Mitigating Contradictions in Dialogue Based on Contrastive Learning Article Swipe
Weizhao Li
,
Junsheng Kong
,
Ben Liao
,
Yi Cai
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2022.findings-acl.219
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2022.findings-acl.219
Chatbot models have achieved remarkable progress in recent years but tend to yield contradictory responses. In this paper, we exploit the advantage of contrastive learning technique to mitigate this issue. To endow the model with the ability of discriminating contradictory patterns, we minimize the similarity between the target response and contradiction related negative example. The negative example is generated with learnable latent noise, which receives contradiction related feedback from the pretrained critic. Experimental results show that our method helps to avoid contradictions in response generation while preserving response fluency, outperforming existing methods on both automatic and human evaluation.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.18653/v1/2022.findings-acl.219
- https://aclanthology.org/2022.findings-acl.219.pdf
- OA Status
- hybrid
- Cited By
- 5
- References
- 28
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4285238886
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4285238886Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.18653/v1/2022.findings-acl.219Digital Object Identifier
- Title
-
Mitigating Contradictions in Dialogue Based on Contrastive LearningWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-01Full publication date if available
- Authors
-
Weizhao Li, Junsheng Kong, Ben Liao, Yi CaiList of authors in order
- Landing page
-
https://doi.org/10.18653/v1/2022.findings-acl.219Publisher landing page
- PDF URL
-
https://aclanthology.org/2022.findings-acl.219.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://aclanthology.org/2022.findings-acl.219.pdfDirect OA link when available
- Concepts
-
Exploit, Contradiction, Fluency, Computer science, Artificial intelligence, Chatbot, Machine learning, Linguistics, Philosophy, Computer securityTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
5Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2023: 4Per-year citation counts (last 5 years)
- References (count)
-
28Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4285238886 |
|---|---|
| doi | https://doi.org/10.18653/v1/2022.findings-acl.219 |
| ids.doi | https://doi.org/10.18653/v1/2022.findings-acl.219 |
| ids.openalex | https://openalex.org/W4285238886 |
| fwci | 0.5877752 |
| type | article |
| title | Mitigating Contradictions in Dialogue Based on Contrastive Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 2788 |
| biblio.first_page | 2781 |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9991999864578247 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T12031 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9800999760627747 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Speech and dialogue systems |
| topics[2].id | https://openalex.org/T12128 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9793999791145325 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | AI in Service Interactions |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C165696696 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8007055521011353 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q11287 |
| concepts[0].display_name | Exploit |
| concepts[1].id | https://openalex.org/C2776728590 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7777576446533203 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q363948 |
| concepts[1].display_name | Contradiction |
| concepts[2].id | https://openalex.org/C2777413886 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7450129985809326 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q3276013 |
| concepts[2].display_name | Fluency |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.7303439378738403 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5397118330001831 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C2779041454 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5174282193183899 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q870780 |
| concepts[5].display_name | Chatbot |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.40892988443374634 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C41895202 |
| concepts[7].level | 1 |
| concepts[7].score | 0.1705315113067627 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[7].display_name | Linguistics |
| concepts[8].id | https://openalex.org/C138885662 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[8].display_name | Philosophy |
| concepts[9].id | https://openalex.org/C38652104 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[9].display_name | Computer security |
| keywords[0].id | https://openalex.org/keywords/exploit |
| keywords[0].score | 0.8007055521011353 |
| keywords[0].display_name | Exploit |
| keywords[1].id | https://openalex.org/keywords/contradiction |
| keywords[1].score | 0.7777576446533203 |
| keywords[1].display_name | Contradiction |
| keywords[2].id | https://openalex.org/keywords/fluency |
| keywords[2].score | 0.7450129985809326 |
| keywords[2].display_name | Fluency |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.7303439378738403 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.5397118330001831 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/chatbot |
| keywords[5].score | 0.5174282193183899 |
| keywords[5].display_name | Chatbot |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.40892988443374634 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/linguistics |
| keywords[7].score | 0.1705315113067627 |
| keywords[7].display_name | Linguistics |
| language | en |
| locations[0].id | doi:10.18653/v1/2022.findings-acl.219 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4363605144 |
| locations[0].source.issn | |
| locations[0].source.type | conference |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Findings of the Association for Computational Linguistics: ACL 2022 |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://aclanthology.org/2022.findings-acl.219.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Findings of the Association for Computational Linguistics: ACL 2022 |
| locations[0].landing_page_url | https://doi.org/10.18653/v1/2022.findings-acl.219 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5006326179 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4394-4987 |
| authorships[0].author.display_name | Weizhao Li |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].raw_affiliation_string | Key Laboratory of Big Data and Intelligent Robot (SCUT), MOE of China |
| authorships[0].affiliations[1].institution_ids | https://openalex.org/I90610280 |
| authorships[0].affiliations[1].raw_affiliation_string | School of Software Engineering, South China University of Technology |
| authorships[0].institutions[0].id | https://openalex.org/I90610280 |
| authorships[0].institutions[0].ror | https://ror.org/0530pts50 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I90610280 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | South China University of Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Weizhao Li |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Key Laboratory of Big Data and Intelligent Robot (SCUT), MOE of China, School of Software Engineering, South China University of Technology |
| authorships[1].author.id | https://openalex.org/A5045187263 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Junsheng Kong |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I90610280 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Software Engineering, South China University of Technology |
| authorships[1].affiliations[1].raw_affiliation_string | Key Laboratory of Big Data and Intelligent Robot (SCUT), MOE of China |
| authorships[1].institutions[0].id | https://openalex.org/I90610280 |
| authorships[1].institutions[0].ror | https://ror.org/0530pts50 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I90610280 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | South China University of Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Junsheng Kong |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Key Laboratory of Big Data and Intelligent Robot (SCUT), MOE of China, School of Software Engineering, South China University of Technology |
| authorships[2].author.id | https://openalex.org/A5064163623 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5084-2682 |
| authorships[2].author.display_name | Ben Liao |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I2250653659 |
| authorships[2].affiliations[0].raw_affiliation_string | Tencent Quantum Lab |
| authorships[2].institutions[0].id | https://openalex.org/I2250653659 |
| authorships[2].institutions[0].ror | https://ror.org/00hhjss72 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I2250653659 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Tencent (China) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ben Liao |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Tencent Quantum Lab |
| authorships[3].author.id | https://openalex.org/A5089123257 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1767-789X |
| authorships[3].author.display_name | Yi Cai |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].raw_affiliation_string | Key Laboratory of Big Data and Intelligent Robot (SCUT), MOE of China |
| authorships[3].affiliations[1].institution_ids | https://openalex.org/I90610280 |
| authorships[3].affiliations[1].raw_affiliation_string | School of Software Engineering, South China University of Technology |
| authorships[3].institutions[0].id | https://openalex.org/I90610280 |
| authorships[3].institutions[0].ror | https://ror.org/0530pts50 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I90610280 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | South China University of Technology |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Yi Cai |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Key Laboratory of Big Data and Intelligent Robot (SCUT), MOE of China, School of Software Engineering, South China University of Technology |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://aclanthology.org/2022.findings-acl.219.pdf |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Mitigating Contradictions in Dialogue Based on Contrastive Learning |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9991999864578247 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W4383501580, https://openalex.org/W4214931137, https://openalex.org/W4387007686, https://openalex.org/W4313813117, https://openalex.org/W4382052417, https://openalex.org/W3192088754, https://openalex.org/W3084631705, https://openalex.org/W2381825231, https://openalex.org/W3176146353, https://openalex.org/W4293646425 |
| cited_by_count | 5 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 4 |
| locations_count | 1 |
