@inproceedings{asghar-etal-2017-deep,
title = "Deep Active Learning for Dialogue Generation",
author = "Asghar, Nabiha and
Poupart, Pascal and
Jiang, Xin and
Li, Hang",
editor = "Ide, Nancy and
Herbelot, Aur{\'e}lie and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*{SEM} 2017)",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S17-1008",
doi = "10.18653/v1/S17-1008",
pages = "78--83",
abstract = "We propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While most existing research proposes offline supervision or hand-crafted reward functions for online reinforcement, we devise a novel interactive learning mechanism based on hamming-diverse beam search for response generation and one-character user-feedback at each step. Experiments show that our model inherently promotes the generation of semantically relevant and interesting responses, and can be used to train agents with customized personas, moods and conversational styles.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asghar-etal-2017-deep">
<titleInfo>
<title>Deep Active Learning for Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nabiha</namePart>
<namePart type="family">Asghar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascal</namePart>
<namePart type="family">Poupart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While most existing research proposes offline supervision or hand-crafted reward functions for online reinforcement, we devise a novel interactive learning mechanism based on hamming-diverse beam search for response generation and one-character user-feedback at each step. Experiments show that our model inherently promotes the generation of semantically relevant and interesting responses, and can be used to train agents with customized personas, moods and conversational styles.</abstract>
<identifier type="citekey">asghar-etal-2017-deep</identifier>
<identifier type="doi">10.18653/v1/S17-1008</identifier>
<location>
<url>https://aclanthology.org/S17-1008</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>78</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Active Learning for Dialogue Generation
%A Asghar, Nabiha
%A Poupart, Pascal
%A Jiang, Xin
%A Li, Hang
%Y Ide, Nancy
%Y Herbelot, Aurélie
%Y Màrquez, Lluís
%S Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F asghar-etal-2017-deep
%X We propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While most existing research proposes offline supervision or hand-crafted reward functions for online reinforcement, we devise a novel interactive learning mechanism based on hamming-diverse beam search for response generation and one-character user-feedback at each step. Experiments show that our model inherently promotes the generation of semantically relevant and interesting responses, and can be used to train agents with customized personas, moods and conversational styles.
%R 10.18653/v1/S17-1008
%U https://aclanthology.org/S17-1008
%U https://doi.org/10.18653/v1/S17-1008
%P 78-83
Markdown (Informal)
[Deep Active Learning for Dialogue Generation](https://aclanthology.org/S17-1008) (Asghar et al., *SEM 2017)
ACL
- Nabiha Asghar, Pascal Poupart, Xin Jiang, and Hang Li. 2017. Deep Active Learning for Dialogue Generation. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pages 78–83, Vancouver, Canada. Association for Computational Linguistics.