Word Segmentation & Dialog Systems 2017


Wikipedia:

See also:

100 Best Word Embedding Videos | Word Lattice


End-to-end task-completion neural dialogue systems
X Li, YN Chen, L Li, J Gao – arXiv preprint arXiv:1703.01008, 2017 – arxiv.org
… 2015. Semantically conditioned lstm-based natural lan- guage generation for spoken dialogue systems … slot value: to simulate the scenario that the slot name was recognized correctly, but the slot value was not recognized cor- rectly, eg, wrong word segmentation; • incorrect slot …

RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems
C Tao, L Mou, D Zhao, R Yan – arXiv preprint arXiv:1701.03079, 2017 – arxiv.org
… We performed Chinese word segmentation, and obtained Chinese terms as primitive tokens. The RUBER metric (along with baselines) is evaluated on two dialog systems. One is a feature- based retrieval-and-reranking system in Song et al …

A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media.
H He, X Sun – AAAI, 2017 – aaai.org
… tion. We also use the same unannotated texts as Peng and Dredze (2016a) from Sina Weibo service in China and texts are word segmented by a Chinese word segmentation system Jieba5 as Peng and Dredze (2016a). The …

Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
X Li, YN Chen, L Li, J Gao, A Celikyilmaz – arXiv preprint arXiv:1703.07055, 2017 – arxiv.org
… While in user simulation, it is much easier to control each variable to directly analyze the importance of NLU in the dialogue system … to simulate the scenario where the slot name was recognized correctly, but the slot value was not, eg, wrong word segmentation; • Incorrect slot …

Alime chat: A sequence to sequence and rerank based chatbot engine
M Qiu, FL Li, S Wang, X Gao, Y Chen, W Zhao… – Proceedings of the 55th …, 2017 – aclweb.org
… There are two points to be noted: (1) all the three mod- els are based on words (ie, word segmentation is needed): the input … Closed-domain dialog systems typically use rule- or template- based methods (Williams and Zweig, 2016; Wen et al., 2016), and dialog state track- ing …

Neural personalized response generation as domain adaptation
W Zhang, T Liu, Y Wang, Q Zhu – arXiv preprint arXiv:1701.02073, 2017 – arxiv.org
… In this paper, LTP (http://www.ltp-cloud.com/) toolkit is used for Chinese word segmentation for all the data. For the personalized training, we invited 5 volunteers … Task-oriented Dialogue Generation The most successful research on the task-oriented dialogue system is mainly …

Automatic chinese factual question generation
M Liu, V Rus, L Liu – IEEE Transactions on Learning …, 2017 – ieeexplore.ieee.org
… Question authoring tools are important in educational technologies, eg, intelligent tutoring systems, as well as in dialogue systems … For this reason, automatic word segmentation is a major step in Chinese morphological analysis …

Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
S Swayamdipta, S Thomson, C Dyer… – arXiv preprint arXiv …, 2017 – arxiv.org
… SegRNNs use continuous vector representations of spans. In past work, they have been applied to joint word segmentation and part-of-speech tag- ging for Chinese (Kong et al., 2016) and to speech recognition (Lu et al., 2016) …

AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience
FL Li, M Qiu, H Chen, X Wang, X Gao, J Huang… – Proceedings of the …, 2017 – dl.acm.org
… We first extract candidate nouns and verbs from natural language knowledge items through word segmentation, part-of- speech (POS) tagging and tf-idf filtering, and use them to … Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models …

Two-stage approach to named entity recognition using Wikipedia and DBpedia
S Ryu, H Yu, GG Lee – Proceedings of the 11th International Conference …, 2017 – dl.acm.org
… Many natural language-based systems such as dialog systems, question answering, and in- formation retrieval use NER to represent important infor- mation in sentences; as a result … (iii) Korean words consist of one or more morphemes3, so errors of word segmentation are often …

