@inproceedings{mazare-etal-2018-training,
title = "Training Millions of Personalized Dialogue Agents",
author = "Mazar{\'e}, Pierre-Emmanuel and
Humeau, Samuel and
Raison, Martin and
Bordes, Antoine",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1298",
doi = "10.18653/v1/D18-1298",
pages = "2775--2779",
abstract = "Current dialogue systems fail at being engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-to-end dialogue models increases when conditioning them on text personas providing some personalized back-story to the model. However, the dataset used in Zhang et al. (2018) is synthetic and only contains around 1k different personas. In this paper we introduce a new dataset providing 5 million personas and 700 million persona-based dialogues. Our experiments show that, at this scale, training using personas still improves the performance of end-to-end systems. In addition, we show that other tasks benefit from the wide coverage of our dataset by fine-tuning our model on the data from Zhang et al. (2018) and achieving state-of-the-art results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mazare-etal-2018-training">
<titleInfo>
<title>Training Millions of Personalized Dialogue Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierre-Emmanuel</namePart>
<namePart type="family">Mazaré</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Humeau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Raison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bordes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct"-"nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current dialogue systems fail at being engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-to-end dialogue models increases when conditioning them on text personas providing some personalized back-story to the model. However, the dataset used in Zhang et al. (2018) is synthetic and only contains around 1k different personas. In this paper we introduce a new dataset providing 5 million personas and 700 million persona-based dialogues. Our experiments show that, at this scale, training using personas still improves the performance of end-to-end systems. In addition, we show that other tasks benefit from the wide coverage of our dataset by fine-tuning our model on the data from Zhang et al. (2018) and achieving state-of-the-art results.</abstract>
<identifier type="citekey">mazare-etal-2018-training</identifier>
<identifier type="doi">10.18653/v1/D18-1298</identifier>
<location>
<url>https://aclanthology.org/D18-1298</url>
</location>
<part>
<date>2018-oct"-"nov</date>
<extent unit="page">
<start>2775</start>
<end>2779</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training Millions of Personalized Dialogue Agents
%A Mazaré, Pierre-Emmanuel
%A Humeau, Samuel
%A Raison, Martin
%A Bordes, Antoine
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct" "nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F mazare-etal-2018-training
%X Current dialogue systems fail at being engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-to-end dialogue models increases when conditioning them on text personas providing some personalized back-story to the model. However, the dataset used in Zhang et al. (2018) is synthetic and only contains around 1k different personas. In this paper we introduce a new dataset providing 5 million personas and 700 million persona-based dialogues. Our experiments show that, at this scale, training using personas still improves the performance of end-to-end systems. In addition, we show that other tasks benefit from the wide coverage of our dataset by fine-tuning our model on the data from Zhang et al. (2018) and achieving state-of-the-art results.
%R 10.18653/v1/D18-1298
%U https://aclanthology.org/D18-1298
%U https://doi.org/10.18653/v1/D18-1298
%P 2775-2779
Markdown (Informal)
[Training Millions of Personalized Dialogue Agents](https://aclanthology.org/D18-1298) (Mazaré et al., EMNLP 2018)
ACL
- Pierre-Emmanuel Mazaré, Samuel Humeau, Martin Raison, and Antoine Bordes. 2018. Training Millions of Personalized Dialogue Agents. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2775–2779, Brussels, Belgium. Association for Computational Linguistics.