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.
Filters
Multi-Referenced Training for Dialogue Response Generation
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Then we explore approaches to multi-referenced training in two aspects. ...
In open-domain dialogue response generation, a dialogue context can be continued with diverse responses, and the dialogue models should capture such one-to-many relations. ...
In this paper, we will investigate why single-referenced training harms our dialogue models and how to apply multi-referenced training.
Why Multi-Referenced Training Matters? ...
arXiv:2009.07117v2
fatcat:zru3p5kwwnaxtl5gtsuii53a2a
Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
[article]
2019
arXiv
pre-print
Preserved Fulltext
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.
A recent work proposed Referenced metric and Unreferenced metric Blended Evaluation Routine (RUBER) to combine a learning-based metric, which predicts relatedness between a generated response and a given ...
Traditional reference-based metrics such as BLEU are ineffective because there could be many valid responses for a given context that share no common words with reference responses. ...
Acknowledgments We thank the anonymous reviewers for their constructive feedback, as well as the members of the PLUS lab for their useful discussion and feedback. ...
arXiv:1904.10635v1
fatcat:n3qzpwd3dzeejiau2qgy23zzfy
Designing Precise and Robust Dialogue Response Evaluators
[article]
2020
arXiv
pre-print
Preserved Fulltext
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.
Automatic dialogue response evaluator has been proposed as an alternative to automated metrics and human evaluation. ...
Experimental results demonstrate that the proposed evaluator achieves a strong correlation (> 0.6) with human judgement and generalizes robustly to diverse responses and corpora. ...
Acknowledgments The authors would like to thank Shinsuke Mori from Kyoto University, Wei Wu from Microsoft, Graham Neubig from CMU, and the anonymous reviewers for their constructive comments. ...
arXiv:2004.04908v2
fatcat:hxacualaurhyjpbw5z2qbeeagi
Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References
[article]
2019
arXiv
pre-print
Preserved Fulltext
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
One alternative is to collect human annotations for evaluation, which can be expensive and time consuming. ...
To demonstrate the effectiveness of multi-reference evaluation, we augment the test set of DailyDialog with multiple references. ...
Referenced Diversity A multi-reference test set also allows referenced diversity evaluation. ...
arXiv:1907.10568v2
fatcat:tzxkifuhzbdb5noypdoq52fqqm
Learning an Unreferenced Metric for Online Dialogue Evaluation
[article]
2020
arXiv
pre-print
Preserved Fulltext
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.
There have been recent efforts to develop automatic dialogue evaluation metrics, but most of them do not generalize to unseen datasets and/or need a human-generated reference response during inference, ...
We show that our model achieves higher correlation with human annotations in an online setting, while not requiring true responses for comparison during inference. ...
We would like to thank Shagun Sodhani and Alborz Geramifard for helpful feedback on the manuscript. ...
arXiv:2005.00583v1
fatcat:o2aw5ywxcffbdehq7p3eajirhq
Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots
[article]
2019
arXiv
pre-print
Preserved Fulltext
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.
Conventional chatbots focus on two-party response generation, which simplifies the real dialogue scene. ...
In this paper, we strive toward a novel task of Response Generation on Multi-Party Chatbot (RGMPC), where the generated responses heavily rely on the interlocutors' roles (e.g., speaker and addressee) ...
Finally, the interlocutor prediction loss is added to the response generation loss for training. ...
arXiv:1910.13106v1
fatcat:lezhqdl4evgurljpt44ugqbufq
MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2010.05594v2 fatcat:5weacbkpbfbvzed4vgdha746pyOther Versions
To ensure consistency between dialogue acts and dialogue states, we implement co-reference features and unify annotations of dialogue acts and dialogue states. ...
In this paper, we introduce MultiWOZ 2.3, in which we differentiate incorrect annotations in dialogue acts from dialogue states, identifying a lack of co-reference when publishing the updated dataset. ...
" slots for taxi/train domains. ...
arXiv:2010.05594v3
fatcat:t2o46xv5ybc25ilow2bo3y3sui
Commonsense-Focused Dialogues for Response Generation: An Empirical Study
[article]
2021
arXiv
pre-print
Preserved Fulltext
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
We evaluate response generation models trained using these datasets and find that models trained on both extracted and our collected data produce responses that consistently exhibit more commonsense than ...
