Adaptive Parameterization for Neural Dialogue Generation
Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , |
Format | Paper Journal Article |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
18.01.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic responses. In this work, we propose an {\bf Ada}ptive {\bf N}eural {\bf D}ialogue generation model, \textsc{AdaND}, which manages various conversations with conversation-specific parameterization. For each conversation, the model generates parameters of the encoder-decoder by referring to the input context. In particular, we propose two adaptive parameterization mechanisms: a context-aware and a topic-aware parameterization mechanism. The context-aware parameterization directly generates the parameters by capturing local semantics of the given context. The topic-aware parameterization enables parameter sharing among conversations with similar topics by first inferring the latent topics of the given context and then generating the parameters with respect to the distributional topics. Extensive experiments conducted on a large-scale real-world conversational dataset show that our model achieves superior performance in terms of both quantitative metrics and human evaluations. |
---|---|
AbstractList | Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic responses. In this work, we propose an {\bf Ada}ptive {\bf N}eural {\bf D}ialogue generation model, \textsc{AdaND}, which manages various conversations with conversation-specific parameterization. For each conversation, the model generates parameters of the encoder-decoder by referring to the input context. In particular, we propose two adaptive parameterization mechanisms: a context-aware and a topic-aware parameterization mechanism. The context-aware parameterization directly generates the parameters by capturing local semantics of the given context. The topic-aware parameterization enables parameter sharing among conversations with similar topics by first inferring the latent topics of the given context and then generating the parameters with respect to the distributional topics. Extensive experiments conducted on a large-scale real-world conversational dataset show that our model achieves superior performance in terms of both quantitative metrics and human evaluations. Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic responses. In this work, we propose an {\bf Ada}ptive {\bf N}eural {\bf D}ialogue generation model, \textsc{AdaND}, which manages various conversations with conversation-specific parameterization. For each conversation, the model generates parameters of the encoder-decoder by referring to the input context. In particular, we propose two adaptive parameterization mechanisms: a context-aware and a topic-aware parameterization mechanism. The context-aware parameterization directly generates the parameters by capturing local semantics of the given context. The topic-aware parameterization enables parameter sharing among conversations with similar topics by first inferring the latent topics of the given context and then generating the parameters with respect to the distributional topics. Extensive experiments conducted on a large-scale real-world conversational dataset show that our model achieves superior performance in terms of both quantitative metrics and human evaluations. |
Author | Song, Yonghao Yin, Dawei Zhao, Xiaofang Chen, Hongshen Zhang, Cheng Cai, Hengyi |
Author_xml | – sequence: 1 givenname: Hengyi surname: Cai fullname: Cai, Hengyi – sequence: 2 givenname: Hongshen surname: Chen fullname: Chen, Hongshen – sequence: 3 givenname: Cheng surname: Zhang fullname: Zhang, Cheng – sequence: 4 givenname: Yonghao surname: Song fullname: Song, Yonghao – sequence: 5 givenname: Xiaofang surname: Zhao fullname: Zhao, Xiaofang – sequence: 6 givenname: Dawei surname: Yin fullname: Yin, Dawei |
BackLink | https://doi.org/10.18653/v1/D19-1188$$DView published paper (Access to full text may be restricted) https://doi.org/10.48550/arXiv.2001.06626$$DView paper in arXiv |
BookMark | eNotj8FOwzAQRC0EEqX0AzgRiXPCxms77rEqtCBVwKH3aIM3KFUaByepgK8ntJzmMKOZeVfivPENC3GTQqKs1nBP4as6JBIgTcAYac7ERCKmsVVSXopZ1-0AQJpMao0TYReO2r46cPRGgfbcc6h-qK98E5U-RC88BKqjh4pq_zFwtOaGw9G-Fhcl1R3P_nUqtqvH7fIp3ryun5eLTUxamtja0rlxCuAdDRI5a-auoKyggqhUzAVYNlqm89IpW6DTmjMtgRRm1hnCqbg91R6x8jZUewrf-R9efsQbE3enRBv858Bdn-_8EJrxUy5RIWqLmcFfUN5UYg |
