Robust Dialogue State Tracking with Weak Supervision and Sparse Data Article Swipe
Michael Heck
,
Nurul Lubis
,
Carel van Niekerk
,
Shutong Feng
,
Christian Geishauser
,
Hsien-chin Lin
,
Milica Gašić
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2202.03354
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2202.03354
Generalising dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsity, distributional shift and the occurrence of new concepts and topics frequently lead to severe performance degradation during inference. In this paper we propose a training strategy to build extractive DST models without the need for fine-grained manual span labels. Two novel input-level dropout methods mitigate the negative impact of sample sparsity. We propose a new model architecture with a unified encoder that supports value as well as slot independence by leveraging the attention mechanism. We combine the strengths of triple copy strategy DST and value matching to benefit from complementary predictions without violating the principle of ontology independence. Our experiments demonstrate that an extractive DST model can be trained without manual span labels. Our architecture and training strategies improve robustness towards sample sparsity, new concepts and topics, leading to state-of-the-art performance on a range of benchmarks. We further highlight our model's ability to effectively learn from non-dialogue data.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2202.03354
- https://arxiv.org/pdf/2202.03354
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4221161082
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4221161082Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2202.03354Digital Object Identifier
- Title
-
Robust Dialogue State Tracking with Weak Supervision and Sparse DataWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-02-07Full publication date if available
- Authors
-
Michael Heck, Nurul Lubis, Carel van Niekerk, Shutong Feng, Christian Geishauser, Hsien-chin Lin, Milica GašićList of authors in order
- Landing page
-
https://arxiv.org/abs/2202.03354Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2202.03354Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2202.03354Direct OA link when available
- Concepts
-
Computer science, Robustness (evolution), Inference, Independence (probability theory), Artificial intelligence, Machine learning, Sample (material), Mathematics, Gene, Chemistry, Chromatography, Biochemistry, StatisticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4221161082 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2202.03354 |
| ids.doi | https://doi.org/10.48550/arxiv.2202.03354 |
| ids.openalex | https://openalex.org/W4221161082 |
| fwci | |
| type | preprint |
| title | Robust Dialogue State Tracking with Weak Supervision and Sparse Data |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12031 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9950000047683716 |
| 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 | Speech and dialogue systems |
| topics[1].id | https://openalex.org/T10028 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9948999881744385 |
| 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 | Topic Modeling |
| topics[2].id | https://openalex.org/T10444 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9451000094413757 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Context-Aware Activity Recognition Systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7689067125320435 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C63479239 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6640939116477966 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[1].display_name | Robustness (evolution) |
| concepts[2].id | https://openalex.org/C2776214188 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5834274888038635 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[2].display_name | Inference |
| concepts[3].id | https://openalex.org/C35651441 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5480034351348877 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q625303 |
| concepts[3].display_name | Independence (probability theory) |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.522344708442688 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4646766781806946 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C198531522 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4325485825538635 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q485146 |
| concepts[6].display_name | Sample (material) |
| concepts[7].id | https://openalex.org/C33923547 |
| concepts[7].level | 0 |
| concepts[7].score | 0.09228459000587463 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[7].display_name | Mathematics |
| concepts[8].id | https://openalex.org/C104317684 |
| concepts[8].level | 2 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[8].display_name | Gene |
| concepts[9].id | https://openalex.org/C185592680 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[9].display_name | Chemistry |