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. ...
Aiming to bridge the gap in commonsense for dialogue response generation, we collect a large-scale multi-turn open-domain dialogue dataset that is focused on commonsense knowledge. ...
arXiv:2109.06427v2
fatcat:c3ktn55vyzhhhkfskn4owddu7m
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
[article]
2022
arXiv
pre-print
Preserved Fulltext
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:2109.14739v1 fatcat:hak2xy2yyjbadan4jbryndrk54
In addition, we introduce a new dialogue multi-task pre-training strategy that allows the model to learn the primary TOD task completion skills from heterogeneous dialog corpora. ...
In this study, we present PPTOD, a unified plug-and-play model for task-oriented dialogue. ...
for generating dialogue responses. ...
arXiv:2109.14739v2
fatcat:dsy25xhxlbbk3f2qccoluwtpiy
Integrating User and Agent Models: A Deep Task-Oriented Dialogue System
[article]
2017
arXiv
pre-print
Preserved Fulltext
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.
Then the built user model is used as a leverage to train the agent model by deep reinforcement learning. ...
Task-oriented dialogue systems can efficiently serve a large number of customers and relieve people from tedious works. ...
Experiments on Multi-Turn Dialogue Generation In this section, we evaluate the proposed SAMIA framework to generate responses in multi-turn dialogues. ...
arXiv:1711.03697v1
fatcat:u67st24k6zdmvkzjyhqejphuci
Beyond Goldfish Memory: Long-Term Open-Domain Conversation
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context. ...
We show how existing models trained on existing datasets perform poorly in this long-term conversation setting in both automatic and human evaluations, and we study long-context models that can perform ...
A memory-augmented generator that takes the dialogue context and access to the long-term memory, and then generates the next response. ...
arXiv:2107.07567v1
fatcat:wrabh7xfcba67n2nj6jfbqlesq
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling
[article]
2020
arXiv
pre-print
Preserved Fulltext
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.
Both single- and multi-domain dialogues are constructed, accounting for 65% and 35%, respectively. ...
In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset ...
We would like to thank the anonymous reviewers for their insightful comments. The corresponding author is Deyi Xiong (dyxiong@tju.edu.cn). ...
arXiv:2010.08738v1
fatcat:2qdeo3lcdbg6xl27y6q3sz7jl4
A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework
[article]
2019
arXiv
pre-print
Preserved Fulltext
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.
In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. ...
The resulting persona hredGAN (phredGAN) shows better performance than both the existing persona-based Seq2Seq and hredGAN models when those external attributes are available in a multi-turn dialogue corpus ...
Problem Formulation: The hredGAN [7] formulates multi-turn dialogue response generation as: given a dialogue history of sequence of utterances, X i = X 1 , X 2 , · · · , X i , where each utterance X ...
arXiv:1905.01998v1
fatcat:bluopydsazaeperznwjouplk5u
Low-Resource Adaptation of Open-Domain Generative Chatbots
[article]
2022
arXiv
pre-print
Preserved Fulltext
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:2108.06329v1 fatcat:ielaqstutjbt3b5akw4q2n3mdq
Additionally, we propose a generic framework that accounts for variety in question types, tracks reference throughout multi-turn conversations, and removes inconsistent and potentially toxic responses. ...
We demonstrate that low parameter models can simultaneously retain their general knowledge conversational abilities while improving in a specific domain. ...
The core response generation model was trained using the ParlAI 2 framework, a platform designed specifically for dialogue models. ...
arXiv:2108.06329v2
fatcat:ayloa42sozbpfbyeyuarroa6si
Pchatbot: A Large-Scale Dataset for Personalized Chatbot
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
Other Versions
Different from existing datasets, Pchatbot provides anonymized user IDs and timestamps for both posts and responses. ...
Besides, current dialogue datasets for personalized chatbot usually contain several persona sentences or attributes. ...
(2) Multi-referenced dialogue. In natural language dialogue, a post can have multiple appropriate responses. ...
arXiv:2009.13284v3
fatcat:x47nvif75zae5oy53fd67shrxe
« Previous
Showing results 1 — 15 out of 19,912 results