Adapting Task-Oriented Dialogue Models for Email Conversations
Intent detection is a key part of any Natural Language Understanding (NLU) system of a conversational assistant. Detecting the correct intent is essential yet difficult for email conversations where multiple directives and intents are present. In such settings, conversation context can become a key...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Deshmukh, Soham Lee, Charles |
description | Intent detection is a key part of any Natural Language Understanding (NLU)
system of a conversational assistant. Detecting the correct intent is essential
yet difficult for email conversations where multiple directives and intents are
present. In such settings, conversation context can become a key disambiguating
factor for detecting the user's request from the assistant. One prominent way
of incorporating context is modeling past conversation history like
task-oriented dialogue models. However, the nature of email conversations (long
form) restricts direct usage of the latest advances in task-oriented dialogue
models. So in this paper, we provide an effective transfer learning framework
(EMToD) that allows the latest development in dialogue models to be adapted for
long-form conversations. We show that the proposed EMToD framework improves
intent detection performance over pre-trained language models by 45% and over
pre-trained dialogue models by 30% for task-oriented email conversations.
Additionally, the modular nature of the proposed framework allows plug-and-play
for any future developments in both pre-trained language and task-oriented
dialogue models. |
doi_str_mv | 10.48550/arxiv.2208.09439 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2208_09439</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2208_09439</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-30f4deb17f5299751dcdd55dca08ba2ffa5ef154a31ac97dea8f1d47de3016ab3</originalsourceid><addsrcrecordid>eNotz7FuwjAUhWEvHSrgATrVL5DUjm0SL0gohbYSiCV7dJN7jayGGNkpgrdvSzudfzrSx9iTFLmujBEvEK_-kheFqHJhtbKPbLVGOE9-PPIG0md2iJ7GiZC_ehjC8Yv4PiANibsQ-eYEfuB1GC8UE0w-jGnOHhwMiRb_O2PNdtPU79nu8PZRr3cZLEubKeE0UidLZwprSyOxRzQGexBVB4VzYMhJo0FJ6G2JBJWTqH9CCbmETs3Y89_tHdCeoz9BvLW_kPYOUd-gU0Qn</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Adapting Task-Oriented Dialogue Models for Email Conversations</title><source>arXiv.org</source><creator>Deshmukh, Soham ; Lee, Charles</creator><creatorcontrib>Deshmukh, Soham ; Lee, Charles</creatorcontrib><description>Intent detection is a key part of any Natural Language Understanding (NLU)
system of a conversational assistant. Detecting the correct intent is essential
yet difficult for email conversations where multiple directives and intents are
present. In such settings, conversation context can become a key disambiguating
factor for detecting the user's request from the assistant. One prominent way
of incorporating context is modeling past conversation history like
task-oriented dialogue models. However, the nature of email conversations (long
form) restricts direct usage of the latest advances in task-oriented dialogue
models. So in this paper, we provide an effective transfer learning framework
(EMToD) that allows the latest development in dialogue models to be adapted for
long-form conversations. We show that the proposed EMToD framework improves
intent detection performance over pre-trained language models by 45% and over
pre-trained dialogue models by 30% for task-oriented email conversations.
Additionally, the modular nature of the proposed framework allows plug-and-play
for any future developments in both pre-trained language and task-oriented
dialogue models.</description><identifier>DOI: 10.48550/arxiv.2208.09439</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2022-08</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2208.09439$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2208.09439$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Deshmukh, Soham</creatorcontrib><creatorcontrib>Lee, Charles</creatorcontrib><title>Adapting Task-Oriented Dialogue Models for Email Conversations</title><description>Intent detection is a key part of any Natural Language Understanding (NLU)
system of a conversational assistant. Detecting the correct intent is essential
yet difficult for email conversations where multiple directives and intents are
present. In such settings, conversation context can become a key disambiguating
factor for detecting the user's request from the assistant. One prominent way
of incorporating context is modeling past conversation history like
task-oriented dialogue models. However, the nature of email conversations (long
form) restricts direct usage of the latest advances in task-oriented dialogue
models. So in this paper, we provide an effective transfer learning framework
(EMToD) that allows the latest development in dialogue models to be adapted for
long-form conversations. We show that the proposed EMToD framework improves
intent detection performance over pre-trained language models by 45% and over
pre-trained dialogue models by 30% for task-oriented email conversations.
Additionally, the modular nature of the proposed framework allows plug-and-play
for any future developments in both pre-trained language and task-oriented
dialogue models.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7FuwjAUhWEvHSrgATrVL5DUjm0SL0gohbYSiCV7dJN7jayGGNkpgrdvSzudfzrSx9iTFLmujBEvEK_-kheFqHJhtbKPbLVGOE9-PPIG0md2iJ7GiZC_ehjC8Yv4PiANibsQ-eYEfuB1GC8UE0w-jGnOHhwMiRb_O2PNdtPU79nu8PZRr3cZLEubKeE0UidLZwprSyOxRzQGexBVB4VzYMhJo0FJ6G2JBJWTqH9CCbmETs3Y89_tHdCeoz9BvLW_kPYOUd-gU0Qn</recordid><startdate>20220819</startdate><enddate>20220819</enddate><creator>Deshmukh, Soham</creator><creator>Lee, Charles</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220819</creationdate><title>Adapting Task-Oriented Dialogue Models for Email Conversations</title><author>Deshmukh, Soham ; Lee, Charles</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-30f4deb17f5299751dcdd55dca08ba2ffa5ef154a31ac97dea8f1d47de3016ab3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Deshmukh, Soham</creatorcontrib><creatorcontrib>Lee, Charles</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Deshmukh, Soham</au><au>Lee, Charles</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Adapting Task-Oriented Dialogue Models for Email Conversations</atitle><date>2022-08-19</date><risdate>2022</risdate><abstract>Intent detection is a key part of any Natural Language Understanding (NLU)
system of a conversational assistant. Detecting the correct intent is essential
yet difficult for email conversations where multiple directives and intents are
present. In such settings, conversation context can become a key disambiguating
factor for detecting the user's request from the assistant. One prominent way
of incorporating context is modeling past conversation history like
task-oriented dialogue models. However, the nature of email conversations (long
form) restricts direct usage of the latest advances in task-oriented dialogue
models. So in this paper, we provide an effective transfer learning framework
(EMToD) that allows the latest development in dialogue models to be adapted for
long-form conversations. We show that the proposed EMToD framework improves
intent detection performance over pre-trained language models by 45% and over
pre-trained dialogue models by 30% for task-oriented email conversations.
Additionally, the modular nature of the proposed framework allows plug-and-play
for any future developments in both pre-trained language and task-oriented
dialogue models.</abstract><doi>10.48550/arxiv.2208.09439</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2208.09439 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2208_09439 |
source | arXiv.org |
subjects | Computer Science - Computation and Language |
title | Adapting Task-Oriented Dialogue Models for Email Conversations |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T18%3A14%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Adapting%20Task-Oriented%20Dialogue%20Models%20for%20Email%20Conversations&rft.au=Deshmukh,%20Soham&rft.date=2022-08-19&rft_id=info:doi/10.48550/arxiv.2208.09439&rft_dat=%3Carxiv_GOX%3E2208_09439%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |