Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding

To build a satisfying chatbot that has the ability of managing a goal-oriented multi-turn dialogue, accurate modeling of human conversation is crucial. In this paper we concentrate on the task of response selection for multi-turn human-computer conversation with a given context. Previous approaches...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: An, Guozhen, Shafiee, Mehrnoosh, Shamsi, Davood
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 An, Guozhen
Shafiee, Mehrnoosh
Shamsi, Davood
description To build a satisfying chatbot that has the ability of managing a goal-oriented multi-turn dialogue, accurate modeling of human conversation is crucial. In this paper we concentrate on the task of response selection for multi-turn human-computer conversation with a given context. Previous approaches show weakness in capturing information of rare keywords that appear in either or both context and correct response, and struggle with long input sequences. We propose Cross Convolution Network (CCN) and Multi Frequency word embedding to address both problems. We train several models using the Ubuntu Dialogue dataset which is the largest freely available multi-turn based dialogue corpus. We further build an ensemble model by averaging predictions of multiple models. We achieve a new state-of-the-art on this dataset with considerable improvements compared to previous best results.
doi_str_mv 10.48550/arxiv.1802.05373
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1802_05373</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1802_05373</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-ccce5c6b21e2499248a3ed5d415c62bbd82857a6c5d6135cca03ec19f4cca71a3</originalsourceid><addsrcrecordid>eNotj0tOwzAYhL1hgQoHYIUvkOBHnMeyilqo1BYJFbEMjv0XWTh2sZNAb09S2MyMRpqRPoTuKEmzUgjyIMOPGVNaEpYSwQt-jd433Sn40bgP_AJ9MDBKi3deg52r1zhrHXyMuPZu9HbojXd4D_23D58RL53Gu8H2Bq8DfA3g1Bm_-aDxqmtB62l9g66O0ka4_fcFOqxXh_op2T4_burlNpF5wROlFAiVt4wCy6qKZaXkoIXO6NSyttUlK0UhcyV0TrlQShIOilbHbIoFlXyB7v9uL4jNKZhOhnMzozYXVP4LZnZQgw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding</title><source>arXiv.org</source><creator>An, Guozhen ; Shafiee, Mehrnoosh ; Shamsi, Davood</creator><creatorcontrib>An, Guozhen ; Shafiee, Mehrnoosh ; Shamsi, Davood</creatorcontrib><description>To build a satisfying chatbot that has the ability of managing a goal-oriented multi-turn dialogue, accurate modeling of human conversation is crucial. In this paper we concentrate on the task of response selection for multi-turn human-computer conversation with a given context. Previous approaches show weakness in capturing information of rare keywords that appear in either or both context and correct response, and struggle with long input sequences. We propose Cross Convolution Network (CCN) and Multi Frequency word embedding to address both problems. We train several models using the Ubuntu Dialogue dataset which is the largest freely available multi-turn based dialogue corpus. We further build an ensemble model by averaging predictions of multiple models. We achieve a new state-of-the-art on this dataset with considerable improvements compared to previous best results.</description><identifier>DOI: 10.48550/arxiv.1802.05373</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2018-02</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1802.05373$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1802.05373$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>An, Guozhen</creatorcontrib><creatorcontrib>Shafiee, Mehrnoosh</creatorcontrib><creatorcontrib>Shamsi, Davood</creatorcontrib><title>Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding</title><description>To build a satisfying chatbot that has the ability of managing a goal-oriented multi-turn dialogue, accurate modeling of human conversation is crucial. In this paper we concentrate on the task of response selection for multi-turn human-computer conversation with a given context. Previous approaches show weakness in capturing information of rare keywords that appear in either or both context and correct response, and struggle with long input sequences. We propose Cross Convolution Network (CCN) and Multi Frequency word embedding to address both problems. We train several models using the Ubuntu Dialogue dataset which is the largest freely available multi-turn based dialogue corpus. We further build an ensemble model by averaging predictions of multiple models. We achieve a new state-of-the-art on this dataset with considerable improvements compared to previous best results.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj0tOwzAYhL1hgQoHYIUvkOBHnMeyilqo1BYJFbEMjv0XWTh2sZNAb09S2MyMRpqRPoTuKEmzUgjyIMOPGVNaEpYSwQt-jd433Sn40bgP_AJ9MDBKi3deg52r1zhrHXyMuPZu9HbojXd4D_23D58RL53Gu8H2Bq8DfA3g1Bm_-aDxqmtB62l9g66O0ka4_fcFOqxXh_op2T4_burlNpF5wROlFAiVt4wCy6qKZaXkoIXO6NSyttUlK0UhcyV0TrlQShIOilbHbIoFlXyB7v9uL4jNKZhOhnMzozYXVP4LZnZQgw</recordid><startdate>20180214</startdate><enddate>20180214</enddate><creator>An, Guozhen</creator><creator>Shafiee, Mehrnoosh</creator><creator>Shamsi, Davood</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20180214</creationdate><title>Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding</title><author>An, Guozhen ; Shafiee, Mehrnoosh ; Shamsi, Davood</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-ccce5c6b21e2499248a3ed5d415c62bbd82857a6c5d6135cca03ec19f4cca71a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>An, Guozhen</creatorcontrib><creatorcontrib>Shafiee, Mehrnoosh</creatorcontrib><creatorcontrib>Shamsi, Davood</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>An, Guozhen</au><au>Shafiee, Mehrnoosh</au><au>Shamsi, Davood</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding</atitle><date>2018-02-14</date><risdate>2018</risdate><abstract>To build a satisfying chatbot that has the ability of managing a goal-oriented multi-turn dialogue, accurate modeling of human conversation is crucial. In this paper we concentrate on the task of response selection for multi-turn human-computer conversation with a given context. Previous approaches show weakness in capturing information of rare keywords that appear in either or both context and correct response, and struggle with long input sequences. We propose Cross Convolution Network (CCN) and Multi Frequency word embedding to address both problems. We train several models using the Ubuntu Dialogue dataset which is the largest freely available multi-turn based dialogue corpus. We further build an ensemble model by averaging predictions of multiple models. We achieve a new state-of-the-art on this dataset with considerable improvements compared to previous best results.</abstract><doi>10.48550/arxiv.1802.05373</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1802.05373
ispartof
issn
language eng
recordid cdi_arxiv_primary_1802_05373
source arXiv.org
subjects Computer Science - Computation and Language
title Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
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%3A54%3A00IST&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=Improving%20Retrieval%20Modeling%20Using%20Cross%20Convolution%20Networks%20And%20Multi%20Frequency%20Word%20Embedding&rft.au=An,%20Guozhen&rft.date=2018-02-14&rft_id=info:doi/10.48550/arxiv.1802.05373&rft_dat=%3Carxiv_GOX%3E1802_05373%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