Modeling Target-Side Inflection in Neural Machine Translation
A Tamchyna, MWD Marco, A Fraser – arXiv preprint arXiv:1707.06012, 2017 – arxiv.org
Page 1. Modeling Target-Side Inflection in Neural Machine Translation Aleš Tamchyna1,2 and Marion Weller-Di Marco1,3 and Alexander Fraser1 1LMU Munich, 2Memsource, 3University of Stuttgart ales.tamchyna@memsource …

Annotation and Detection of Emotion in Text-based Dialogue Systems with CNN
J Zhao, Q Gao – arXiv preprint arXiv:1710.00987, 2017 – arxiv.org
… With UTF-8, EmoNet gains the ability to perform in multi-language dialogue systems … [9] Sproat R, Gale W, Shih C, et al. A stochastic finite-state word- segmentation algorithm for Chinese[J]. Computational linguis- tics, 1996, 22(3): 377-404 …

Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
T Zhao, T Kawahara – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… Therefore DA segmentation becomes essential for spoken dialog systems … Zheng et al. (2013) applied a joint coding method to Chinese word segmentation and POS tagging by changing POS labels using a “BIES” tag coding scheme …

Turn-taking Estimation Model Based on Joint Embedding of Lexical and Prosodic Contents
C Liu, C Ishi, H Ishiguro – Proc. Interspeech 2017, 2017 – pdfs.semanticscholar.org
… Furthermore, recog- nizing whether a phrase is backchannel is critical for a dialog system since it means a user has no intention to interrupt and requires no response; the system … 3.1.1. Word segmentation Word segmentation is a critical first step in Japanese text analy- sis …

Gbot at the NTCIR-13 STC-2 Task
H Zhang, T Guo, Y Lan, J Guo, J Li, X Cheng – research.nii.ac.jp
… Firstly, we directly use character level sen- tence as input rather than word level sentence, because word segmentation in Chinese is not perfect … How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation …

A Complete Bibliography of ACM Transactions on Speech and Language Processing (TSLP)
NHF Beebe – 2017 – tug.ctan.org
… Higashinaka:2004:EDU [HMNA04] Ryuichiro Higashinaka, Noboru Miyazaki, Mikio Nakano, and Kiyoaki Aikawa. Evaluating dis- course understanding in spoken dialogue systems. ACM Trans- actions on Speech and Language Processing (TSLP), 1(1):1–20, November 2004 …

Diversifying Neural Conversation Model with Maximal Marginal Relevance
Y Song, Z Tian, D Zhao, M Zhang, R Yan – Proceedings of the Eighth …, 2017 – aclweb.org
… We performed standard Chinese word segmentation. 4.2 Experimental Setups All the methods are established on the base of the traditional seq2seq with same settings … 2016a. Build- ing end-to-end dialogue systems using generative hi- erarchical neural network models …

Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
G Kondrak, T Watanabe – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… 173 Addressing Domain Adaptation for Chinese Word Segmentation with Global Recurrent Structure Shen Huang, Xu Sun and Houfeng Wang … End-to-End Task-Completion Neural Dialogue Systems Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao and Asli Celikyilmaz …

Building an Intelligent Call Distributor
TK Tran, DM Pham, B Van Huynh – Computer Science On-line Conference, 2017 – Springer
… 3. Pham, N., Vu, Q.: A spoken dialog system for stock information inquiry. In: Proceedings of IT@EDU, Ho Chi Minh City, Vietnam (2012)Google Scholar. 4. Phuong, L.-H., Thi Minh Huyên, N., Roussanaly, A., Vinh, HT: A hybrid approach to word segmentation of vietnamese texts …

Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context
R Takeda, K Komatani – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… Figure 3: Word segmentation Goldwater et al., 2009; Elsner et al., 2013; Uchiumi et al., 2015). The lexical acquisition technique is necessary in other areas, such as dialogue system that acquires knowledge through dialogue (Ono et al., 2016) …

Negotiation of Antibiotic Treatment in Medical Consultations: A Corpus based Study
N Wang – Proceedings of ACL 2017, Student Research …, 2017 – aclweb.org
… Current research for dialogue systems offer an alternative ap- proach … Also, NER is conducted on Chinese. Thus, domain specific word segmentation (Song and Xia, 2012) is a prerequisite if we extend our work to larger datasets in a more scalable way …

Interaction Style Recognition Based on Multi-Layer Multi-View Profile Representation
WL Wei, JC Lin, CH Wu – IEEE Transactions on Affective …, 2017 – ieeexplore.ieee.org
… Dialogue system or conversa- tional agent, as one of the prominent HCI research areas, has been applied to a wide range of domains, from simple goal- oriented applications such as airline travel information ser- vice [1], city tour guide [2] and nursing home assistant [3] to …

Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text
T Shinozaki, S Watanabe, D Mochihashi… – Proc. Interspeech …, 2017 – merl.com
… of these functions by performing character recognition [1]. However, many applications including infor- mation retrieval and spoken dialog systems still require … by making a hierarchical Bayesian model [6, 7, 8, 9], which originates from the unsupervised word segmentation in text …

AppTechMiner: Mining Applications and Techniques from Scientific Articles
M Singh, S Dan, S Agarwal, P Goyal… – Proceedings of the 6th …, 2017 – dl.acm.org
… Word Alignment, Conditional Random Fields, Maximum Entropy, Coreference Resolution, Machine Learning, Dialogue Systems, Textual Entailment … Role Analysis, Multiclass Clasi er, Coreference Resolution, Latent Dirichlet Chinese Word Segmentation Entity Recognition …

Language is Not About Language: Towards Formalizing the Role of Extra-Linguistic Factors in Human and Machine Language Acquisition and Communication
O Räsänen – Proc. GLU 2017 International Workshop on …, 2017 – pdfs.semanticscholar.org
… methods and end-to-end systems trained on large- scale data sets, the state-of-the-art ASR and dialogue systems still fall far … experiences and external and internal constraints available to human learners solving the same problem (see [7] for a case in early word segmentation) …

Abstractive Document Summarization via Neural Model with Joint Attention
L Hou, P Hu, C Bei – National CCF Conference on Natural Language …, 2017 – Springer
… Examples of two word segmentation methods. Open image in new window. 3.2 RNN Encoder-Decoder. The RNN encoder-decoder framework is the fundamental for many current NLP models and is widely used in machine translation, dialog systems and automatic document …

Natural Language Processing: State of The Art, Current Trends and Challenges
D Khurana, A Koli, K Khatter, S Singh – arXiv preprint arXiv:1708.05148, 2017 – arxiv.org
… Dialogue systems. 6.7 Medicine … [103] 7.2 Naive Bayes Classifiers The choice of area is wide ranging covering usual items like word segmentation and translation but also unusual areas like segmentation for infant learning and identifying documents for opinions and facts …

Classification-based spoken text selection for LVCSR language modeling
V Chunwijitra, C Wutiwiwatchai – EURASIP …, 2017 – asmp-eurasipjournals.springeropen …
… Therefore, after the text is cleaned and normalized, we need to identify word boundaries. In this work, we use TLex [17], a Thai word segmentation tool based on CRF, to automatically identify word boundaries in tweet texts. 4 Style-based data selection …

Bringing Semantic Structures to User Intent Detection in Online Medical Queries
C Zhang, N Du, W Fan, Y Li, CT Lu, PS Yu – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. Bringing Semantic Structures to User Intent Detection in Online Medical Queries Chenwei Zhang?¶, Nan Du†, Wei Fan‡, Yaliang Li†, Chun-Ta Lu?, Philip S. Yu?§ ? Department of Computer Science, University of Illinois …

Sentence?Chain Based Seq2seq Model for Corpus Expansion
E Chung, JG Park – ETRI Journal, 2017 – Wiley Online Library
… As examples of external resource approaches, an in-domain corpus expansion using focused Web crawling was proposed in [11]. For Chinese word segmentation, a technique of exploiting the redundancy in a Web corpus was first proposed in [12] …

