-sequence approach [19, 21], and to reasoning with inference for …

Dialogue Act Classification in Domain-Independent Conversations Using a Deep Recurrent Neural Network
H Khanpour, N Guntakandla, R Nielsen – aclweb.org
… Many applications benefit from the use of automatic dialogue act classi- fication such as dialogue systems, machine translation, Automatic Speech Recognition (ASR), topic identification, and talking avatars (Král and Cerisara … Sequence to sequence learning with neural networks …

“Your Paper has been Accepted, Rejected, or Whatever: Automatic Generation of Scientific Paper Reviews”
A Bartoli, A De Lorenzo, E Medvet, F Tarlao – International Conference on …, 2016 – Springer
… Wen, TH, Gasic, M., Mrkši?, N., Su, PH, Vandyke, D., Young, S.: Semantically conditioned LSTM-based natural language generation for spoken dialogue systems, pp. 1711–1721, September 2015. 17. Sutskever, I., Vinyals, O., Le, QV: Sequence to sequence learning with neural …

“Text analytics in industry: Challenges, desiderata and trends”
A Ittoo, LM Nguyen, A van den Bosch – Computers in Industry, 2016 – Elsevier
The recent decades have witnessed an unprecedented expansion in the volume of unstructured data in digital textual formats. Companies are now starting to recogn.

Reading Comprehension using Entity-based Memory Network
X Wang, K Sudoh, M Nagata, T Shibata… – arXiv preprint arXiv: …, 2016 – arxiv.org
… arXiv:1412.3555 (2014) 3. Dodge, J., Gane, A., Zhang, X., Bordes, A., Chopra, S., Miller, A., Szlam, A., Weston, J.: Evaluating prerequisite qualities for learning end-to-end dialog systems. … Sutskever, I., Vinyals, O., Le, QV: Sequence to sequence learning with neural networks. …

Multi-view response selection for human-computer conversation
X Zhou, D Dong, H Wu, S Zhao, R Yan, D Yu, X Liu… – EMNLP’16, 2016 – ir.hit.edu.cn
… Vinyals and Le (2015) re- garded single-turn conversation as a sequence-to- sequence problem and proposed an encoder-decoder based response generation model, where the post re- sponse is first encoded using LSTM and its embed- ding used as the initialization state of …

Neural Emoji Recommendation in Dialogue Systems
R Xie, Z Liu, R Yan, M Sun – arXiv preprint arXiv:1612.04609, 2016 – arxiv.org
… Page 7. We will explore more flexible emoji recommendation meth- ods in dialogue systems with emoji positions and coherence into consideration, making communications more natural and lively. … Sequence to sequence learning with neu- ral networks. …

Characters who speak their minds: Dialogue generation in Talk of the Town
J Ryan, M Mateas, N Wardrip-Fruin – Proc. AIIDE, 2016 – researchgate.net
… Bot Colony also employs a traditional NLG pipeline—a first for a commercially re- leased title—particularly one in the style of service-based dialogue systems, made possible by … CFGs-2-NLU: Sequence-to-sequence learn- ing for mapping utterances to semantics and …

Sequence-based structured prediction for semantic parsing
C Xiao, M Dymetman, C Gardent – Proceedings Association For …, 2016 – aclweb.org
Page 1. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1341–1350, Berlin, Germany, August 7-12, 2016. cO2016 Association for Computational Linguistics Sequence-based Structured Prediction for Semantic Parsing …

A survey of voice translation methodologies—Acoustic dialect decoder
H Krupakar, K Rajvel, B Bharathi… – Information …, 2016 – ieeexplore.ieee.org
… 1–35, 2015. [26] A. Graves, “Generating sequences with recurrent neural networks,” arXiv Prepr. arXiv1308.0850, pp. 1–43, 2013. [27] I. Sutskever, O. Vinyals, and Q. V Le, “Sequence to sequence learning with neural networks,” Adv. Neural Inf. Process. Syst., pp. …

