Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff

Is chatbot able to completely replace the human agent? The short answer could be - "it depends...". For some challenging cases, e.g., dialogue's topical spectrum spreads beyond the training corpus coverage, the chatbot may malfunction and return unsatisfied utterances. This problem ca...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Jiawei, Gao, Zhe, Kang, Yangyang, Jiang, Zhuoren, He, Guoxiu, Sun, Changlong, Liu, Xiaozhong, Lu, Wei
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 Liu, Jiawei
Gao, Zhe
Kang, Yangyang
Jiang, Zhuoren
He, Guoxiu
Sun, Changlong
Liu, Xiaozhong
Lu, Wei
description Is chatbot able to completely replace the human agent? The short answer could be - "it depends...". For some challenging cases, e.g., dialogue's topical spectrum spreads beyond the training corpus coverage, the chatbot may malfunction and return unsatisfied utterances. This problem can be addressed by introducing the Machine-Human Chatting Handoff (MHCH), which enables human-algorithm collaboration. To detect the normal/transferable utterances, we propose a Difficulty-Assisted Matching Inference (DAMI) network, utilizing difficulty-assisted encoding to enhance the representations of utterances. Moreover, a matching inference mechanism is introduced to capture the contextual matching features. A new evaluation metric, Golden Transfer within Tolerance (GT-T), is proposed to assess the performance by considering the tolerance property of the MHCH. To provide insights into the task and validate the proposed model, we collect two new datasets. Extensive experimental results are presented and contrasted against a series of baseline models to demonstrate the efficacy of our model on MHCH.
doi_str_mv 10.48550/arxiv.2012.07610
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2012_07610</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2012_07610</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-ba73c96309ad1e1d01c8add411f735b6fd76d791cf11821fd9a414c9486b62803</originalsourceid><addsrcrecordid>eNotj8tOwzAURL3pArV8ACv8Awm-seMHOxQVAmpVFtlHN35QS42L3LSCvwdCV6MZHY10CLkDVgpd1-wB81e8lBWDqmRKArshb10cPZ2OtMuYTsHnR_qevYt2iumDYnJ0fcHDGee6RbuPyRftecREmz1O89z-YscQVmQR8HDyt9dcku553TVtsdm9vDZPmwKlYsWAilsjOTPowINjYDU6JwCC4vUgg1PSKQM2AOgKgjMoQFgjtBxkpRlfkvv_21mm_8xxxPzd_0n1sxT_AdlbRoM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff</title><source>arXiv.org</source><creator>Liu, Jiawei ; Gao, Zhe ; Kang, Yangyang ; Jiang, Zhuoren ; He, Guoxiu ; Sun, Changlong ; Liu, Xiaozhong ; Lu, Wei</creator><creatorcontrib>Liu, Jiawei ; Gao, Zhe ; Kang, Yangyang ; Jiang, Zhuoren ; He, Guoxiu ; Sun, Changlong ; Liu, Xiaozhong ; Lu, Wei</creatorcontrib><description>Is chatbot able to completely replace the human agent? The short answer could be - "it depends...". For some challenging cases, e.g., dialogue's topical spectrum spreads beyond the training corpus coverage, the chatbot may malfunction and return unsatisfied utterances. This problem can be addressed by introducing the Machine-Human Chatting Handoff (MHCH), which enables human-algorithm collaboration. To detect the normal/transferable utterances, we propose a Difficulty-Assisted Matching Inference (DAMI) network, utilizing difficulty-assisted encoding to enhance the representations of utterances. Moreover, a matching inference mechanism is introduced to capture the contextual matching features. A new evaluation metric, Golden Transfer within Tolerance (GT-T), is proposed to assess the performance by considering the tolerance property of the MHCH. To provide insights into the task and validate the proposed model, we collect two new datasets. Extensive experimental results are presented and contrasted against a series of baseline models to demonstrate the efficacy of our model on MHCH.</description><identifier>DOI: 10.48550/arxiv.2012.07610</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Human-Computer Interaction</subject><creationdate>2020-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2012.07610$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2012.07610$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Jiawei</creatorcontrib><creatorcontrib>Gao, Zhe</creatorcontrib><creatorcontrib>Kang, Yangyang</creatorcontrib><creatorcontrib>Jiang, Zhuoren</creatorcontrib><creatorcontrib>He, Guoxiu</creatorcontrib><creatorcontrib>Sun, Changlong</creatorcontrib><creatorcontrib>Liu, Xiaozhong</creatorcontrib><creatorcontrib>Lu, Wei</creatorcontrib><title>Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff</title><description>Is chatbot able to completely replace the human agent? The short answer could be - "it depends...". For some challenging cases, e.g., dialogue's topical spectrum spreads beyond the training corpus coverage, the chatbot may malfunction and return unsatisfied utterances. This problem can be addressed by introducing the Machine-Human Chatting Handoff (MHCH), which enables human-algorithm collaboration. To detect the normal/transferable utterances, we propose a Difficulty-Assisted Matching Inference (DAMI) network, utilizing difficulty-assisted encoding to enhance the representations of utterances. Moreover, a matching inference mechanism is introduced to capture the contextual matching features. A new evaluation metric, Golden Transfer within Tolerance (GT-T), is proposed to assess the performance by considering the tolerance property of the MHCH. To provide insights into the task and validate the proposed model, we collect two new datasets. Extensive experimental results are presented and contrasted against a series of baseline models to demonstrate the efficacy of our model on MHCH.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Human-Computer Interaction</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAURL3pArV8ACv8Awm-seMHOxQVAmpVFtlHN35QS42L3LSCvwdCV6MZHY10CLkDVgpd1-wB81e8lBWDqmRKArshb10cPZ2OtMuYTsHnR_qevYt2iumDYnJ0fcHDGee6RbuPyRftecREmz1O89z-YscQVmQR8HDyt9dcku553TVtsdm9vDZPmwKlYsWAilsjOTPowINjYDU6JwCC4vUgg1PSKQM2AOgKgjMoQFgjtBxkpRlfkvv_21mm_8xxxPzd_0n1sxT_AdlbRoM</recordid><startdate>20201214</startdate><enddate>20201214</enddate><creator>Liu, Jiawei</creator><creator>Gao, Zhe</creator><creator>Kang, Yangyang</creator><creator>Jiang, Zhuoren</creator><creator>He, Guoxiu</creator><creator>Sun, Changlong</creator><creator>Liu, Xiaozhong</creator><creator>Lu, Wei</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201214</creationdate><title>Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff</title><author>Liu, Jiawei ; Gao, Zhe ; Kang, Yangyang ; Jiang, Zhuoren ; He, Guoxiu ; Sun, Changlong ; Liu, Xiaozhong ; Lu, Wei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-ba73c96309ad1e1d01c8add411f735b6fd76d791cf11821fd9a414c9486b62803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Human-Computer Interaction</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Jiawei</creatorcontrib><creatorcontrib>Gao, Zhe</creatorcontrib><creatorcontrib>Kang, Yangyang</creatorcontrib><creatorcontrib>Jiang, Zhuoren</creatorcontrib><creatorcontrib>He, Guoxiu</creatorcontrib><creatorcontrib>Sun, Changlong</creatorcontrib><creatorcontrib>Liu, Xiaozhong</creatorcontrib><creatorcontrib>Lu, Wei</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Liu, Jiawei</au><au>Gao, Zhe</au><au>Kang, Yangyang</au><au>Jiang, Zhuoren</au><au>He, Guoxiu</au><au>Sun, Changlong</au><au>Liu, Xiaozhong</au><au>Lu, Wei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff</atitle><date>2020-12-14</date><risdate>2020</risdate><abstract>Is chatbot able to completely replace the human agent? The short answer could be - "it depends...". For some challenging cases, e.g., dialogue's topical spectrum spreads beyond the training corpus coverage, the chatbot may malfunction and return unsatisfied utterances. This problem can be addressed by introducing the Machine-Human Chatting Handoff (MHCH), which enables human-algorithm collaboration. To detect the normal/transferable utterances, we propose a Difficulty-Assisted Matching Inference (DAMI) network, utilizing difficulty-assisted encoding to enhance the representations of utterances. Moreover, a matching inference mechanism is introduced to capture the contextual matching features. A new evaluation metric, Golden Transfer within Tolerance (GT-T), is proposed to assess the performance by considering the tolerance property of the MHCH. To provide insights into the task and validate the proposed model, we collect two new datasets. Extensive experimental results are presented and contrasted against a series of baseline models to demonstrate the efficacy of our model on MHCH.</abstract><doi>10.48550/arxiv.2012.07610</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2012.07610
ispartof
issn
language eng
recordid cdi_arxiv_primary_2012_07610
source arXiv.org
subjects Computer Science - Computation and Language
Computer Science - Human-Computer Interaction
title Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T13%3A52%3A55IST&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=Time%20to%20Transfer:%20Predicting%20and%20Evaluating%20Machine-Human%20Chatting%20Handoff&rft.au=Liu,%20Jiawei&rft.date=2020-12-14&rft_id=info:doi/10.48550/arxiv.2012.07610&rft_dat=%3Carxiv_GOX%3E2012_07610%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