Named Entity Recognition with Gated Convolutional Neural Networks
C Wang, W Chen, B Xu – … and Natural Language Processing Based on …, 2017 – Springer
… NER is also a popular NLP task and plays a vital role for downstream systems, such as machine translation systems and dialogue systems … Levow, GA: The third international chinese language processing bakeoff: word segmentation and named entity recognition …

CI-Bot: A Hybrid Chatbot Enhanced by Crowdsourcing
X Liang, R Ding, M Lin, L Li, X Li, S Lu – … ) Joint Conference on Web and Big …, 2017 – Springer
… When dealing with a Chinese question, word segmentation algorithm divides the content into a list of keywords … ACM pp. 379–388 (2016)Google Scholar. 11. Huang, THK, Lasecki, WS, Bigham, JP: Guardian: a crowd-powered spoken dialog system for web APIs …

Implementation of robot journalism by programming custombot using tokenization and custom tagging
N Lee, K Kim, T Yoon – Advanced Communication Technology …, 2017 – ieeexplore.ieee.org
… Semantic Role Labelling is also used for Dialogue System; it is a task which identifies sentence elements such as subject and object … A. Text Segmentation Text segmentation, also called tokenization or word segmentation, is a process of dividing a string into several meaningful …

Joint Learning of Response Ranking and Next Utterance Suggestion in Human-Computer Conversation System
R Yan, D Zhao – Proceedings of the 40th International ACM SIGIR …, 2017 – dl.acm.org
Page 1. Joint Learning of Response Ranking and Next Utterance Suggestion in Human-Computer Conversation System Rui Yan †,? 1 Institute of Computer Science and Technology Peking University Beijing 100871, China ruiyan@pku.edu.cn …

Can Discourse Relations be Identified Incrementally?
F Yung, H Noji, Y Matsumoto – Proceedings of the Eighth International …, 2017 – aclweb.org
… On top of generating more natural and timely response in dialogue systems and im- proving language modeling in speech recognition, 157 Page 2 … 2012. Incremental joint approach to word segmentation, pos tagging, and dependency parsing in chinese …

Transition-Based Deep Input Linearization
R Puduppully, Y Zhang, M Shrivastava – … of the 15th Conference of the …, 2017 – aclweb.org
Page 1. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 643–654, Valencia, Spain, April 3-7, 2017. cO2017 Association for Computational Linguistics …

Accent sandhi estimation of Tokyo dialect of Japanese using conditional random fields
M Suzuki, R Kuroiwa, K Innami… – … on Information and …, 2017 – search.ieice.org
… proposed doing word segmentation, pronun- ciation estimation, and accent estimation simultaneously by using pairs of words, POS … engaged in a wide range of research on spoken language processing, including analysis, synthesis, recognition, dialogue systems, and computer …

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
R Barzilay, MY Kan – Proceedings of the 55th Annual Meeting of the …, 2017 – aclweb.org
… Mohit Bansal (Vision, Robotics and Grounding Area) Chia-Hui Chang (Information Extraction and NLP Applications Area) Grzegorz Chrupa?a (Machine Learning Area) Mona Diab (Multilingual Area) Jason Eisner (Phonology, Morphology and Word Segmentation Area) Manaal …

Recent trends in deep learning based natural language processing
T Young, D Hazarika, S Poria, E Cambria – arXiv preprint arXiv …, 2017 – arxiv.org
… language related tasks at all levels, ranging from parsing and part-of-speech (POS) tagging, to machine translation and dialog systems … compositional characters (such as Chinese), building systems at the character level is a natural choice to avoid word segmentation (Chen et …

Style Transfer in Text: Exploration and Evaluation
Z Fu, X Tan, N Peng, D Zhao, R Yan – arXiv preprint arXiv:1711.06861, 2017 – arxiv.org
… Vinyals, and Le 2014) have demonstrated great success in many generation tasks, such as machine transla- tion, dialog system and image … used an adversarial network to separate the shared and the private features for multi-task learning to help chinese word segmentation …

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
M Palmer, R Hwa, S Riedel – Proceedings of the 2017 Conference on …, 2017 – aclweb.org
Page 1. EMNLP 2017 The Conference on Empirical Methods in Natural Language Processing Proceedings of the Conference September 9-11, 2017 Copenhagen, Denmark Page 2. c?2017 The Association for Computational Linguistics …

Integrating Extractive and Abstractive Models for Long Text Summarization
S Wang, X Zhao, B Li, B Ge… – Big Data (BigData …, 2017 – ieeexplore.ieee.org
… natural language processing tasks, including but not limited to machine translation [2], voice recognition [3] and dialogue systems [22], etc … is constructed according to historical data from 2010 to 2016, which significantly improves the accuracy of the word segmentation, and from …

Constructing a Language From Scratch: Combining Bottom–Up and Top–Down Learning Processes in a Computational Model of Language Acquisition
J Gaspers, P Cimiano, K Rohlfing… – IEEE Transactions on …, 2017 – ieeexplore.ieee.org
… architecture involved in language acquisition. Index Terms—Cognitive modeling, language acquisition, lan- guage development, speech, top–down and bottom–up processes, word segmentation. I. INTRODUCTION HUMANS acquire …

Decoding with value networks for neural machine translation
D He, H Lu, Y Xia, T Qin, L Wang, T Liu – Advances in Neural …, 2017 – papers.nips.cc
… For all datasets in Chinese, we used a public tool for word segmentation … Second, the idea of using value networks is quite general, and we will extend it to other sequence-to-sequence learning tasks, such as image captioning and dialog systems. 8 Page 9. Acknowledgments …

Combining Domain Knowledge and Deep Learning Makes NMT More Adaptive
L Ding, Y He, L Zhou, Q Liu – China Workshop on Machine Translation, 2017 – Springer
… and helps benefit many NLP task, such as dictionary compilation, sentiment classification, machine translation and dialogue system etc … Such preprocess as word segmentation, garbled characters filtering, improves match rates to get a primary domain knowledge base with …

A Complete Bibliography of ACM Transactions on Asian Language Information Processing
NHF Beebe – 2017 – tug.ctan.org
… Kim:2003:RRE [37] Harksoo Kim and Jungyun Seo. Resolution of referring expressions in a Korean multimodal dialogue system. ACM Transactions on Asian Lan- guage Information Processing, 2(4):324–337, December 2003. CODEN …

Learning Algorithms for Broad-Coverage Semantic Parsing
S Swayamdipta – 2017 – cs.cmu.edu
Page 1. Learning Algorithms for Broad-Coverage Semantic Parsing Swabha Swayamdipta September 2017 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee: Noah A. Smith, Chair …

Journal of Phonetics & Audiology
RT Kalathottukaren, SC Purdy – 2017 – researchgate.net
… The functions of prosody have been identified at the grammatical, emotional, and pragmatic levels of communication [22,23]. Prosodic cues such as voice onset time, pitch contour, coarticulation, and syllable duration helps word segmentation in children and adults [24-26] …

Transition-Based Technique for Syntactic Linearization and Deep Input Linearization
RS Puduppully – 2017 – web2py.iiit.ac.in
Page 1. Transition-Based Technique for Syntactic Linearization and Deep Input Linearization Thesis submitted in partial fulfillment of the requirements for the degree of MS by Research in Computer Science by Ratish Surendran Puduppully 201407662 …

Community Standards for Linguistically-Annotated Resources
N Ide, N Calzolari, J Eckle-Kohler, D Gibbon… – Handbook of Linguistic …, 2017 – Springer
… ISO 24615:2010, Language resource management – Syntactic annotation framework (SynAF). ISO 24614-1:2010, Language resource management – Word segmentation of written texts – Part 1: Basic concepts and general principles (WordSeg-1) …

Advanced data exploitation in speech analysis: An overview
Z Zhang, N Cummins, B Schuller – IEEE Signal Processing …, 2017 – ieeexplore.ieee.org
… For speech processing, crowdsourcing has been widely employed for a range of tasks, including speech data col- lection/acquisition, speech annotation, speech perception, assessment of speech synthesis, and dialog system evalua- tion [15], [26] …

(Visited 29 times, 1 visits today)