A Wizard-of-Oz Study on A Non-Task-Oriented Dialog Systems That Reacts to User Engagement
Z Yu, L Nicolich-Henkin, AW Black… – 17th Annual Meeting of …, 2016 – aclweb.org
… cO2016 Association for Computational Linguistics A Wizard-of-Oz Study on A Non-Task-Oriented Dialog Systems That Reacts to … as machine translation (Ritter et al., 2011), retrieval-based response selection (Banchs and Li, 2012), and sequence-to-sequence recurrent neural …

Response Selection with Topic Clues for Retrieval-based Chatbots
Y Wu, W Wu, Z Li, M Zhou – arXiv preprint arXiv:1605.00090, 2016 – arxiv.org
… Although previous research on conversation focused on dialog systems, recently, with the large amount of con- versation data … based methods employ statistical machine translation techniques (Ritter, Cherry, and Dolan 2011) or the sequence to sequence framework (Shang, Lu …

A neural knowledge language model
S Ahn, H Choi, T Pärnamaa, Y Bengio – arXiv preprint arXiv:1608.00318, 2016 – arxiv.org
… understanding. Beyond its usage as a standalone application, it has been an indispensable component in many language/speech tasks such as speech recognition [26, 1], machine translation [17], and dialogue systems [40, 34]. …

Situated Intelligent Interactive Systems
Z Yu – 2016 – cs.cmu.edu
“… My work is also novel in dynamically augmenting a personalized knowledge base for dialog systems that provides a personalized experience for each user [Yu et al., 2016f]. I used … sequence-to-sequence models also contributed in generating coherent response to simulate …

Ranking Responses Oriented to Conversational Relevance in Chat-bots
B Wu, B Wang, H Xue – aclweb.org
… 2015. Building end-to- end dialogue systems using generative hierarchical neural network models. arXiv preprint arXiv:1507.04808. … 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems, pages 3104–3112. …

Gaussian Attention Model and Its Application to Knowledgebase Embedding and Question Answering
L Zhang, J Winn, R Tomioka – arXiv preprint arXiv:1611.02266, 2016 – arxiv.org
Page 1. Under review as a conference paper at ICLR 2017 GAUSSIAN ATTENTION MODEL AND ITS APPLICATION TO KNOWLEDGE BASE EMBEDDING AND QUESTION ANSWERING Liwen Zhang Department of Computer …

Syntax or semantics? knowledge-guided joint semantic frame parsing
YN Chen, D Hakanni-Tür, G Tur, A Celikyilmaz, J Guo… – 2016 – csie.ntu.edu.tw
… microsoft.com ABSTRACT Spoken language understanding (SLU) is a core component of a spo- ken dialogue system, which involves intent prediction and slot filling and also called semantic frame parsing. Recently recurrent …

Seqgan: sequence generative adversarial nets with policy gradient
L Yu, W Zhang, J Wang, Y Yu – arXiv preprint arXiv:1609.05473, 2016 – arxiv.org
Page 1. SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient Lantao Yu†, Weinan Zhang†, Jun Wang‡, Yong Yu† †Shanghai Jiao Tong University, ‡University College London {yulantao,wnzhang,yyu}@apex.sjtu.edu.cn, j.wang@cs.ucl.ac.uk Abstract …

Detecting Context Dependent Messages in a Conversational Environment
C Li, Y Wu, W Wu, C Xing, Z Li, M Zhou – arXiv preprint arXiv:1611.00483, 2016 – arxiv.org
… Differing from traditional dialogue systems (cf., (Young et al., 2013)) which rely on hand-crafted features and rules to generate reply sentences for specific applications such as voice dialling (Williams, 2008) and ap- pointment scheduling (Janarthanam et al., 2011) etc., recent …

Knowledge as a teacher: Knowledge-guided structural attention networks
YN Chen, D Hakkani-Tur, G Tur, A Celikyilmaz… – arXiv preprint arXiv: …, 2016 – arxiv.org
… Abstract Natural language understanding (NLU) is a core component of a spoken dialogue system. Recently … 1 Introduction In the past decade, goal-oriented spoken dialogue systems (SDS), such as the virtual personal assis- tants …

Contextual LSTM (CLSTM) models for Large scale NLP tasks
S Ghosh, O Vinyals, B Strope, S Roy, T Dean… – arXiv preprint arXiv: …, 2016 – arxiv.org
… This has impli- cations for a wide variety of NL applications like question answering, sentence completion, paraphrase generation, and next utterance prediction in dialog systems. … This can be used in various applications in dialog systems, eg, intent modeling. …

