@inproceedings{zhu-etal-2021-discovering,
title = "Discovering Better Model Architectures for Medical Query Understanding",
author = "Zhu, Wei and
Ni, Yuan and
Wang, Xiaoling and
Xie, Guotong",
editor = "Kim, Young-bum and
Li, Yunyao and
Rambow, Owen",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-industry.29",
doi = "10.18653/v1/2021.naacl-industry.29",
pages = "230--237",
abstract = "In developing an online question-answering system for the medical domains, natural language inference (NLI) models play a central role in question matching and intention detection. However, which models are best for our datasets? Manually selecting or tuning a model is time-consuming. Thus we experiment with automatically optimizing the model architectures on the task at hand via neural architecture search (NAS). First, we formulate a novel architecture search space based on the previous NAS literature, supporting cross-sentence attention (cross-attn) modeling. Second, we propose to modify the ENAS method to accelerate and stabilize the search results. We conduct extensive experiments on our two medical NLI tasks. Results show that our system can easily outperform the classical baseline models. We compare different NAS methods and demonstrate our approach provides the best results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2021-discovering">
<titleInfo>
<title>Discovering Better Model Architectures for Medical Query Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoling</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guotong</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Young-bum</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In developing an online question-answering system for the medical domains, natural language inference (NLI) models play a central role in question matching and intention detection. However, which models are best for our datasets? Manually selecting or tuning a model is time-consuming. Thus we experiment with automatically optimizing the model architectures on the task at hand via neural architecture search (NAS). First, we formulate a novel architecture search space based on the previous NAS literature, supporting cross-sentence attention (cross-attn) modeling. Second, we propose to modify the ENAS method to accelerate and stabilize the search results. We conduct extensive experiments on our two medical NLI tasks. Results show that our system can easily outperform the classical baseline models. We compare different NAS methods and demonstrate our approach provides the best results.</abstract>
<identifier type="citekey">zhu-etal-2021-discovering</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-industry.29</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-industry.29</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>230</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discovering Better Model Architectures for Medical Query Understanding
%A Zhu, Wei
%A Ni, Yuan
%A Wang, Xiaoling
%A Xie, Guotong
%Y Kim, Young-bum
%Y Li, Yunyao
%Y Rambow, Owen
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F zhu-etal-2021-discovering
%X In developing an online question-answering system for the medical domains, natural language inference (NLI) models play a central role in question matching and intention detection. However, which models are best for our datasets? Manually selecting or tuning a model is time-consuming. Thus we experiment with automatically optimizing the model architectures on the task at hand via neural architecture search (NAS). First, we formulate a novel architecture search space based on the previous NAS literature, supporting cross-sentence attention (cross-attn) modeling. Second, we propose to modify the ENAS method to accelerate and stabilize the search results. We conduct extensive experiments on our two medical NLI tasks. Results show that our system can easily outperform the classical baseline models. We compare different NAS methods and demonstrate our approach provides the best results.
%R 10.18653/v1/2021.naacl-industry.29
%U https://aclanthology.org/2021.naacl-industry.29
%U https://doi.org/10.18653/v1/2021.naacl-industry.29
%P 230-237
Markdown (Informal)
[Discovering Better Model Architectures for Medical Query Understanding](https://aclanthology.org/2021.naacl-industry.29) (Zhu et al., NAACL 2021)
ACL
- Wei Zhu, Yuan Ni, Xiaoling Wang, and Guotong Xie. 2021. Discovering Better Model Architectures for Medical Query Understanding. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers, pages 230–237, Online. Association for Computational Linguistics.