Natural Language Generation, Deep Neural Networks & Dialog Systems 2017


References:

See also:

100 Best Natural Language Generation Videos | Combinatory Categorial Grammar & Natural Language Generation | Context-Free Grammar & Natural Language Generation | DNN (Deep Neural Network) & Human Language Technology 2017 | Grammar Parsing & Natural Language Generation | Gutenberg Corpus & Natural Language Generation | Natural Language Generation Pipeline | NLTK & Natural Language Generation 2017 | OWL Ontology & Natural Language Generation 2017


Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation.
IV Serban, T Klinger, G Tesauro, K Talamadupula… – AAAI, 2017 – aaai.org
… 2016). However, these models have not been applied to natural language generation … Evaluation Methods It has long been known that accurate evaluation of dialogue system responses is difficult (Schatzmann, Georgila, and Young 2005). Liu et al …

GuessWhat?! Visual object discovery through multi-modal dialogue
H De Vries, F Strub, S Chandar, O Pietquin… – Proc. of …, 2017 – openaccess.thecvf.com
… introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems … Thanks to advances in training deep neural networks [14] and the availability of large-scale classification datasets [24, 33, 47], automatic …

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient.
L Yu, W Zhang, J Wang, Y Yu – AAAI, 2017 – aaai.org
… to represent a data instance in a latent hidden space (Kingma and Welling 2014), while still utilizing (deep) neural networks for non … little progress has been made in applying GANs to sequence discrete data generation prob- lems, eg natural language generation (Huszár 2015) …

Controllable text generation
Z Hu, Z Yang, X Liang, R Salakhutdinov… – arXiv preprint arXiv …, 2017 – arxiv.org
… Despite their impressive advances in visual domain, such as image generation (Radford et al., 2015), learning interpretable image representations (Chen et al., 2016), and image editing (Zhu et al., 2016), applications to natural language generation have been relatively less …

Deep reinforcement learning: An overview
Y Li – arXiv preprint arXiv:1701.07274, 2017 – arxiv.org
… been witnessing the renaissance of reinforcement learning (Krakovsky, 2016), especially, the combination of reinforcement learning and deep neural networks, ie, deep … Tamar et al., 2016), dual learning for machine translation (He et al., 2016a), spoken dialogue systems (Su et …

A knowledge-grounded neural conversation model
M Ghazvininejad, C Brockett, MW Chang… – arXiv preprint arXiv …, 2017 – arxiv.org
… This contrasts with traditional dialog systems, which can easily inject entities and facts into responses using slot- filling, but often at the cost of significant hand- coding, making such systems difficult to scale to new domains or tasks …

Deal or no deal? end-to-end learning for negotiation dialogues
M Lewis, D Yarats, YN Dauphin, D Parikh… – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. arXiv:1706.05125v1 [cs.AI] 16 Jun 2017 Deal or No Deal? End-to-End Learning for Negotiation Dialogues Mike Lewis1, Denis Yarats1, Yann N. Dauphin1, Devi Parikh2,1 and Dhruv Batra2,1 1Facebook AI Research …

Adversarial generation of natural language
S Rajeswar, S Subramanian, F Dutil, C Pal… – arXiv preprint arXiv …, 2017 – arxiv.org
… Deep neural networks have recently enjoyed some success at modeling natural language (Mikolov et al., 2010; Zaremba et al., 2014; Kim et al … for modeling images (Radford et al., 2015; Dumoulin et al., 2016), advances in their use for natural language generation has lagged be …

Toward controlled generation of text
Z Hu, Z Yang, X Liang… – International …, 2017 – proceedings.mlr.press
… interpretable image representations (Chen et al., 2016), and image editing (Zhu et al., 2016), applications to natural language generation have been … knowledge or human intentions (Hu et al., 2016a;b); or plug the disentangled generation model into dialog systems to generate …

Neural personalized response generation as domain adaptation
W Zhang, T Liu, Y Wang, Q Zhu – arXiv preprint arXiv:1701.02073, 2017 – arxiv.org
… Re- cently, as the powerful of deep neural network on learning from large-scale data, 13 … S. Young, Multi-domain neural network language generation for spoken dialogue systems, in: NAACL. 16 … conditioned lstm-based natural language generation for spoken dialogue systems …

Generative encoder-decoder models for task-oriented spoken dialog systems with chatting capability
T Zhao, A Lu, K Lee, M Eskenazi – arXiv preprint arXiv:1706.08476, 2017 – arxiv.org
… It encodes the dialog history using deep neural networks and then generates the next sys- tem … Sys- tem (Raux et al., 2005) is a task-oriented spoken dialog system that contains … has been a popular score used to evaluate the performance of natural language generation (Wen et …

Latent intention dialogue models
TH Wen, Y Miao, P Blunsom, S Young – arXiv preprint arXiv:1705.10229, 2017 – arxiv.org
… et al., 2014; Bahdanau et al., 2015), caption generation (Karpathy & Fei-Fei, 2015; Xu et al., 2015), and natural language generation (Wen et al … For exam- ple both goal-oriented dialogue systems (Wen et al., 2017; Bordes & Weston, 2017) and sequence-to-sequence learn- ing …

DeepTingle
A Khalifa, GAB Barros, J Togelius – arXiv preprint arXiv:1705.03557, 2017 – arxiv.org
… Natural Language Generation Natural language generation approaches can be divided into two categories: Rule- or template-based … proposes a two-part system, composed of a deep neural network trained over a … Stochastic language generation for spoken dialogue systems …

The technology behind personal digital assistants: an overview of the system architecture and key components
R Sarikaya – IEEE Signal Processing Magazine, 2017 – ieeexplore.ieee.org
Page 1. 67 IEEE SIgnal ProcESSIng MagazInE | January 2017 | 1053-5888/17©2017IEEE e have long envisioned that one day computers will understand natural language and anticipate what we need, when and where we need it, and proactively complete tasks on our behalf …

Effect of a Humanoid’s Active Role during Learning with Embodied Dialogue System
M Kerzel, HG Ng, S Griffiths, S Wermter – Proceedings of the Workshop – researchgate.net
… State-of-the-art learning approaches, such as deep neural networks [1], [2 … B. Spoken Dialogue Systems Spoken dialogue systems (SDS) [13] are modules in … Recognition, Spoken Language Understanding, Dialogue Management (DM), Natural Language Generation and Text-to …

Composite Task-Completion Dialogue System via Hierarchical Deep Reinforcement Learning
B Peng, X Li, L Li, J Gao, A Celikyilmaz, S Lee… – arXiv preprint arXiv …, 2017 – arxiv.org
… car_size= ? Text Input I’d like to book a flight to LA on 4/14. … Natural Language Generation(NLG) Semantic Frame Inform(arrive_city=LA, depart_flight_date=4/14) Dialogue System Dialogue Management (DM) System Action/Policy request_depart_city wi wi+1 …

Recurrent neural networks with missing information imputation for medical examination data prediction
HG Kim, GJ Jang, HJ Choi, M Kim… – Big Data and Smart …, 2017 – ieeexplore.ieee.org
… r. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, TN Sainath et al., “Deep neural networks for acoustic … N. Mrksic, P.-H. Su, D. Vandyke, and S. Young, “Semantically conditioned LSTM-based natural language generation for spoken dialogue systems,” arXiv preprint …

Affective Neural Response Generation
N Asghar, P Poupart, J Hoey, X Jiang, L Mou – arXiv preprint arXiv …, 2017 – arxiv.org
… Introduction Human-computer dialogue systems have wide applications ranging from restaurant booking (Wen et al. 2015) to emo- tional virtual agents (Malhotra et al. 2015). Inspired by the recent success of deep neural networks in natural lan- guage processing (NLP) tasks …

Automated Crowdturfing Attacks and Defenses in Online Review Systems
Y Yao, B Viswanath, J Cryan, H Zheng… – Proceedings of the 2017 …, 2017 – dl.acm.org
… workers [73]. But just as ML classifiers can effectively detect these attacks, advances in deep learning and deep neural networks (DNNs) can also serve to make these attacks much more powerful and diffi- cult to defend. Specifically …

Hybrid methodological approach to context-dependent speech recognition
D Miškovi?, M Gnjatovi?, P Štrbac… – International …, 2017 – journals.sagepub.com
Although the importance of contextual information in speech recognition has been acknowledged for a long time now, it has remained clearly underutilized even in…

En route to a better integration and evaluation of social capacities in vocal artificial agents
F Lefèvre – Proceedings of the 1st ACM SIGCHI International …, 2017 – dl.acm.org
… More recently attempts to introduce deep neural networks (DNN) in SDS have led to a … A methodology for turn-taking capabilities enhancement in Spoken Dialogue Systems using Reinforcement Learning … Automatic corpus extension for data-driven natural language generation …

The use of autoencoders for discovering patient phenotypes
H Suresh, P Szolovits, M Ghassemi – arXiv preprint arXiv:1703.07004, 2017 – arxiv.org
… Autoencoders deep neural networks where the target values are the same as the input values, and … natural language processing applications from machine translation [11] to dialogue systems [12] to … “Semantically conditioned lstm-based natural language generation for spoken …

Predicting head pose in dyadic conversation
D Greenwood, S Laycock, I Matthews – International Conference on …, 2017 – Springer
… [4] employed a Variational Autoencoder (VAE) for natural language generation … Ding, C., Xie, L., Zhu, P.: Head motion synthesis from speech using deep neural networks … Nishimura, R., Kitaoka, N., Nakagawa, S.: A spoken dialog system for chat-like conversations considering …

Redundancy localization for the conversationalization of unstructured responses
S Krause, M Kozhevnikov, E Malmi… – Proceedings of the 18th …, 2017 – aclweb.org
… world dialogue. 1 Introduction Recent years have seen a growing interest in re- search on conversational agents. Several strands of dialogue systems have emerged which differ in underlying goals and methods. Some systems …

Method for aspect-based sentiment annotation using rhetorical analysis
? Augustyniak, K Rajda, T Kajdanowicz – Asian Conference on Intelligent …, 2017 – Springer
… on the size of the rule-based system responsible for the completions of the text), or deep neural networks [21] … Wen, TH., Gasic, M., Mrksic, N., Su, PH., Vandyke, D., Young, S.: Semantically conditioned LSTM-based natural language generation for spoken dialogue systems …

Towards a top-down policy engineering framework for attribute-based access control
M Narouei, H Khanpour, H Takabi, N Parde… – Proceedings of the …, 2017 – dl.acm.org
… Next, the extracted sentences will be fed to the deep neural network classi er in order to build the network and make predictions … frequency in a variety of text processing applications, from sentiment analysis [41] to conversational text processing for dialogue systems [22, 48] …

Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
P Wiriyathammabhum, D Summers-Stay… – ACM Computing …, 2017 – 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 …

Open-Domain Neural Dialogue Systems
YN Chen, J Gao – Proceedings of the IJCNLP 2017, Tutorial Abstracts, 2017 – aclweb.org
… Natural Language Generation NLG ap- proaches can be grouped into two categories, one focuses on generating text using templates or rules (linguistic … End-to-End Task-Oriented Dialogue System Awaring the representation power of deep neural networks, there are more …

Text Generation Using Different Recurrent Neural Networks
P Taneja, KG Verma – 2017 – dspace.thapar.edu
Page 1. Text Generation Using Different Recurrent Neural Networks Thesis submitted in partial fulfillment of the requirements for the award of degree of Master of Engineering in Computer Science and Engineering Submitted by Partiksha Taneja (Roll No. 801532041) …

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
Z Lipton, X Li, J Gao, L Li, F Ahmed, L Deng – arXiv preprint arXiv …, 2017 – arxiv.org
… tick- arXiv:1711.05715v1 [cs.AI] 15 Nov 2017 Page 2. Language Understanding Natural Language Generation State Tracker Dialog Policy Figure 1: Components of a dialogue system ets, and ultimately completes a booking. A …

Image Description Using Deep Neural Network
AP Deshmukh, AS Ghotkar – 2017 – ijsrst.com
… a wide range of NLP applications such as machine translation, summarizing, dialogue systems and machine … Natural language generation still remains an open research problem … inspired by recent advances in the applications of Convolution deep neural networks and recurrent …

Achieving Fluency and Coherency in Task-oriented Dialog
R Gangadharaiah, BM Narayanaswamy, C Elkan – alborz-geramifard.com
… Advances in training deep neural networks has demonstrated the potential to build chatbots with … for many of the independent modules in traditional dialog systems, such as, the natural language understanding component, the natural language generation component, the …

Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning
B Peng, X Li, J Gao, J Liu, YN Chen… – arXiv preprint arXiv …, 2017 – arxiv.org
… that converts natural language to system-readable se- mantic frames, natural language generation (NLG) that … Marc Lanctot, et al., “Mastering the game of go with deep neural networks and tree … speeding up on-line policy learn- ing in spoken dialogue systems,” in Proceedings …

Adversarial generation of natural language
S Subramanian, S Rajeswar, F Dutil, C Pal… – Proceedings of the 2nd …, 2017 – aclweb.org
… Deep neural networks have recently enjoyed some success at modeling natural language (Mikolov et al … 2015; Dumoulin et al., 2016), advances in their use for natural language generation has lagged … in other domains of NLP such as non goal-oriented dialog systems where a …

Analysing the influence of semantic knowledge in natural language generation
C Barros, E Lloret – Digital Information Management (ICDIM) …, 2017 – ieeexplore.ieee.org
… development and improvement of chatbots [1]. The area of Natural Language Generation (NLG) aims … a broad range of contexts, such as text summarisation [3], dialog systems [4], generation … trend in generating LM based on deep learning (eg deep neural networks), these kind …

A retrieval-based dialogue system utilizing utterance and context embeddings
A Bartl, G Spanakis – arXiv preprint arXiv:1710.05780, 2017 – arxiv.org
… or just for the sake of enter- tainment [4]. The traditional design of Dialogue Systems [5] follows a modular approach, splitting the system usually into a Natural Language Understanding (NLU) module, a Dialogue Manager and a Natural Language Generation (NLG) unit …

Domain Transfer for Deep Natural Language Generation from Abstract Meaning Representations
N Dethlefs – IEEE Computational Intelligence Magazine, 2017 – ieeexplore.ieee.org
… In this article, we focus on the problem of domain adaptation for natural language generation … Meaning Representations Page 2. august 2017 | IEEE ComputatIonal IntEllIgEnCE magazInE 19 I. Introduction natural language generation (NLG) is the task of …

Cascaded LSTMs Based Deep Reinforcement Learning for Goal-Driven Dialogue
Y Ma, X Wang, Z Dong, H Chen – National CCF Conference on Natural …, 2017 – Springer
… A goal-driven dialogue system usually has three components [1]: Natural Language Understanding (NLU), Dialogue Management (DM), Natural Language Generation (NLG) … (2) A deep neural network (DNN) maps dialogue embeddings to the Q-values of different actions …

Unsupervised Automatic Text Style Transfer Using LSTM
M Han, O Wu, Z Niu – National CCF Conference on Natural Language …, 2017 – Springer
… [8] introduced a method to learn syntactically-informed paraphrases for natural language generation … Section 2 briefly introduces the Seq2Seq deep neural network model and existing studies … machine translation [1], speech recognition [18], and dialogue systems [27] producing …

Learning concepts through conversations in spoken dialogue systems
R Jia, L Heck, D Hakkani-Tür… – Acoustics, Speech and …, 2017 – ieeexplore.ieee.org
… [1] M. Henderson, B. Thomson, and SJ Young, “Deep Neural Network Approach for … Milica Gasic, Nikola Mrkšic, Pei-Hao Su, David Vandyke, and Steve Young, “Semantically conditioned lstm-based natural language generation for spoken dialogue systems,” in Proceedings …

A Survey on Dialogue Systems: Recent Advances and New Frontiers
H Chen, X Liu, D Yin, J Tang – arXiv preprint arXiv:1711.01731, 2017 – arxiv.org
… 2. TASK-ORIENTED DIALOGUE SYSTEMS Task-oriented dialogue systems have been an important branch of spoken dialogue systems. In this section, we will review pipeline and end-to-end methods for task-oriented dialogue systems … Natural language generation (NLG) …

An Integrated Framework for Multimodal Human-Robot Interaction
LF D’Haro, AI Niculescu, C Cai, S Nair, RE Banchs… – researchgate.net
… [4] Hinton, G., Deng, L., Yu, D., Dahl, GE, Mohamed, AR, Jaitly, N., & Kingsbury, B. “Deep neural networks for acoustic … K., Artstein, R., Can, D., Georgiou, P., & Traum, D. “Which ASR should I choose for my dialogue system?” Proc … “Building natural language generation systems” …