Sequential Match Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
Y Wu, W Wu, M Zhou, Z Li – arXiv preprint arXiv:1612.01627, 2016 – arxiv.org
… and an input message with or without context (Hu et al., 2014; Ji et al., 2014; Wang et al., 2015; Yan et al., 2016; Wu et al., 2016; Zhou et al., 2016), while the latter employs statistical machine translation techniques (Ritter et al., 2011) or the sequence to sequence framework …

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
IV Serban, A Sordoni, R Lowe, L Charlin… – arXiv preprint arXiv: …, 2016 – arxiv.org
… In NAACL-HLT. [28] Sutskever, I., Vinyals, O., and Le, QV (2014). Sequence to sequence learning with neural networks. In NIPS, pages 3104–3112. [29] Young, S., Gasic, M., Thomson, B., and Williams, JD (2013). POMDP-based statistical spoken dialog systems: A review. …

Compositional Sentence Representation from Character within Large Context Text
G Kim, H Lee, J Choi, S Lee – arXiv preprint arXiv:1605.00482, 2016 – arxiv.org
… The HCRN was tested on a spoken dialogue act classification task. The dialogue act (DA) is the communicative intention of a speaker for each sen- tence. Prediction of the DA can be further used as an input to modules in dialogue systems such as dialogue manager. …

Multimodal Memory Modelling for Video Captioning
J Wang, W Wang, Y Huang, L Wang, T Tan – arXiv preprint arXiv: …, 2016 – arxiv.org
… These memory networks have been successfully applied to the tasks which need long-term dependency modelling, eg, textual ques- tion answering [3, 14], visual question answering [39] and dialog systems [8]. As we know, few memory models have been proposed for video …

Deep learning in the automotive industry: Applications and tools
A Luckow, M Cook, N Ashcraft, E Weill… – Big Data (Big Data), …, 2016 – ieeexplore.ieee.org
… Deep learning is extensively used by many online and mobile services, such as the voice recognition and dialog systems of Siri, the Google Assistant, Amazon’s Alexa and Microsoft Cortana, as well as the image classification systems in Google Photo and Facebook. …

End-to-end reinforcement learning of dialogue agents for information access
B Dhingra, L Li, X Li, J Gao, YN Chen, F Ahmed… – arXiv preprint arXiv: …, 2016 – arxiv.org
… All components of the KB- InfoBot are trained in an end-to-end fashion using reinforcement learning. Goal-oriented dialogue systems typically need to interact with an external database to access real-world knowledge (eg, movies playing in a city). …

Log-linear rnns: Towards recurrent neural networks with flexible prior knowledge
M Dymetman, C Xiao – arXiv preprint arXiv:1607.02467, 2016 – arxiv.org
Page 1. Log-Linear RNNs : Towards Recurrent Neural Networks with Flexible Prior Knowledge (Version 1.0) Marc Dymetman Chunyang Xiao Xerox Research Centre Europe, Grenoble, France {marc.dymetman,chunyang.xiao}@xrce.xerox.com Monday 11th July, 2016 Abstract …

Summarizing source code using a neural attention model
S Iyer, I Konstas, A Cheung, L Zettlemoyer – … of the 54th Annual Meeting of the … – aclweb.org
… Perhaps most closely related, Wen et al. (2015) generate text for spoken dialogue systems with a two-stage approach, comprising an LSTM decoder seman- tically conditioned on the logical representation of speech acts, and a reranker to generate the fi- nal output. …

Globally Coherent Text Generation with Neural Checklist Models
CKLZY Choi – aclweb.org
“… Evaluations on cooking recipes and dialogue system responses demonstrate high coherence with greatly improved semantic coverage of the agenda. 1 Introduction … (2016) present neural network models for generating dialogue system responses given a set of agenda items. …

Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
P Wiriyathammabhum, D Summers-Stay… – ACM Computing …, 2016 – dl.acm.org
Page 1. 71 Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics PERATHAM WIRIYATHAMMABHUM, University of Maryland, College Park DOUGLAS SUMMERS-STAY, US …

