Filters








8,494 Hits in 4.7 sec

TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues [article]

Po-Wei Lin, Shang-Yu Su, Yun-Nung Chen
2022 arXiv   pre-print
The goal of dialogue relation extraction (DRE) is to identify the relation between two entities in a given dialogue.  ...  During conversations, speakers may expose their relations to certain entities by explicit or implicit clues, such evidences called "triggers".  ...  This work was financially supported from Google and the Young Scholar Fellowship Program by Ministry of Science and Technology (MOST) in Taiwan, under Grants 111-2628-E-002-016 and 111-2634-F-002-014.  ... 
arXiv:2108.13811v2 fatcat:rqqqo2as6beldjojo5eknhs5hu

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks [article]

Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria
2021 arXiv   pre-print
Dialogue relation extraction (DRE) aims to detect the relation between two entities mentioned in a multi-party dialogue.  ...  Thus, they fail to model the crucial inter-speaker relations that may give additional context to relevant argument entities through pronouns and triggers.  ...  Each dialogue contains several relational triples (x, y, r), and the task is to predict the relation r between each argument pair (x, y).  ... 
arXiv:2009.05092v3 fatcat:yvl66ojjuzex3py75kbcag5nie

Discovering Emotion and Reasoning its Flip in Multi-Party Conversations using Masked Memory Network and Transformer [article]

Shivani Kumar, Anubhav Shrimal, Md Shad Akhtar, Tanmoy Chakraborty
2021 arXiv   pre-print
We propose a masked memory network to address the former and a Transformer-based network for the latter task.  ...  During a conversation, the cognitive state of a speaker often alters due to certain past utterances, which may lead to a flip in their emotional state.  ...  In comparison, our proposed EFR task deals with multiple speakers in a conversational dialogue and aims at extracting the cause (or reason) of an emotion flip for a speaker.  ... 
arXiv:2103.12360v3 fatcat:5zpzvcu3mbdflbqz2mnmx4r5ze

Discourse Marker Detection for Hesitation Events on Mandarin Conversation

Yu-Wun Wang, Hen-Hsen Huang, Kuan-Yu Chen, Hsin-Hsi Chen
2018 Interspeech 2018  
We propose a sequential labeling model to detect discourse markers in conversations by taking information on both acoustic level and word level into account.  ...  Experimental results show the integration of wordlevel acoustic feature extraction network significantly enhances the detection performance. Our approach for further applications is also discussed.  ...  For instance, dialogue systems can provide more explanation to users sounding more uncertain, and a reminding system can detect users' difficulties in memory recall and trigger the assistance.  ... 
doi:10.21437/interspeech.2018-2129 dblp:conf/interspeech/WangHCC18 fatcat:vxy2m3v5nfcw3kp7ko2ytg2dne

Modeling Human Communication Dynamics [Social Sciences

Louis-philippe Morency
2010 IEEE Signal Processing Magazine  
ACKNOWLEDGMENTS I am indebted to the following sources for their permission to reproduce figures drawn from my work and related work for this "History" column: Taylor and Francis Group, LLC for Figures  ...  1, 2, 3, and 8, as referenced in [3]; Acoustical Society of America for Figure 4 , as referenced in [4]; Alcatel-Lucent USA Inc. for Figures 6, 8, 9 , and 10, as referenced in [3], [6], [13] , and  ...  When a gesture occurs, the recognition and meaning of the gesture is enhanced due to this dialogue context prediction. Thus recognition is enabled by the meaningfulness of a gesture in dialogue.  ... 
doi:10.1109/msp.2010.937500 fatcat:66d5yogfpvdpnjdpdzvdk7hoii

A Long Short-Term Memory Framework for Predicting Humor in Dialogues

Dario Bertero, Pascale Fung
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We propose a first-ever attempt to employ a Long Short-Term memory based framework to predict humor in dialogues.  ...  We show how the LSTM effectively models the setup-punchline relation reducing the number of false positives and increasing the recall.  ...  Acknowledgments This work was partially funded by the Hong Kong Phd Fellowship Scheme, and partially by grant #16214415 of the Hong Kong Research Grants Council.  ... 
doi:10.18653/v1/n16-1016 dblp:conf/naacl/BerteroF16 fatcat:p6bvsejmqzchzgxtlxv2hitnru

Data-driven models for timing feedback responses in a Map Task dialogue system

Raveesh Meena, Gabriel Skantze, Joakim Gustafson
2014 Computer Speech and Language  
Our results confirm that a model trained on these speaker modalities offers both smooth turn-transitions and responsive system behaviour.  ...  Using this data we trained various models that use automatically extractable prosodic, contextual and lexico-syntactic features for online detection of feedback response locations.  ...  We would also like to thank the participants of our user evaluation and perception tests.  ... 
doi:10.1016/j.csl.2014.02.002 fatcat:pt7hk3op6bdvnm2euymzqhaexa

Topic Break Detection in Interview Dialogues Using Sentence Embedding of Utterance and Speech Intention Based on Multitask Neural Networks

Kazuyuki Matsumoto, Manabu Sasayama, Taiga Kirihara
2022 Sensors  
In multi-task learning, not only topic breaks but also the intention associated with the utterance and the speaker are targets of prediction.  ...  similarities between words are likely to fail.  ...  Acknowledgments: This research was supported by corpus annotations by several graduate students belonging to the Tokushima University Graduate School North Laboratory and students belonging to the Shinoyama  ... 
doi:10.3390/s22020694 pmid:35062654 pmcid:PMC8780003 fatcat:k3zlfbcwffexncoobbrekgtz6i

