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
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

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
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

Strong Influence of Responses in Training Dialogue Response Generator

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

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

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

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
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

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
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

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
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

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
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

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

Cristina Garbacea, Qiaozhu Mei
2020 arXiv   pre-print
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

Situated Dialogue Learning through Procedural Environment Generation [article]

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

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
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

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
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

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
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

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)  
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

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