Learning to respond with deep neural networks for retrieval-based human-computer conversation system
R Yan, Y Song, H Wu – Proceedings of the 39th International ACM SIGIR …, 2016 – dl.acm.org
Page 1. Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System Rui Yan Baidu Inc. No. 10, Xibeiwang East Road, Beijing 100193, China yanrui02@baidu.com Yiping Song Baidu Inc. No. …

GuessWhat?! Visual object discovery through multi-modal dialogue
H de Vries, F Strub, S Chandar, O Pietquin… – arXiv preprint arXiv: …, 2016 – arxiv.org
… Abstract We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. … Although goal-directed dialogue systems are appeal- ing, they remain hard to design. …

“Seeing is believing: the quest for multimodal knowledge by Gerard de Melo and Niket Tandon, with Martin Vesely as coordinator”
G de Melo, N Tandon – ACM SIGWEB Newsletter, 2016 – dl.acm.org
… In speech recognition, markedly lower error rates have enabled powerful dialog systems, including Siri on Apple’s iOS, Alexa for Amazon Echo, and various others powering advanced customer support services. … Sequence to sequence – video to text. …

An Exploratory Study on Process Representations
CN Naik – 2016 – search.proquest.com
“… many potential applications in NLP and have been shown to benet question answering [7, 8], textual entailment [9], machine translation [1012], and dialogue systems [13, 14 … We aim to build a role classier using sequence-to-sequence models without any feature engineering. …

Character Modeling through Dialogue for Expressive Natural Language Generation
G Lin – 2016 – escholarship.org
“… scripts from the IMSDb website. A derived corpus, Movie-Triples [Serban et al., 12 Page 27. 2015b], was created to build end-to-end dialogue systems with recurrent neural networks (RNN) and n-gram models. It contains dialogue of 3 turns between …

Multi-behavioral Sequential Prediction for Collaborative Filtering
Q Liu, S Wu, L Wang – arXiv preprint arXiv:1608.07102, 2016 – pdfs.semanticscholar.org
Page 1. Multi-behavioral Sequential Prediction for Collaborative Filtering Qiang Liu, Shu Wu, Liang Wang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR …

Neural Network Approaches to Dialog Response Retrieval and Generation
NIO Lasguido, S Sakti, G Neubig… – … on Information and …, 2016 – search.ieice.org
… Natural language dialogue systems promise to establish ef- ficient interfaces for communication between humans and computers [1]–[5]. One way to create a simple yet effec- tive dialog system is using example-based dialog modeling (EBDM) [6]–[9]. EBDM is a data-driven …

Constructing a Natural Language Inference Dataset using Generative Neural Networks
J Starc, D Mladeni? – arXiv preprint arXiv:1607.06025, 2016 – arxiv.org
… neutral Table 1: Three NLI examples from SNLI. 2014), image caption generation(Xu et al., 2015), or dialogue systems (Serban et al., 2016a). Another type of generative models are autoencoders that generate a stream of random samples from the original distribution. …

“1. Continuously Improving Natural Language Understanding for Robotic Systems through Semantic Parsing, Dialog, and Multi-modal Perception”
J Thomason – 2016 – pdfs.semanticscholar.org
“… [2014], Lu and Chen [2015]). Recent work angles to translate human instructions directly to grounded behavior like route- following, skipping parsing in favor of sequence-to-sequence, instruction-to-action mapping using neural methods (Mei et al. [2016]). …

Designing Regularizers and Architectures for Recurrent Neural Networks
D Krueger – 2016 – papyrus.bib.umontreal.ca
“Page 1. Université de Montréal Designing Regularizers and Architectures for Recurrent Neural Networks par David Krueger Département d’informatique et de recherche opérationnelle Faculté des arts et des sciences Mémoire …

Large-scale affective computing for visual multimedia
B Jou – 2016 – search.proquest.com
“Large-scale affective computing for visual multimedia. Abstract. In recent years, Affective Computing has arisen as a prolific interdisciplinary field for engineering systems that integrate human affections. While human-computer …

Learning Open Domain Knowledge From Text
GG Angeli – 2016 – nlp.stanford.edu
“Page 1. LEARNING OPEN DOMAIN KNOWLEDGE FROM TEXT A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY …