Internet Archive Scholar
Filters
























4,488 Hits in 5.8 sec

Commonsense-Focused Dialogues for Response Generation: An Empirical Study [article]

Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (173.9 kB)
https://web.archive.org/web/20210921033006/https://arxiv.org/pdf/2109.06427v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2021 pre-print arXiv:2109.06427v1 fatcat:teqn7olfv5fxbi7e2th4hor5ei
Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet. In this paper, we present an empirical study of commonsense in dialogue response generation.  ...  language generation as in dialogue.  ...  Task Introduction and Motivations Commonsense-Focused Dialogue Response Generation We study commonsense-focused response generation for dialogues.  ... 
arXiv:2109.06427v2 fatcat:c3ktn55vyzhhhkfskn4owddu7m
Open Access Multiple Versions
Citation

Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur. "Commonsense-Focused Dialogues for Response Generation: An Empirical Study." arXiv (2021)

Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation [article]

Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.2 MB)
https://web.archive.org/web/20220327165636/https://arxiv.org/pdf/2110.08501v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2021 pre-print
arXiv:2110.08501v1 fatcat:zrswlmoed5axbiwrz7u5jlusre
Empirical results show TBS models outperform end-to-end and knowledge-augmented RG baselines on most automatic metrics and generate more informative, specific, and commonsense-following responses, as evaluated  ...  In this paper, we present Think-Before-Speaking (TBS), a generative approach to first externalize implicit commonsense knowledge (think) and use this knowledge to generate responses (speak).  ...  ), generate an appropriate response R.  ... 
arXiv:2110.08501v2 fatcat:i3ybu2kbsnfm7k7jfafu5x7ifu
Open Access Multiple Versions
Citation

Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur. "Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation." arXiv (2022)

Strong Influence of Responses in Training Dialogue Response Generator

So-Eon Kim, Yeon-Soo Lim, Seong-Bae Park
2021 Applied Sciences  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (920.5 kB)
https://web.archive.org/web/20210817072259/https://res.mdpi.com/d_attachment/applsci/applsci-11-07415/article_deploy/applsci-11-07415.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

The sequence-to-sequence model is a widely used model for dialogue response generators, but it tends to generate safe responses for most input queries.  ...  The effectiveness of RGRW is proven by showing that it generates more diverse and informative responses than the baseline response generator by focusing more on the tokens that are important for generating  ...  CCM [13] and ConKADI [6] are commonsense knowledge-aware response generators.  ... 
doi:10.3390/app11167415 fatcat:g47h64izhrfuzjzzcxlip2tefm
DOAJ
Citation

So-Eon Kim, Yeon-Soo Lim, Seong-Bae Park. "Strong Influence of Responses in Training Dialogue Response Generator." Applied Sciences 11.16 (2021) 7415

Empathetic response generation through Graph-based Multi-hop Reasoning on Emotional Causality

Jiashuo Wang, Wenjie Li, Peiqin Lin, Feiteng Mu
2021 Knowledge-Based Systems  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20211013104120/https://arxiv.org/pdf/2110.04614v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2021 pre-print arXiv:2110.04614v1 fatcat:o4aipjiqdffippwjq3chhgfnlq
Empathetic response generation aims to comprehend the user emotion and then respond to it appropriately.  ...  Most existing works merely focus on what the emotion is and ignore how the emotion is evoked, thus weakening the capacity of the model to understand the emotional experience of the user for generating  ...  Similar to the task of emotional response generation, empathetic response generation also focuses on the emotional expression of users.  ... 
doi:10.1016/j.knosys.2021.107547 fatcat:lrwfsmfajjdydgdz4kbqfjyrsy
Multiple Versions
Citation

Jiashuo Wang, Wenjie Li, Peiqin Lin, Feiteng Mu. "Empathetic response generation through Graph-based Multi-hop Reasoning on Emotional Causality." Knowledge-Based Systems (2021) 107547

A Survey of Knowledge-Enhanced Text Generation [article]

Wenhao Yu, Chenguang Zhu, Zaitang Li, Zhiting Hu, Qingyun Wang, Heng Ji, Meng Jiang
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.0 MB)
https://web.archive.org/web/20210710103638/https://arxiv.org/pdf/2010.04389v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2021 pre-print arXiv:2010.04389v2 fatcat:h2kprdm4knbglljkqarxetwkny

Other Versions

2022 accepted
doi:10.1145/3512467 arXiv:2010.04389v4 fatcat:7eb7m3yvovbzjagvxezppdnuge
2020 pre-print
arXiv:2010.04389v1 fatcat:7cnt7u4u5nc5tk3ihxi364ycd4
The main content includes two parts: (i) general methods and architectures for integrating knowledge into text generation; (ii) specific techniques and applications according to different forms of knowledge  ...  This research direction is known as knowledge-enhanced text generation.  ...  For example, dialogue systems generate responses with specific attitudes.  ... 
arXiv:2010.04389v3 fatcat:vzdtlz4j65g2va7gwkbmzyxkhq
Open Access Multiple Versions
Citation

Wenhao Yu, Chenguang Zhu, Zaitang Li, Zhiting Hu, Qingyun Wang, Heng Ji, Meng Jiang. "A Survey of Knowledge-Enhanced Text Generation." arXiv (2022)

Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems [article]

Behnam Hedayatnia, Karthik Gopalakrishnan, Seokhwan Kim, Yang Liu, Mihail Eric, Dilek Hakkani-Tur
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20201017061234/https://arxiv.org/pdf/2005.12529v4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2005.12529v1 fatcat:rxht7exfl5gzdoxtrwqoqy7yvu
2020 pre-print
arXiv:2005.12529v2 fatcat:esjvo4zz2zh4pnt3y4dzpwt4ku
2020 pre-print
arXiv:2005.12529v3 fatcat:4xwuhmt3irgqzhrdzxze6htake
Open-domain dialogue systems aim to generate relevant, informative and engaging responses.  ...  We also investigate different dialogue policy models to predict an action plan given the dialogue context.  ...  Our work focuses on neural generative models for response generation in opendomain dialogue systems. Figure 2 : 2 Policy-driven neural response generation.  ... 
arXiv:2005.12529v4 fatcat:rugerkc3tvbi3jzz2y7oayvcwm
Multiple Versions
Citation

Behnam Hedayatnia, Karthik Gopalakrishnan, Seokhwan Kim, Yang Liu, Mihail Eric, Dilek Hakkani-Tur. "Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems." arXiv (2020)

Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts [article]

Wenhao Yu, Chenguang Zhu, Lianhui Qin, Zhihan Zhang, Tong Zhao, Meng Jiang
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (501.4 kB)
https://web.archive.org/web/20220320040027/https://arxiv.org/pdf/2203.07285v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Generative commonsense reasoning (GCR) in natural language is to reason about the commonsense while generating coherent text.  ...  Nevertheless, these approaches have seldom investigated diversity in the GCR tasks, which aims to generate alternative explanations for a real-world situation or predict all possible outcomes.  ...  Figure 1 shows an example in the commonsense explanation generation (ComVE) task.  ... 
arXiv:2203.07285v1 fatcat:rmsntuibuzgaxgjyojt4yrlrva
Open Access
Citation

Wenhao Yu, Chenguang Zhu, Lianhui Qin, Zhihan Zhang, Tong Zhao, Meng Jiang. "Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts." arXiv (2022)

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models [article]

Iulian V. Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, Joelle Pineau
2016 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (436.0 kB)
https://web.archive.org/web/20200930135934/https://arxiv.org/pdf/1507.04808v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2015 pre-print
arXiv:1507.04808v1 fatcat:3xb6uhxoj5g6tm3nl4niltpfpm
2015 pre-print
arXiv:1507.04808v2 fatcat:s5q5opcsevfzve2vvgrpujrrfm
Generative models produce system responses that are autonomously generated word-by-word, opening up the possibility for realistic, flexible interactions.  ...  We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models.  ...  Banchs for providing the Movie-DiC dataset, and Luisa Coheur for providing the SubTle dataset. The authors also thank the anonymous AAAI reviewers for their helpful feedback.  ... 
arXiv:1507.04808v3 fatcat:sw2dgffakvchphom64e2ebg43y
Multiple Versions
Citation

Iulian V. Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, Joelle Pineau. "Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models." arXiv (2016)

Neural Language Generation: Formulation, Methods, and Evaluation [article]

Cristina Garbacea, Qiaozhu Mei
2020 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20200825140201/https://arxiv.org/pdf/2007.15780v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Next we include a comprehensive outline of methods and neural architectures employed for generating diverse texts.  ...  We hope this survey will provide an informative overview of formulations, methods, and assessments of neural natural language generation.  ...  framework for dialogue response generation focused on movie and restaurant reviews (Srinivasan et al., 2019) .  ... 
arXiv:2007.15780v1 fatcat:oixtreazxvbgvclicpxiqzbxrm
Citation

Cristina Garbacea, Qiaozhu Mei. "Neural Language Generation: Formulation, Methods, and Evaluation." arXiv (2020)

Situated Dialogue Learning through Procedural Environment Generation [article]

Prithviraj Ammanabrolu, Renee Jia, Mark O. Riedl
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.1 MB)
https://web.archive.org/web/20211010024803/https://arxiv.org/pdf/2110.03262v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2021 pre-print arXiv:2110.03262v1 fatcat:b4kt342qufdephpb6mknn43c7e
An ablation study shows that this method of learning from the tail of a distribution results in significantly higher generalization abilities as measured by zero-shot performance on never-before-seen quests  ...  We augment LIGHT by learning to procedurally generate additional novel textual worlds and quests to create a curriculum of steadily increasing difficulty for training agents to achieve such goals.  ...  responsible for changing the state of the world.  ... 
arXiv:2110.03262v2 fatcat:grqhsmg5srb6lotre7dorzr3je
Multiple Versions
Citation

Prithviraj Ammanabrolu, Renee Jia, Mark O. Riedl. "Situated Dialogue Learning through Procedural Environment Generation." arXiv (2022)

Sketch-Fill-A-R: A Persona-Grounded Chit-Chat Generation Framework [article]

Michael Shum, Stephan Zheng, Wojciech Kryściński, Caiming Xiong, Richard Socher
2019 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (759.9 kB)
https://web.archive.org/web/20200906041252/https://arxiv.org/pdf/1910.13008v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

We propose Sketch-Fill-A-R, a framework that uses a persona-memory to generate chit-chat responses in three phases. First, it generates dynamic sketch responses with open slots.  ...  Human-like chit-chat conversation requires agents to generate responses that are fluent, engaging and consistent.  ...  ., 2018) is an example of an undirected chit-chat dialogue agent.  ... 
arXiv:1910.13008v1 fatcat:sonllzafwzaq5fcdjneeik6e4e
Citation

Michael Shum, Stephan Zheng, Wojciech Kryściński, Caiming Xiong, Richard Socher. "Sketch-Fill-A-R: A Persona-Grounded Chit-Chat Generation Framework." arXiv (2019)

COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas [article]

Chen Xu, Piji Li, Wei Wang, Haoran Yang, Siyun Wang, Chuangbai Xiao
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.6 MB)
https://web.archive.org/web/20220504174553/https://arxiv.org/pdf/2205.00872v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2022 pre-print arXiv:2205.00872v1 fatcat:rfocfqfluzeevh2nsadoi2vzsu

Other Versions

2022 accepted
doi:10.1145/3477495.3531957 arXiv:2205.00872v3 fatcat:gpeufppnqbhi5co4iklf524w6q
Extensive experiments on a large public dataset, Persona-Chat, demonstrate that our model outperforms state-of-the-art baselines for generating less egocentric, more human-like, and higher quality responses  ...  In this work, we propose COSPLAY(COncept Set guided PersonaLized dialogue generation Across both partY personas) that considers both parties as a "team": expressing self-persona while keeping curiosity  ...  Chuangbai Xiao for insightful suggestions and careful mentoring. We also want to thank Dr. Yan Wang, Dr. Wei Bi, and other members of the NLP group at Tencent AI Lab for helpful discussions.  ... 
arXiv:2205.00872v2 fatcat:yxeb7fves5fnrfengk7osb5eem
Multiple Versions
Citation

Chen Xu, Piji Li, Wei Wang, Haoran Yang, Siyun Wang, Chuangbai Xiao. "COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas." arXiv (2022)

Survey of Hallucination in Natural Language Generation [article]

Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, Pascale Fung
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (706.3 kB)
https://web.archive.org/web/20220514040639/https://arxiv.org/pdf/2202.03629v4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Other Versions

2022 pre-print
arXiv:2202.03629v1 fatcat:xnjdlsuxprf5xgcxdkxrsfite4
2022 pre-print
arXiv:2202.03629v2 fatcat:vf6ojdr7mbch5dhh6beay2sngm
2022 pre-print
arXiv:2202.03629v3 fatcat:ramec5o5r5h23haxfuoxt6nfx4
downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation.  ...  This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation.  ...  HALLUCINATION IN DIALOGUE GENERATION Dialogue generation is an NLG task that automatically generates responses according to user utterances.  ... 
arXiv:2202.03629v4 fatcat:s6c26a7orncrffis55q5swo5ue
Open Access Multiple Versions
Citation

Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, Pascale Fung. "Survey of Hallucination in Natural Language Generation." arXiv (2022)

Counterfactual Story Reasoning and Generation

Lianhui Qin, Antoine Bosselut, Ari Holtzman, Chandra Bhagavatula, Elizabeth Clark, Yejin Choi
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20191203105107/https://www.aclweb.org/anthology/D19-1509.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

text generation correlate well with human scores for counterfactual rewriting.  ...  In this paper, we propose Counterfactual Story Rewriting: given an original story and an intervening counterfactual event, the task is to minimally revise the story to make it compatible with the given  ...  Acknowledgements We thanks the anonymous reviewers as well as Michel Galley, Jianfeng Gao, and others for many helpful comments.  ... 
doi:10.18653/v1/d19-1509 dblp:conf/emnlp/QinBHBCC19 fatcat:b2ftanxqxvezrl5f4yyulelp2i
Citation

Lianhui Qin, Antoine Bosselut, Ari Holtzman, Chandra Bhagavatula, Elizabeth Clark, Yejin Choi. "Counterfactual Story Reasoning and Generation." Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019) 5042-5052

Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction [article]

Wei Wei, Jiayi Liu, Xianling Mao, Guibing Guo, Feida Zhu, Pan Zhou, Yuchong Hu
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.4 MB)
https://web.archive.org/web/20210615060704/https://arxiv.org/pdf/2106.03044v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions.  ...  However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses.  ...  To evaluate the emotion perception ability of different approaches over the emotion categories, we build an emotion-rich dialogue set for a fair empirical comparison.  ... 
arXiv:2106.03044v1 fatcat:c32tcpnjcrhbhioowa4teeydcm
Citation

Wei Wei, Jiayi Liu, Xianling Mao, Guibing Guo, Feida Zhu, Pan Zhou, Yuchong Hu. "Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction." arXiv (2021)

« Previous Showing results 1 — 15 out of 4,488 results