@inproceedings{xu-etal-2019-neural,
title = "Neural Response Generation with Meta-words",
author = "Xu, Can and
Wu, Wei and
Tao, Chongyang and
Hu, Huang and
Schuerman, Matt and
Wang, Ying",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1538",
doi = "10.18653/v1/P19-1538",
pages = "5416--5426",
abstract = "We present open domain dialogue generation with meta-words. A meta-word is a structured record that describes attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues and perform response generation in an explainable and controllable manner. To incorporate meta-words into generation, we propose a novel goal-tracking memory network that formalizes meta-word expression as a goal in response generation and manages the generation process to achieve the goal with a state memory panel and a state controller. Experimental results from both automatic evaluation and human judgment on two large-scale data sets indicate that our model can significantly outperform state-of-the-art generation models in terms of response relevance, response diversity, and accuracy of meta-word expression.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2019-neural">
<titleInfo>
<title>Neural Response Generation with Meta-words</title>
</titleInfo>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongyang</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Schuerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present open domain dialogue generation with meta-words. A meta-word is a structured record that describes attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues and perform response generation in an explainable and controllable manner. To incorporate meta-words into generation, we propose a novel goal-tracking memory network that formalizes meta-word expression as a goal in response generation and manages the generation process to achieve the goal with a state memory panel and a state controller. Experimental results from both automatic evaluation and human judgment on two large-scale data sets indicate that our model can significantly outperform state-of-the-art generation models in terms of response relevance, response diversity, and accuracy of meta-word expression.</abstract>
<identifier type="citekey">xu-etal-2019-neural</identifier>
<identifier type="doi">10.18653/v1/P19-1538</identifier>
<location>
<url>https://aclanthology.org/P19-1538</url>
</location>
<part>
<date>2019-jul</date>
<extent unit="page">
<start>5416</start>
<end>5426</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Response Generation with Meta-words
%A Xu, Can
%A Wu, Wei
%A Tao, Chongyang
%A Hu, Huang
%A Schuerman, Matt
%A Wang, Ying
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 jul
%I Association for Computational Linguistics
%C Florence, Italy
%F xu-etal-2019-neural
%X We present open domain dialogue generation with meta-words. A meta-word is a structured record that describes attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues and perform response generation in an explainable and controllable manner. To incorporate meta-words into generation, we propose a novel goal-tracking memory network that formalizes meta-word expression as a goal in response generation and manages the generation process to achieve the goal with a state memory panel and a state controller. Experimental results from both automatic evaluation and human judgment on two large-scale data sets indicate that our model can significantly outperform state-of-the-art generation models in terms of response relevance, response diversity, and accuracy of meta-word expression.
%R 10.18653/v1/P19-1538
%U https://aclanthology.org/P19-1538
%U https://doi.org/10.18653/v1/P19-1538
%P 5416-5426
Markdown (Informal)
[Neural Response Generation with Meta-words](https://aclanthology.org/P19-1538) (Xu et al., ACL 2019)
ACL
- Can Xu, Wei Wu, Chongyang Tao, Huang Hu, Matt Schuerman, and Ying Wang. 2019. Neural Response Generation with Meta-words. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5416–5426, Florence, Italy. Association for Computational Linguistics.