A Proposal to Enhance Human-Machine Interaction by Means of Multi-agent Conversational Interfaces
D Griol, AS de Miguel, JM Molina – International Conference on Hybrid …, 2017 – Springer
… companies have been making huge investments in research into technologies such as Artificial Intelligence, deep neural networks, machine learning … Let \(A_{i}\) be the output of the dialog system (the system answer) at time i, expressed in terms … Natural Language Generation …

Deep Learning for Dialogue Systems
YN Chen, A Celikyilmaz, D Hakkani-Tür – Proceedings of ACL 2017 …, 2017 – aclweb.org
… Natural Language Generation (NLG … 4 Deep Learning Based Dialogue System … Language Understanding With the advances on deep learning, deep belief networks (DBNs) with deep neural networks (DNNs) have been applied to domain and intent classification tasks (Sarikaya …

Bayes By Backprop Neural Networks for Dialogue Management
C Tegho – 2017 – pdfs.semanticscholar.org
… 1.6 Natural Language Generation and Speech Synthesis … In a dialogue system, the total number of turns needed to accurately estimate the optimal policy is large … Deep neural network models on the other hand scale well with data and are computationally less complex than GPs …

Multilingual spoken dialog systems for handheld devices
BML Srivastava – 2017 – researchgate.net
… Gaussian Mixture Model FF-DNN Feed Forward Deep Neural Network GMM Gaussian … Scaling MFCC Mel Frequency Cepstral Coefficients NLG Natural Language Generation PCA Principal … Model SDC Shifted Delta Coefficients SDS Spoken Dialog System SGD Stochastic …

A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
I Casanueva, P Budzianowski, PH Su, N Mrkši?… – arXiv preprint arXiv …, 2017 – arxiv.org
… belief state tracking and policy) and output processing modules (Natural Language Generation (NLG) and … Building end-to-end dialogue systems using generative hierarchical neural network models … Mas- tering the game of go with deep neural networks and tree search …

Big Data for Conversational Interfaces: Current Opportunities and Prospects
D Griol, JM Molina, Z Callejas – Big Data Management, 2017 – Springer
… Natural language generation is the process of obtaining sentences in natural language from the non-linguistic … From around 2010, Deep Neural Networks (DNNs) have replaced HMM models … Once the spoken dialog system has recognized what the user uttered, it is necessary to …

General Pipeline Architecture for Domain-Specific Dialogue Extraction from different IRC Channels
A Abouzeid – 2017 – content.grin.com
… on-one dialogues as pre-training sets that could be used with the Deep Neural Network … only an imagination. Typical architecture of Modern Dialogue Systems has five main … standing (NLU), (3) Dialogue Management (DM), (4) Natural Language Generation …

Response selection from unstructured documents for human-computer conversation systems
Z Yan, N Duan, J Bao, P Chen, M Zhou, Z Li – Knowledge-Based Systems, 2017 – Elsevier
… semantic matching techniques. Wang et al. [21] present a deep neural network model using tree structures as the input. However, collecting enough QR pairs is often intractable in many domain specific tasks. Compared to previous …

Learning Generative End-to-end Dialog Systems with Knowledge
T Zhao – 2017 – cs.cmu.edu
… MTL Multi-task Learning NLG Natural Language Generation NLP Natural Language Processing … End-to-end (E2E) generative dialog systems based on encoder-decoder deep neural networks [15, 92] are indeed one of the strongest candidates to satisfy the first property …

Miscommunication handling in spoken dialog systems based on error-aware dialog state detection
CH Wu, MH Su, WB Liang – EURASIP Journal on Audio, Speech, and …, 2017 – Springer
… December 2017 , 2017:9 | Cite as. Miscommunication handling in spoken dialog systems based on error-aware dialog state detection … Keywords. Error-aware dialog act Miscommunication Spoken dialog systems. Download fulltext PDF. 1 Introduction …

Deep reinforcement learning for conversational robots playing games
H Cuayahuitl – 2017 – eprints.lincoln.ac.uk
… [6] H. Cuayáhuitl, S. Yu, A. Williamson, and J. Carse. Scaling up deep reinforcement learning for multi-domain dialogue systems … Hierarchical reinforcement learning for situated natural language generation … Mastering the game of Go with deep neural networks and tree search …

Natural Language Processing, Moving from Rules to Data
AH Dediu, JM Matos, C Martín-Vide – International Conference on Theory …, 2017 – Springer
… natural language generation … that well-known IPAs like Apple Siri, Google Assistant, Microsoft Cortana, Amazon Echo, etc., marked a significant progress after 2012, mainly due to the recent advances in deep learning technologies [19] — especially deep neural networks (DNNs …

Incorporating Structural Bias into Neural Networks
Z Yang – 2017 – cs.cmu.edu
Page 1. November 2, 2017 DRAFT Thesis Proposal Incorporating Structural Bias into Neural Networks Zichao Yang Nov 2017 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee …

Remembering what you said: Semantic personalized memory for personal digital assistants
V Agarwal, OZ Khan, R Sarikaya – Acoustics, Speech and …, 2017 – ieeexplore.ieee.org
… tion of successful referring expressions,” in Workshop on Natural Language Generation, 2011, pp … and Eric Fosler- Lussier, “Knowledge graph inference for spoken dialog systems,” in ICASSP … Huang, Larry Heck, and Heng Ji, “Leverag- ing deep neural networks and knowledge …

Challenges in data-to-document generation
S Wiseman, SM Shieber, AM Rush – arXiv preprint arXiv:1707.08052, 2017 – arxiv.org
Page 1. arXiv:1707.08052v1 [cs.CL] 25 Jul 2017 Challenges in Data-to-Document Generation Sam Wiseman and Stuart M. Shieber and Alexander M. Rush School of Engineering and Applied Sciences Harvard University Cambridge …

Automatic Neural Question Generation using Community-based Question Answering Systems
T Baghaee – 2017 – uleth.ca
… users’ reviews. We first present a general understanding of the deep learning approach. We then go through the intuition behind deep neural networks and later expand this idea by describing more advanced models … 7 Page 17. 2.3. DEEP NEURAL NETWORK process …

Deep Memory Networks for Natural Conversations
??? – 2017 – s-space.snu.ac.kr
Page 1.

Day Workshop Towards Intelligent Social Robots: Social Cognitive Systems in Smart Environments
A Aly, S Griffiths, V Nitsch, T Taniguchi, S Wermter… – 2017 – researchgate.net
… To achieve this aim, we present an embodied dialogue system which enables a humanoid to take on an active role during learning by guiding its user with verbal … State-of-the-art learning approaches, such as deep neural networks [1], [2], rely on a large quantity of training data …

Constructing Sentences from Text Fragments: Aggregation in Text-to-text Generation
V Chenal – 2017 – digitool.library.mcgill.ca
… Page 3. ii Abstract Sentence aggregation, the task of determining what input units belong in the same output sentence is an essential process in a natural language generation system. Al … with an additional model and experiments. Page 11. 2 Natural Language Generation …

Streaming Architecture for Large-Scale Quantized Neural Networks on an FPGA-Based Dataflow Platform
C Baskin, N Liss, A Mendelson… – arXiv preprint arXiv …, 2017 – arxiv.org
… ABSTRACT Deep neural networks (DNNs) are used by different ap- plications that are executed on a range of computer architectures, from IoT devices to supercomputers. The footprint of these networks is huge as well as their com- putational and communication needs …

A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
Y Wu, W Wu, C Xing, C Xu, Z Li, M Zhou – arXiv preprint arXiv:1710.11344, 2017 – arxiv.org
… Dialog systems focus on helping people complete specific tasks in vertical domains (Young … Generation-based chatbots reply to a message with natural language generation techniques … in its previous turns and performed matching with a deep neural network architecture; Zhou …

Verbalization of Service Robot Experience as Explanations in Language Including Vision-Based Learned Elements
SPP Selvaraj – 2017 – pdfs.semanticscholar.org
… Then, we generate a description by combining the groundings using a template based natural language generation … We demonstrate automatic annotation by using a deep neural network (DNN) to find which floor the CoBot is in after reaching a new floor via an elevator …

Computational Linguistic Creativity: Poetry generation given visual input
M Loller-Andersen – 2017 – brage.bibsys.no
… In Natural Language Generation (NLG), poetry is one of the more interesting and com- plex challenges, because its value depends on … algorithm for supervised deep feed forward multilayer perceptrons., while Ivakhnenko (1971) already de- scribed a deep neural network with 8 …

Workshop Program
A ANANDKUMAR, FEI SHA – 2017 – pdfs.semanticscholar.org
… developing algorithms for end-to-end training of deep neural network policies that … design and structures, advanced decoding strategies, and natural language generation applications … 02:00 PM Joelle Pineau: Discriminative and Generative Models for Building Dialogue Systems …

A novel X-FEM based fast computational method for crack propagation
Z Cheng, H Wang, PMB Vitanyi, N Chater, M Barzegari… – arxiv.org
… arXiv:1708.01759 [pdf, other] Title: Referenceless Quality Estimation for Natural Language Generation … Computer Interaction (cs.HC). arXiv:1708.01818 [pdf, other] Title: Depth Adaptive Deep Neural Network for Semantic Segmentation …

Mixed-initiative intent recognition using cloud-based cognitive services
M Kraus – 2017 – oparu.uni-ulm.de
… More recently, discriminative hierarchical models like deep neural networks or convolutional neural networks are applied (Yu & Deng, 2012) … 6 Page 19. 3.1 Spoken Dialogue Systems Both scores, LM and AM, are used to determine the best hypothesis for the word sequence by …

Towards the Implementation of an Intelligent Software Agent for the Elderly
AHF Dinevari – 2017 – era.library.ualberta.ca
… 64 6 Response Generation 65 6.1 Natural Language Generation … ML Machine Learning. MUC Machine Understanding Conference. NLG Natural Language Generation. NLP Natural Language Processing. NLU Natural Language Understanding …

Využití uživatelské odezvy pro zvýšení kvality ?e?ové syntézy
V Hude?ek – 2017 – dspace.cuni.cz
… user. The dialogue system than derives a relevant response using its policy. The … approaches. The derived response then has to be translated into a human readable lan- guage, using Natural Language Generation (NLG) techniques. The response can …

Helping users learn about social processes while learning from users: developing a positive feedback in social computing
VSS Pillutla – 2017 – search.proquest.com
… Some smoothing techniques are used. to repair any incoherence occurring in such extractions. The summary generated by abstraction. techniques is not limited to the explicit words of the text; natural language generation techniques. are used to generate the summary [120] …

Can We Speculate Running Application With Server Power Consumption Trace?
Y Li, H Hu, Y Wen, J Zhang – IEEE transactions on cybernetics, 2017 – ieeexplore.ieee.org
… Recently, different ensemble methods based on the above listed classifiers have been proposed and have shown promising performance [29]. However, we have not seen any work on ensemble method of the above methods and deep neural network like LSTM …

Entity-Centric Discourse Analysis and Its Applications
X Wang – 2017 – repository.kulib.kyoto-u.ac.jp
… 63 6.2 Memories in Deep Neural Networks . . . . . 65 … We propose a novel empty category detection method which represents various tree-based features using vectors and employs deep neural networks to detect the missing words …

Multimodal Analysis of User-Generated Multimedia Content
R Shah, R Zimmermann – 2017 – Springer
… of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning … Finally, since the advances in deep neural network (DNN) technologies enabled significant performance boost in many multimedia analytics …

Theory and Applications of Models of Computation
TV Gopal, G Jäger, S Steila – 2017 – Springer
Page 1. TV Gopal Gerhard Jäger Silvia Steila (Eds.) 123 LNCS 10185 14th Annual Conference, TAMC 2017 Bern, Switzerland, April 20–22, 2017 Proceedings Theory and Applications of Models of Computation Page 2. Lecture Notes in Computer Science 10185 …

Statistical Parametric Speech Synthesis Using Conversational Data and Phenomena
R Dall – 2017 – datashare.is.ed.ac.uk
… BAP Bandwise Aperiodicity CPU Central Processing Unit CSS Conversational Speech Synthesis DM Discourse Marker DNN Deep Neural Network DT Decision Tree DP Decision Parameter EM Expectation-Maximisation F0 Fundamental Frequency …

Learning from Temporally-Structured Human Activities Data
ZC Lipton – 2017 – search.proquest.com
… care, self-driving cars, and dialogue systems. While Turings test remains unpassed and Asimovs prognostications remain. unfulfilled, the field of artificial intelligence entered a period of accelerated development. Over the past decade, deep neural networks have significantly …

(Visited 63 times, 1 visits today)