@inproceedings{raghu-etal-2019-disentangling,
title = "{D}isentangling {L}anguage and {K}nowledge in {T}ask-{O}riented {D}ialogs",
author = "Raghu, Dinesh and
Gupta, Nikhil and
{Mausam}",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1126",
doi = "10.18653/v1/N19-1126",
pages = "1239--1255",
abstract = "The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response{'}s language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNeT outperforms state-of-the-art models, with considerable improvements ({\textgreater}10{\%}) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNeT to be robust to KB modifications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raghu-etal-2019-disentangling">
<titleInfo>
<title>Disentangling Language and Knowledge in Task-Oriented Dialogs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="family">Raghu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response’s language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNeT outperforms state-of-the-art models, with considerable improvements (\textgreater10%) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNeT to be robust to KB modifications.</abstract>
<identifier type="citekey">raghu-etal-2019-disentangling</identifier>
<identifier type="doi">10.18653/v1/N19-1126</identifier>
<location>
<url>https://aclanthology.org/N19-1126</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1239</start>
<end>1255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disentangling Language and Knowledge in Task-Oriented Dialogs
%A Raghu, Dinesh
%A Gupta, Nikhil
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%A Mausam
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F raghu-etal-2019-disentangling
%X The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response’s language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNeT outperforms state-of-the-art models, with considerable improvements (\textgreater10%) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNeT to be robust to KB modifications.
%R 10.18653/v1/N19-1126
%U https://aclanthology.org/N19-1126
%U https://doi.org/10.18653/v1/N19-1126
%P 1239-1255
Markdown (Informal)
[Disentangling Language and Knowledge in Task-Oriented Dialogs](https://aclanthology.org/N19-1126) (Raghu et al., NAACL 2019)
ACL
- Dinesh Raghu, Nikhil Gupta, and Mausam. 2019. Disentangling Language and Knowledge in Task-Oriented Dialogs. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1239–1255, Minneapolis, Minnesota. Association for Computational Linguistics.