| best_oa_location.id | doi:10.18653/v1/2022.findings-acl.219 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4363605144 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Findings of the Association for Computational Linguistics: ACL 2022 |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://aclanthology.org/2022.findings-acl.219.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Findings of the Association for Computational Linguistics: ACL 2022 |
| best_oa_location.landing_page_url | https://doi.org/10.18653/v1/2022.findings-acl.219 |
| primary_location.id | doi:10.18653/v1/2022.findings-acl.219 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4363605144 |
| primary_location.source.issn | |
| primary_location.source.type | conference |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Findings of the Association for Computational Linguistics: ACL 2022 |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://aclanthology.org/2022.findings-acl.219.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Findings of the Association for Computational Linguistics: ACL 2022 |
| primary_location.landing_page_url | https://doi.org/10.18653/v1/2022.findings-acl.219 |
| publication_date | 2022-01-01 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W3035656139, https://openalex.org/W3156636935, https://openalex.org/W3128699722, https://openalex.org/W2980433389, https://openalex.org/W3035451444, https://openalex.org/W2965373594, https://openalex.org/W3173190788, https://openalex.org/W4287692509, https://openalex.org/W3099617520, https://openalex.org/W2983160116, https://openalex.org/W2964289358, https://openalex.org/W4287547182, https://openalex.org/W1945616565, https://openalex.org/W4287900772, https://openalex.org/W3173210704, https://openalex.org/W2963167310, https://openalex.org/W3035068109, https://openalex.org/W2963903950, https://openalex.org/W2972916088, https://openalex.org/W1975879668, https://openalex.org/W3155584966, https://openalex.org/W3173803111, https://openalex.org/W3175643241, https://openalex.org/W3022187094, https://openalex.org/W3034600233, https://openalex.org/W46849891, https://openalex.org/W3005680577, https://openalex.org/W2962852262 |
| referenced_works_count | 28 |
| abstract_inverted_index.In | 15 |
| abstract_inverted_index.To | 30 |
| abstract_inverted_index.in | 6, 82 |
| abstract_inverted_index.is | 57 |
| abstract_inverted_index.of | 22, 37 |
| abstract_inverted_index.on | 92 |
| abstract_inverted_index.to | 11, 26, 79 |
| abstract_inverted_index.we | 18, 41 |
| abstract_inverted_index.The | 54 |
| abstract_inverted_index.and | 49, 95 |
| abstract_inverted_index.but | 9 |
| abstract_inverted_index.our | 76 |
| abstract_inverted_index.the | 20, 32, 35, 43, 46, 69 |
| abstract_inverted_index.both | 93 |
| abstract_inverted_index.from | 68 |
| abstract_inverted_index.have | 2 |
| abstract_inverted_index.show | 74 |
| abstract_inverted_index.tend | 10 |
| abstract_inverted_index.that | 75 |
| abstract_inverted_index.this | 16, 28 |
| abstract_inverted_index.with | 34, 59 |
| abstract_inverted_index.avoid | 80 |
| abstract_inverted_index.endow | 31 |
| abstract_inverted_index.helps | 78 |
| abstract_inverted_index.human | 96 |
| abstract_inverted_index.model | 33 |
| abstract_inverted_index.which | 63 |
| abstract_inverted_index.while | 85 |
| abstract_inverted_index.years | 8 |
| abstract_inverted_index.yield | 12 |
| abstract_inverted_index.issue. | 29 |
| abstract_inverted_index.latent | 61 |
| abstract_inverted_index.method | 77 |
| abstract_inverted_index.models | 1 |
| abstract_inverted_index.noise, | 62 |
| abstract_inverted_index.paper, | 17 |
| abstract_inverted_index.recent | 7 |
| abstract_inverted_index.target | 47 |
| abstract_inverted_index.Chatbot | 0 |
| abstract_inverted_index.ability | 36 |
| abstract_inverted_index.between | 45 |
| abstract_inverted_index.critic. | 71 |
| abstract_inverted_index.example | 56 |
| abstract_inverted_index.exploit | 19 |
| abstract_inverted_index.methods | 91 |
| abstract_inverted_index.related | 51, 66 |
| abstract_inverted_index.results | 73 |
| abstract_inverted_index.achieved | 3 |
| abstract_inverted_index.example. | 53 |
| abstract_inverted_index.existing | 90 |
| abstract_inverted_index.feedback | 67 |
| abstract_inverted_index.fluency, | 88 |
| abstract_inverted_index.learning | 24 |
| abstract_inverted_index.minimize | 42 |
| abstract_inverted_index.mitigate | 27 |
| abstract_inverted_index.negative | 52, 55 |
| abstract_inverted_index.progress | 5 |
| abstract_inverted_index.receives | 64 |
| abstract_inverted_index.response | 48, 83, 87 |
| abstract_inverted_index.advantage | 21 |
| abstract_inverted_index.automatic | 94 |
| abstract_inverted_index.generated | 58 |
| abstract_inverted_index.learnable | 60 |
| abstract_inverted_index.patterns, | 40 |
| abstract_inverted_index.technique | 25 |
| abstract_inverted_index.generation | 84 |
| abstract_inverted_index.preserving | 86 |
| abstract_inverted_index.pretrained | 70 |
| abstract_inverted_index.remarkable | 4 |
| abstract_inverted_index.responses. | 14 |
| abstract_inverted_index.similarity | 44 |
| abstract_inverted_index.contrastive | 23 |
| abstract_inverted_index.evaluation. | 97 |
| abstract_inverted_index.Experimental | 72 |
| abstract_inverted_index.contradiction | 50, 65 |
| abstract_inverted_index.contradictory | 13, 39 |
| abstract_inverted_index.outperforming | 89 |
| abstract_inverted_index.contradictions | 81 |
| abstract_inverted_index.discriminating | 38 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.7400000095367432 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile.value | 0.63107686 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |