Let's Talk! Striking Up Conversations via Conversational Visual Question Generation

Let's Talk! Striking Up Conversations via Conversational Visual Question Generation

An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example, from social media platforms) and asks an engaging question to initiate a conversation with the user. The existing...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-05
Hauptverfasser: Shih-Han, Chan, Tsai-Lun, Yang, Yun-Wei, Chu, Chi-Yang, Hsu, Ting-Hao, Huang, Yu-Shian Chiu, Lun-Wei Ku
Format: Artikel
Sprache:eng
Schlagworte:
Questions
Starters
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Shih-Han, Chan
Tsai-Lun, Yang
Yun-Wei, Chu
Chi-Yang, Hsu
Ting-Hao, Huang
Yu-Shian Chiu
Lun-Wei Ku
description An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example, from social media platforms) and asks an engaging question to initiate a conversation with the user. The existing vision-to-question models mostly generate tedious and obvious questions, which might not be ideals conversation starters. This paper introduces a two-phase framework that first generates a visual story for the photo set and then uses the story to produce an interesting question. The human evaluation shows that our framework generates more response-provoking questions for starting conversations than other vision-to-question baselines.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2667073754</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2667073754</sourcerecordid><originalsourceid>FETCH-proquest_journals_26670737543</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQI9kktUS9WCEnMyVZUCC4pyszOzEtXCC1QcM7PK0stKk4syczPK1Yoy0xEEUnMUQjLLC4FUoGlqcUgEQX31LzUIrAkDwNrWmJOcSovlOZmUHZzDXH20C0oyi8EKY_Pyi8tAppRHG9kZmZuYG5sbmpiTJwqABL_QCA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2667073754</pqid></control><display><type>article</type><title>Let's Talk! Striking Up Conversations via Conversational Visual Question Generation</title><source>Free E- Journals</source><creator>Shih-Han, Chan ; Tsai-Lun, Yang ; Yun-Wei, Chu ; Chi-Yang, Hsu ; Ting-Hao, Huang ; Yu-Shian Chiu ; Lun-Wei Ku</creator><creatorcontrib>Shih-Han, Chan ; Tsai-Lun, Yang ; Yun-Wei, Chu ; Chi-Yang, Hsu ; Ting-Hao, Huang ; Yu-Shian Chiu ; Lun-Wei Ku</creatorcontrib><description>An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example, from social media platforms) and asks an engaging question to initiate a conversation with the user. The existing vision-to-question models mostly generate tedious and obvious questions, which might not be ideals conversation starters. This paper introduces a two-phase framework that first generates a visual story for the photo set and then uses the story to produce an interesting question. The human evaluation shows that our framework generates more response-provoking questions for starting conversations than other vision-to-question baselines.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Questions ; Starters</subject><ispartof>arXiv.org, 2022-05</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Shih-Han, Chan</creatorcontrib><creatorcontrib>Tsai-Lun, Yang</creatorcontrib><creatorcontrib>Yun-Wei, Chu</creatorcontrib><creatorcontrib>Chi-Yang, Hsu</creatorcontrib><creatorcontrib>Ting-Hao, Huang</creatorcontrib><creatorcontrib>Yu-Shian Chiu</creatorcontrib><creatorcontrib>Lun-Wei Ku</creatorcontrib><title>Let's Talk! Striking Up Conversations via Conversational Visual Question Generation</title><title>arXiv.org</title><description>An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example, from social media platforms) and asks an engaging question to initiate a conversation with the user. The existing vision-to-question models mostly generate tedious and obvious questions, which might not be ideals conversation starters. This paper introduces a two-phase framework that first generates a visual story for the photo set and then uses the story to produce an interesting question. The human evaluation shows that our framework generates more response-provoking questions for starting conversations than other vision-to-question baselines.</description><subject>Questions</subject><subject>Starters</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQI9kktUS9WCEnMyVZUCC4pyszOzEtXCC1QcM7PK0stKk4syczPK1Yoy0xEEUnMUQjLLC4FUoGlqcUgEQX31LzUIrAkDwNrWmJOcSovlOZmUHZzDXH20C0oyi8EKY_Pyi8tAppRHG9kZmZuYG5sbmpiTJwqABL_QCA</recordid><startdate>20220519</startdate><enddate>20220519</enddate><creator>Shih-Han, Chan</creator><creator>Tsai-Lun, Yang</creator><creator>Yun-Wei, Chu</creator><creator>Chi-Yang, Hsu</creator><creator>Ting-Hao, Huang</creator><creator>Yu-Shian Chiu</creator><creator>Lun-Wei Ku</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220519</creationdate><title>Let's Talk! Striking Up Conversations via Conversational Visual Question Generation</title><author>Shih-Han, Chan ; Tsai-Lun, Yang ; Yun-Wei, Chu ; Chi-Yang, Hsu ; Ting-Hao, Huang ; Yu-Shian Chiu ; Lun-Wei Ku</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26670737543</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Questions</topic><topic>Starters</topic><toplevel>online_resources</toplevel><creatorcontrib>Shih-Han, Chan</creatorcontrib><creatorcontrib>Tsai-Lun, Yang</creatorcontrib><creatorcontrib>Yun-Wei, Chu</creatorcontrib><creatorcontrib>Chi-Yang, Hsu</creatorcontrib><creatorcontrib>Ting-Hao, Huang</creatorcontrib><creatorcontrib>Yu-Shian Chiu</creatorcontrib><creatorcontrib>Lun-Wei Ku</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shih-Han, Chan</au><au>Tsai-Lun, Yang</au><au>Yun-Wei, Chu</au><au>Chi-Yang, Hsu</au><au>Ting-Hao, Huang</au><au>Yu-Shian Chiu</au><au>Lun-Wei Ku</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Let's Talk! Striking Up Conversations via Conversational Visual Question Generation</atitle><jtitle>arXiv.org</jtitle><date>2022-05-19</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example, from social media platforms) and asks an engaging question to initiate a conversation with the user. The existing vision-to-question models mostly generate tedious and obvious questions, which might not be ideals conversation starters. This paper introduces a two-phase framework that first generates a visual story for the photo set and then uses the story to produce an interesting question. The human evaluation shows that our framework generates more response-provoking questions for starting conversations than other vision-to-question baselines.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2667073754
source Free E- Journals
subjects Questions
Starters
title Let's Talk! Striking Up Conversations via Conversational Visual Question Generation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T00%3A35%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Let's%20Talk!%20Striking%20Up%20Conversations%20via%20Conversational%20Visual%20Question%20Generation&rft.jtitle=arXiv.org&rft.au=Shih-Han,%20Chan&rft.date=2022-05-19&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2667073754%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2667073754&rft_id=info:pmid/&rfr_iscdi=true