Automatic generation of concise summaries of spoken dialogues in unrestricted domains

Klaus Zechner
2001 Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '01  
This paper introduces the task, the challenges involved, and presents an approach to obtain automatic extract summaries for multi-party dialogues of four di erent genres, without any restriction on domain  ...  dis uencies (ii) detection and insertion of sentence boundaries (iii) detection and linking of cross-speaker information units (question-answer pairs).  ...  We used a corpus of 23 dialogues from four di erent genres (80 topical segments, about 47000 words total) for system development and evaluation and the dis uency annotated SwitchBoard corpus 13] for training  ... 
doi:10.1145/383952.383989 dblp:conf/sigir/Zechner01 fatcat:cmwallcsfneithr7nsfeq5yf7u

Exploiting Text Matching Techniques for Knowledge-Grounded Conversation

Yeonchan Ahn, Sang-Goo Lee, Jaehui Park
2020 IEEE Access  
Models based on Match-Reduce strategy first match every turn of the context with knowledge sentences to capture fine-grained interactions and aggregate them while minimizing information loss to predict  ...  To generate an informative and context-coherent response, it is important to conjugate dialogue context and external knowledge in a balanced manner.  ...  The decoder uses the knowledge sentence chosen by the speaker, k, during training, and, k pred , the knowledge sentence predicted by the trained knowledge selection module during inference.  ... 
doi:10.1109/access.2020.3007893 fatcat:jyu3rvorwjhbrfsjafnwct5eiu

Predicting student emotions in computer-human tutoring dialogues

Diane J. Litman, Kate Forbes-Riley
2004 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04  
We examine the utility of speech and lexical features for predicting student emotions in computerhuman spoken tutoring dialogues.  ...  Finally, we compare our results with emotion prediction in human-human tutoring dialogues.  ...  Acknowledgments This research is supported by NSF Grants 9720359 & 0328431. Thanks to the Why2-Atlas team and S. Silliman for system design and data collection.  ... 
doi:10.3115/1218955.1219000 dblp:conf/acl/LitmanF04 fatcat:fw3zfvkh6zbdxloc6muuid44eu

Computational study of human communication dynamic

Louis-Philippe Morency
2011 Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding - J-HGBU '11  
Even when only one person speaks at the time, other participants exchange information continuously amongst themselves and with the speaker through gesture, gaze, posture and facial expressions.  ...  To correctly interpret the high-level communicative signals, an observer needs to jointly integrate all spoken words, subtle prosodic changes and simultaneous gestures from all participants.  ...  When a gesture occurs, the recognition and meaning of the gesture is enhanced due to this dialogue context prediction. Thus recognition is enabled by the meaningfulness of a gesture in dialogue.  ... 
doi:10.1145/2072572.2072578 dblp:conf/mm/Morency11 fatcat:mgrnbi4swnhhhmz5xlyujdwkry

Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues [article]

Yinhe Zheng, Yida Wang, Pei Ke, Zhenyu Yang, Minlie Huang
2022 arXiv   pre-print
For training and evaluation, we present X-Weibo, a Chinese multi-turn open-domain dialogue dataset with automatic annotation for emotions, DAs, and topical words.  ...  At inference, we disentangle semantic and token variations by specifying sampling methods and constraints for each module separately.  ...  This work was also supported by the Guoqiang Institute of Tsinghua University, with Grant No. 2019GQG1 and 2020GQG0005.  ... 
arXiv:2106.03065v2 fatcat:6rq6rquka5gtxmvyc2bhvlohii

Managing interpersonal discourse expectations: a comparative analysis of contrastive discourse particles in Dutch

Geertje van Bergen, Lotte Hogeweg
2021 Linguistics  
In this article we investigate how speakers manage discourse expectations in dialogue by comparing the meaning and use of three Dutch discourse particles, i.e. wel, toch and eigenlijk, which all express  ...  a contrast between their host utterance and a discourse-based expectation.  ...  This work was supported by the Netherlands Organisation for Scientific Research (NWO), grant number 275-89-022, awarded to Geertje van Bergen.  ... 
doi:10.1515/ling-2021-0020 fatcat:vc5hquqwmnfn7ipeiq3wlfedmm

Recognizing Emotion Cause in Conversations [article]

Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Deepanway Ghosal, Rishabh Bhardwaj, Samson Yu Bai Jian, Pengfei Hong, Romila Ghosh, Abhinaba Roy, Niyati Chhaya, Alexander Gelbukh, Rada Mihalcea
2021 arXiv   pre-print
Furthermore, we define different cause types based on the source of the causes, and establish strong Transformer-based baselines to address two different sub-tasks on this dataset: causal span extraction  ...  We address the problem of recognizing emotion cause in conversations, define two novel sub-tasks of this problem, and provide a corresponding dialogue-level dataset, along with strong Transformer-based  ...  Compliance with Ethical Standards -This article does not contain any studies with human participants or animals performed by any of the authors.  ... 
arXiv:2012.11820v4 fatcat:qornwntchzap3hqrjqajsd2yxy
« Previous Showing results 1 — 15 out of 8,494 results