@inproceedings{kang-etal-2019-recommendation,
title = "Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue",
author = "Kang, Dongyeop and
Balakrishnan, Anusha and
Shah, Pararth and
Crook, Paul and
Boureau, Y-Lan and
Weston, Jason",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1203",
doi = "10.18653/v1/D19-1203",
pages = "1951--1961",
abstract = "Traditional recommendation systems produce static rather than interactive recommendations invariant to a user{'}s specific requests, clarifications, or current mood, and can suffer from the cold-start problem if their tastes are unknown. These issues can be alleviated by treating recommendation as an interactive dialogue task instead, where an expert recommender can sequentially ask about someone{'}s preferences, react to their requests, and recommend more appropriate items. In this work, we collect a goal-driven recommendation dialogue dataset (GoRecDial), which consists of 9,125 dialogue games and 81,260 conversation turns between pairs of human workers recommending movies to each other. The task is specifically designed as a cooperative game between two players working towards a quantifiable common goal. We leverage the dataset to develop an end-to-end dialogue system that can simultaneously converse and recommend. Models are first trained to imitate the behavior of human players without considering the task goal itself (supervised training). We then finetune our models on simulated bot-bot conversations between two paired pre-trained models (bot-play), in order to achieve the dialogue goal. Our experiments show that models finetuned with bot-play learn improved dialogue strategies, reach the dialogue goal more often when paired with a human, and are rated as more consistent by humans compared to models trained without bot-play. The dataset and code are publicly available through the ParlAI framework.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2019-recommendation">
<titleInfo>
<title>Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongyeop</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anusha</namePart>
<namePart type="family">Balakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pararth</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Y-Lan</namePart>
<namePart type="family">Boureau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Weston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Traditional recommendation systems produce static rather than interactive recommendations invariant to a user’s specific requests, clarifications, or current mood, and can suffer from the cold-start problem if their tastes are unknown. These issues can be alleviated by treating recommendation as an interactive dialogue task instead, where an expert recommender can sequentially ask about someone’s preferences, react to their requests, and recommend more appropriate items. In this work, we collect a goal-driven recommendation dialogue dataset (GoRecDial), which consists of 9,125 dialogue games and 81,260 conversation turns between pairs of human workers recommending movies to each other. The task is specifically designed as a cooperative game between two players working towards a quantifiable common goal. We leverage the dataset to develop an end-to-end dialogue system that can simultaneously converse and recommend. Models are first trained to imitate the behavior of human players without considering the task goal itself (supervised training). We then finetune our models on simulated bot-bot conversations between two paired pre-trained models (bot-play), in order to achieve the dialogue goal. Our experiments show that models finetuned with bot-play learn improved dialogue strategies, reach the dialogue goal more often when paired with a human, and are rated as more consistent by humans compared to models trained without bot-play. The dataset and code are publicly available through the ParlAI framework.</abstract>
<identifier type="citekey">kang-etal-2019-recommendation</identifier>
<identifier type="doi">10.18653/v1/D19-1203</identifier>
<location>
<url>https://aclanthology.org/D19-1203</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1951</start>
<end>1961</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue
%A Kang, Dongyeop
%A Balakrishnan, Anusha
%A Shah, Pararth
%A Crook, Paul
%A Boureau, Y-Lan
%A Weston, Jason
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F kang-etal-2019-recommendation
%X Traditional recommendation systems produce static rather than interactive recommendations invariant to a user’s specific requests, clarifications, or current mood, and can suffer from the cold-start problem if their tastes are unknown. These issues can be alleviated by treating recommendation as an interactive dialogue task instead, where an expert recommender can sequentially ask about someone’s preferences, react to their requests, and recommend more appropriate items. In this work, we collect a goal-driven recommendation dialogue dataset (GoRecDial), which consists of 9,125 dialogue games and 81,260 conversation turns between pairs of human workers recommending movies to each other. The task is specifically designed as a cooperative game between two players working towards a quantifiable common goal. We leverage the dataset to develop an end-to-end dialogue system that can simultaneously converse and recommend. Models are first trained to imitate the behavior of human players without considering the task goal itself (supervised training). We then finetune our models on simulated bot-bot conversations between two paired pre-trained models (bot-play), in order to achieve the dialogue goal. Our experiments show that models finetuned with bot-play learn improved dialogue strategies, reach the dialogue goal more often when paired with a human, and are rated as more consistent by humans compared to models trained without bot-play. The dataset and code are publicly available through the ParlAI framework.
%R 10.18653/v1/D19-1203
%U https://aclanthology.org/D19-1203
%U https://doi.org/10.18653/v1/D19-1203
%P 1951-1961
Markdown (Informal)
[Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue](https://aclanthology.org/D19-1203) (Kang et al., EMNLP-IJCNLP 2019)
ACL