| concepts[10].id | https://openalex.org/C43617362 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q170050 |
| concepts[10].display_name | Chromatography |
| concepts[11].id | https://openalex.org/C55493867 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[11].display_name | Biochemistry |
| concepts[12].id | https://openalex.org/C105795698 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[12].display_name | Statistics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7689067125320435 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/robustness |
| keywords[1].score | 0.6640939116477966 |
| keywords[1].display_name | Robustness (evolution) |
| keywords[2].id | https://openalex.org/keywords/inference |
| keywords[2].score | 0.5834274888038635 |
| keywords[2].display_name | Inference |
| keywords[3].id | https://openalex.org/keywords/independence |
| keywords[3].score | 0.5480034351348877 |
| keywords[3].display_name | Independence (probability theory) |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.522344708442688 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.4646766781806946 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/sample |
| keywords[6].score | 0.4325485825538635 |
| keywords[6].display_name | Sample (material) |
| keywords[7].id | https://openalex.org/keywords/mathematics |
| keywords[7].score | 0.09228459000587463 |
| keywords[7].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2202.03354 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2202.03354 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2202.03354 |
| locations[1].id | doi:10.48550/arxiv.2202.03354 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2202.03354 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5015873217 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9841-5025 |
| authorships[0].author.display_name | Michael Heck |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Heck, Michael |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5044076701 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4461-7243 |
| authorships[1].author.display_name | Nurul Lubis |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lubis, Nurul |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5023425411 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-4551-7447 |
| authorships[2].author.display_name | Carel van Niekerk |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | van Niekerk, Carel |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5031650617 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1307-4223 |
| authorships[3].author.display_name | Shutong Feng |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Feng, Shutong |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5057058723 |
| authorships[4].author.orcid | https://orcid.org/0009-0004-6369-3438 |
| authorships[4].author.display_name | Christian Geishauser |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Geishauser, Christian |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5103130759 |
| authorships[5].author.orcid | https://orcid.org/0009-0006-0027-226X |
| authorships[5].author.display_name | Hsien-chin Lin |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Lin, Hsien-Chin |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5051889115 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-0318-9147 |
| authorships[6].author.display_name | Milica Gašić |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Gašić, Milica |
| authorships[6].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2202.03354 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Robust Dialogue State Tracking with Weak Supervision and Sparse Data |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12031 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9950000047683716 |
| 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 | Speech and dialogue systems |
| related_works | https://openalex.org/W3125750421, https://openalex.org/W2055243143, https://openalex.org/W68147753, https://openalex.org/W2770593030, https://openalex.org/W2949765904, https://openalex.org/W4306949324, https://openalex.org/W3154990682, https://openalex.org/W4388544318, https://openalex.org/W618363683, https://openalex.org/W2560201613 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2202.03354 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| 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 | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2202.03354 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2202.03354 |
| primary_location.id | pmh:oai:arXiv.org:2202.03354 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2202.03354 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2202.03354 |
| publication_date | 2022-02-07 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 48, 78, 83, 157 |
| abstract_inverted_index.In | 43 |
| abstract_inverted_index.We | 76, 99, 161 |
| abstract_inverted_index.an | 127 |
| abstract_inverted_index.as | 89, 91 |
| abstract_inverted_index.be | 132 |
| abstract_inverted_index.by | 94 |
| abstract_inverted_index.is | 8 |
| abstract_inverted_index.of | 30, 73, 103, 120, 159 |
| abstract_inverted_index.on | 16, 156 |
| abstract_inverted_index.to | 5, 12, 37, 51, 111, 153, 167 |
| abstract_inverted_index.we | 46 |
| abstract_inverted_index.DST | 54, 107, 129 |
| abstract_inverted_index.Our | 123, 138 |
| abstract_inverted_index.Two | 64 |
| abstract_inverted_index.and | 18, 27, 33, 108, 140, 150 |
| abstract_inverted_index.can | 131 |
| abstract_inverted_index.due | 11 |
| abstract_inverted_index.for | 59 |
| abstract_inverted_index.new | 6, 31, 79, 148 |
| abstract_inverted_index.our | 164 |
| abstract_inverted_index.the | 13, 28, 57, 70, 96, 101, 118 |
| abstract_inverted_index.copy | 105 |
| abstract_inverted_index.data | 7 |
| abstract_inverted_index.from | 113, 170 |
| abstract_inverted_index.lead | 36 |
| abstract_inverted_index.need | 58 |
| abstract_inverted_index.slot | 92 |
| abstract_inverted_index.span | 62, 136 |
| abstract_inverted_index.that | 86, 126 |
| abstract_inverted_index.this | 44 |
| abstract_inverted_index.well | 90 |
| abstract_inverted_index.with | 82 |
| abstract_inverted_index.(DST) | 4 |
| abstract_inverted_index.build | 52 |
| abstract_inverted_index.data. | 172 |
| abstract_inverted_index.learn | 169 |
| abstract_inverted_index.model | 80, 130 |
| abstract_inverted_index.novel | 65 |
| abstract_inverted_index.paper | 45 |
| abstract_inverted_index.range | 158 |
| abstract_inverted_index.shift | 26 |
| abstract_inverted_index.state | 2 |
| abstract_inverted_index.value | 88, 109 |
| abstract_inverted_index.Sample | 23 |
| abstract_inverted_index.during | 21, 41 |
| abstract_inverted_index.impact | 72 |
| abstract_inverted_index.manual | 61, 135 |
| abstract_inverted_index.models | 55 |
| abstract_inverted_index.sample | 74, 146 |
| abstract_inverted_index.severe | 38 |
| abstract_inverted_index.strong | 14 |
| abstract_inverted_index.topics | 34 |
| abstract_inverted_index.triple | 104 |
| abstract_inverted_index.ability | 166 |
| abstract_inverted_index.benefit | 112 |
| abstract_inverted_index.combine | 100 |
| abstract_inverted_index.dropout | 67 |
| abstract_inverted_index.encoder | 85 |
| abstract_inverted_index.further | 162 |
| abstract_inverted_index.improve | 143 |
| abstract_inverted_index.labels. | 63, 137 |
| abstract_inverted_index.leading | 152 |
| abstract_inverted_index.methods | 68 |
| abstract_inverted_index.model's | 165 |
| abstract_inverted_index.propose | 47, 77 |
| abstract_inverted_index.topics, | 151 |
| abstract_inverted_index.towards | 145 |
| abstract_inverted_index.trained | 133 |
| abstract_inverted_index.unified | 84 |
| abstract_inverted_index.without | 56, 116, 134 |
| abstract_inverted_index.abundant | 17 |
| abstract_inverted_index.concepts | 32, 149 |
| abstract_inverted_index.dialogue | 1 |
| abstract_inverted_index.matching | 110 |
| abstract_inverted_index.mitigate | 69 |
| abstract_inverted_index.negative | 71 |
| abstract_inverted_index.ontology | 121 |
| abstract_inverted_index.reliance | 15 |
| abstract_inverted_index.strategy | 50, 106 |
| abstract_inverted_index.supports | 87 |
| abstract_inverted_index.tracking | 3 |
| abstract_inverted_index.training | 49, 141 |
| abstract_inverted_index.attention | 97 |
| abstract_inverted_index.highlight | 163 |
| abstract_inverted_index.principle | 119 |
| abstract_inverted_index.sparsity, | 24, 147 |
| abstract_inverted_index.sparsity. | 75 |
| abstract_inverted_index.strengths | 102 |
| abstract_inverted_index.training. | 22 |
| abstract_inverted_index.violating | 117 |
| abstract_inverted_index.especially | 9 |
| abstract_inverted_index.extractive | 53, 128 |
| abstract_inverted_index.frequently | 35 |
| abstract_inverted_index.inference. | 42 |
| abstract_inverted_index.leveraging | 95 |
| abstract_inverted_index.mechanism. | 98 |
| abstract_inverted_index.occurrence | 29 |
| abstract_inverted_index.robustness | 144 |
| abstract_inverted_index.strategies | 142 |
| abstract_inverted_index.benchmarks. | 160 |
| abstract_inverted_index.challenging | 10 |
| abstract_inverted_index.degradation | 40 |
| abstract_inverted_index.demonstrate | 125 |
| abstract_inverted_index.effectively | 168 |
| abstract_inverted_index.experiments | 124 |
| abstract_inverted_index.input-level | 66 |
| abstract_inverted_index.performance | 39, 155 |
| abstract_inverted_index.predictions | 115 |
| abstract_inverted_index.supervision | 20 |
| abstract_inverted_index.Generalising | 0 |
| abstract_inverted_index.architecture | 81, 139 |
| abstract_inverted_index.fine-grained | 19, 60 |
| abstract_inverted_index.independence | 93 |
| abstract_inverted_index.non-dialogue | 171 |
| abstract_inverted_index.complementary | 114 |
| abstract_inverted_index.independence. | 122 |
| abstract_inverted_index.distributional | 25 |
| abstract_inverted_index.state-of-the-art | 154 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |