@inproceedings{otani-etal-2022-lite,
title = "{LITE}: {I}ntent-based Task Representation Learning Using Weak Supervision",
author = "Otani, Naoki and
Gamon, Michael and
Jauhar, Sujay Kumar and
Yang, Mei and
Malireddi, Sri Raghu and
Riva, Oriana",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.172/",
doi = "10.18653/v1/2022.naacl-main.172",
pages = "2410--2424",
abstract = "Users write to-dos as personal notes to themselves, about things they need to complete, remember or organize. To-do texts are usually short and under-specified, which poses a challenge for current text representation models. Yet, understanding and representing their meaning is the first step towards providing intelligent assistance for to-do management. We address this problem by proposing a neural multi-task learning framework, LITE, which extracts representations of English to-do tasks with a multi-head attention mechanism on top of a pre-trained text encoder. To adapt representation models to to-do texts, we collect weak-supervision labels from semantically rich external resources (e.g., dynamic commonsense knowledge bases), following the principle that to-do tasks with similar intents have similar labels. We then train the model on multiple generative/predictive training objectives jointly. We evaluate our representation model on four downstream tasks and show that our approach consistently improves performance over baseline models, achieving error reduction of up to 38.7{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otani-etal-2022-lite">
<titleInfo>
<title>LITE: Intent-based Task Representation Learning Using Weak Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Otani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gamon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujay</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Jauhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sri</namePart>
<namePart type="given">Raghu</namePart>
<namePart type="family">Malireddi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oriana</namePart>
<namePart type="family">Riva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Users write to-dos as personal notes to themselves, about things they need to complete, remember or organize. To-do texts are usually short and under-specified, which poses a challenge for current text representation models. Yet, understanding and representing their meaning is the first step towards providing intelligent assistance for to-do management. We address this problem by proposing a neural multi-task learning framework, LITE, which extracts representations of English to-do tasks with a multi-head attention mechanism on top of a pre-trained text encoder. To adapt representation models to to-do texts, we collect weak-supervision labels from semantically rich external resources (e.g., dynamic commonsense knowledge bases), following the principle that to-do tasks with similar intents have similar labels. We then train the model on multiple generative/predictive training objectives jointly. We evaluate our representation model on four downstream tasks and show that our approach consistently improves performance over baseline models, achieving error reduction of up to 38.7%.</abstract>
<identifier type="citekey">otani-etal-2022-lite</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.172</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.172/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2410</start>
<end>2424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LITE: Intent-based Task Representation Learning Using Weak Supervision
%A Otani, Naoki
%A Gamon, Michael
%A Jauhar, Sujay Kumar
%A Yang, Mei
%A Malireddi, Sri Raghu
%A Riva, Oriana
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F otani-etal-2022-lite
%X Users write to-dos as personal notes to themselves, about things they need to complete, remember or organize. To-do texts are usually short and under-specified, which poses a challenge for current text representation models. Yet, understanding and representing their meaning is the first step towards providing intelligent assistance for to-do management. We address this problem by proposing a neural multi-task learning framework, LITE, which extracts representations of English to-do tasks with a multi-head attention mechanism on top of a pre-trained text encoder. To adapt representation models to to-do texts, we collect weak-supervision labels from semantically rich external resources (e.g., dynamic commonsense knowledge bases), following the principle that to-do tasks with similar intents have similar labels. We then train the model on multiple generative/predictive training objectives jointly. We evaluate our representation model on four downstream tasks and show that our approach consistently improves performance over baseline models, achieving error reduction of up to 38.7%.
%R 10.18653/v1/2022.naacl-main.172
%U https://aclanthology.org/2022.naacl-main.172/
%U https://doi.org/10.18653/v1/2022.naacl-main.172
%P 2410-2424
Markdown (Informal)
[LITE: Intent-based Task Representation Learning Using Weak Supervision](https://aclanthology.org/2022.naacl-main.172/) (Otani et al., NAACL 2022)
ACL
- Naoki Otani, Michael Gamon, Sujay Kumar Jauhar, Mei Yang, Sri Raghu Malireddi, and Oriana Riva. 2022. LITE: Intent-based Task Representation Learning Using Weak Supervision. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2410–2424, Seattle, United States. Association for Computational Linguistics.