ContentType | Paper Journal Article |
Copyright | 2020. 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. http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
Copyright_xml | – notice: 2020. 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. – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS AKY GOX |
DOI | 10.48550/arxiv.2001.06626 |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection arXiv Computer Science arXiv.org |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository – sequence: 2 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
ExternalDocumentID | 2001_06626 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS AKY GOX |
ID | FETCH-LOGICAL-a526-88fdd72500c363aad869dba7babaaf4eeb08e65219fd48b3d55e7520a4378d6a3 |
IEDL.DBID | 8FG |
IngestDate | Mon Jan 08 05:40:47 EST 2024 Thu Oct 10 16:30:11 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-a526-88fdd72500c363aad869dba7babaaf4eeb08e65219fd48b3d55e7520a4378d6a3 |
OpenAccessLink | https://www.proquest.com/docview/2343358376?pq-origsite=%requestingapplication% |
PQID | 2343358376 |
PQPubID | 2050157 |
ParticipantIDs | arxiv_primary_2001_06626 proquest_journals_2343358376 |
PublicationCentury | 2000 |
PublicationDate | 20200118 2020-01-18 |
PublicationDateYYYYMMDD | 2020-01-18 |
PublicationDate_xml | – month: 01 year: 2020 text: 20200118 day: 18 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2020 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 1.7624233 |
SecondaryResourceType | preprint |
Snippet | Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of... Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of... |
SourceID | arxiv proquest |
SourceType | Open Access Repository Aggregation Database |
SubjectTerms | Adaptive systems Coders Computer Science - Computation and Language Computer Science - Information Retrieval Computer Science - Learning Encoders-Decoders Mathematical models Parameterization Parameters Semantics |
SummonAdditionalLinks | – databaseName: arXiv.org dbid: GOX link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV07TwMxDLbaTiwIBKiFgjKwBvJObqyAUiHxGIrU7eQ0OakLqtqC-Pkkl6sYEGtiD3Gi-HNsfwG4VhbZkhtBEzz2VElU1KU4gobkLHi0upIsNyc_v5jZu3pa6EUPyL4XBjffq6_CD-y3t7ng5yZzlJs-9IXIJVuPr4uSnGypuDr5X7mEMduhP1dr6y-mR3DYAT0yKTtzDL34cQJuEnCdLxjyhrkqKhMllz5IksAjyUwZSed-VV5USOGEztOnMJ8-zO9mtPu7gKIWJq23CcEmeMGW0kjE4EwVPFqPHrFRMXrmokmus2qCcl4GrZNhBEMlrQsG5RkMUvgfh0C0SQBYch1VsKpRDEXUPCCrQs6gWD6CYbviel3oKfLHkrxujTGC8d4IdXc0t7WQSkqd4lJz_r_mBRyIHFgyTrkbw2C3-YyXyfvu_FW7BT95IYMS priority: 102 providerName: Cornell University |
Title | Adaptive Parameterization for Neural Dialogue Generation |
URI | https://www.proquest.com/docview/2343358376 https://arxiv.org/abs/2001.06626 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEF60xbNPWq0lB6-xu9lHkpP46AOhtUiF3sIku4GCtLGt4snf7kyS6kHwEtjsJfttmPd8w9iVCoFnwgQ-msepryQoP0I_wreoLIQLdSw5NSePJ2b0oh7nel4H3DZ1WeVOJpaC2q4yipH3Aqmk1OhOmZvizaepUZRdrUdo7LOmICY86hQfDH9iLIEJ0WKWVTKzpO7qwfpz8UFuobgm7nPqoC5f_RHFpX4ZHLLmFAq3PmJ7bnnMDsqyzGxzwqJbCwUJJG8KVEVFxMpV36SHxqZHzBrw6j0sqgiMV3FI0_Ypmw36s_uRX8868EEHBvHJrcWP5TyTRgLYyMQ2hTCFFCBXzqU8cgZVbZxbFaXSao1ABhyUDCNrQJ6xxnK1dC3maYMGsxTaKRuqXHEInBYWeGwp4xKKNmuVJ06Kis6CBlGKpASjzTo7EJL6V94kv8Cf_799gT5vQC1R6JZGHdbYrt_dJWrsbdotr6XLmnf9yfQZV8OnOT7HX_1vaAeXrw |
link.rule.ids | 228,230,786,790,891,12792,21416,27956,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LTwIxEJ4oxOjNZ0BR9-C10m4f2z0ZHxBUIMRgwm0zuy0JiYEV0PjzbXcXPZh4bS_t12be8w3AlYiQZkyFxJnHKREcBdHOjyDGKQtmIxlz6puTB0PVexVPEzmpAm6rqqxyIxMLQW0WmY-Rt0MuOJfOnVI3-TvxU6N8drUaobENdU-5qWtQv-sMRy8_UZZQRc5m5mU6syDvauPya_bpHUN27dnPfQ91sfRHGBcaprsP9RHmdnkAW3Z-CDtFYWa2OgJ9azD3IikYoa-j8tTKZedk4MzNwHNr4FvwMCtjMEHJIu23j2Hc7Yzve6SadkBQhsohNDXGHZbSjCuOaLSKTYpRiiniVFibUm2VU7bx1AidciOlgzKkKHikjUJ-ArX5Ym4bEEjlTGbOpBUmElNBMbSSGaSx8TmXiDWhUdw4yUtCCz-KkiUFGE1obUBIqs-8Sn6hP_1_-xJ2e-NBP-k_Dp_PYC_0rillhOkW1NbLD3vu9Pc6vage6Rtsw5gd |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Adaptive+Parameterization+for+Neural+Dialogue+Generation&rft.jtitle=arXiv.org&rft.au=Cai%2C+Hengyi&rft.au=Chen%2C+Hongshen&rft.au=Zhang%2C+Cheng&rft.au=Song%2C+Yonghao&rft.date=2020-01-18&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.2001.06626 |