Scalable Attentive Sentence Pair Modeling via Distilled Sentence Embedding Article Swipe
Oren Barkan
,
Noam Razin
,
Itzik Malkiel
,
Ori Katz
,
Avi Caciularu
,
Noam Koenigstein
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v34i04.5722
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v34i04.5722
Recent state-of-the-art natural language understanding models, such as BERT and XLNet, score a pair of sentences (A and B) using multiple cross-attention operations – a process in which each word in sentence A attends to all words in sentence B and vice versa. As a result, computing the similarity between a query sentence and a set of candidate sentences, requires the propagation of all query-candidate sentence-pairs throughout a stack of cross-attention layers. This exhaustive process becomes computationally prohibitive when the number of candidate sentences is large. In contrast, sentence embedding techniques learn a sentence-to-vector mapping and compute the similarity between the sentence vectors via simple elementary operations. In this paper, we introduce Distilled Sentence Embedding (DSE) – a model that is based on knowledge distillation from cross-attentive models, focusing on sentence-pair tasks. The outline of DSE is as follows: Given a cross-attentive teacher model (e.g. a fine-tuned BERT), we train a sentence embedding based student model to reconstruct the sentence-pair scores obtained by the teacher model. We empirically demonstrate the effectiveness of DSE on five GLUE sentence-pair tasks. DSE significantly outperforms several ELMO variants and other sentence embedding methods, while accelerating computation of the query-candidate sentence-pairs similarities by several orders of magnitude, with an average relative degradation of 4.6% compared to BERT. Furthermore, we show that DSE produces sentence embeddings that reach state-of-the-art performance on universal sentence representation benchmarks. Our code is made publicly available at https://github.com/microsoft/Distilled-Sentence-Embedding.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v34i04.5722
- https://ojs.aaai.org/index.php/AAAI/article/download/5722/5578
- OA Status
- diamond
- Cited By
- 2
- References
- 39
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W2967472393
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2967472393Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v34i04.5722Digital Object Identifier
- Title
-
Scalable Attentive Sentence Pair Modeling via Distilled Sentence EmbeddingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-04-03Full publication date if available
- Authors
-
Oren Barkan, Noam Razin, Itzik Malkiel, Ori Katz, Avi Caciularu, Noam KoenigsteinList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v34i04.5722Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/5722/5578Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/5722/5578Direct OA link when available
- Concepts
-
Sentence, Computer science, Natural language processing, Embedding, Artificial intelligenceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 1, 2020: 1Per-year citation counts (last 5 years)
- References (count)
-
39Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2967472393 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v34i04.5722 |
| ids.doi | https://doi.org/10.1609/aaai.v34i04.5722 |
| ids.mag | 2967472393 |
| ids.openalex | https://openalex.org/W2967472393 |
| fwci | 0.22037795 |
| type | preprint |
| title | Scalable Attentive Sentence Pair Modeling via Distilled Sentence Embedding |
| biblio.issue | 04 |
| biblio.volume | 34 |
| biblio.last_page | 3242 |
| biblio.first_page | 3235 |
| 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 | 0.9998999834060669 |
| 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/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9994999766349792 |
| 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 | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T13629 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9876000285148621 |
| 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 | Text Readability and Simplification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2777530160 |
| concepts[0].level | 2 |
| concepts[0].score | 0.883657693862915 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q41796 |
| concepts[0].display_name | Sentence |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7156749963760376 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C204321447 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6287834644317627 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[2].display_name | Natural language processing |
| concepts[3].id | https://openalex.org/C41608201 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6113581657409668 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q980509 |
| concepts[3].display_name | Embedding |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5713156461715698 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| keywords[0].id | https://openalex.org/keywords/sentence |
| keywords[0].score | 0.883657693862915 |
| keywords[0].display_name | Sentence |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7156749963760376 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/natural-language-processing |
| keywords[2].score | 0.6287834644317627 |
| keywords[2].display_name | Natural language processing |
| keywords[3].id | https://openalex.org/keywords/embedding |
| keywords[3].score | 0.6113581657409668 |
| keywords[3].display_name | Embedding |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.5713156461715698 |
| keywords[4].display_name | Artificial intelligence |
| language | en |
| locations[0].id | doi:10.1609/aaai.v34i04.5722 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/5722/5578 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v34i04.5722 |
| locations[1].id | pmh:oai:arXiv.org:1908.05161 |
| 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 | https://arxiv.org/pdf/1908.05161 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/1908.05161 |
| locations[2].id | doi:10.48550/arxiv.1908.05161 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.48550/arxiv.1908.05161 |
| locations[3].id | mag:2967472393 |
| locations[3].is_oa | False |
| locations[3].source | |
| locations[3].license | |
| locations[3].pdf_url | |
| locations[3].version | |
| locations[3].raw_type | |
| locations[3].license_id | |
| locations[3].is_accepted | False |
| locations[3].is_published | |
| locations[3].raw_source_name | |
| locations[3].landing_page_url | |
| indexed_in | arxiv, crossref, datacite |
| authorships[0].author.id | https://openalex.org/A5077269072 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5059-0905 |
| authorships[0].author.display_name | Oren Barkan |
| authorships[0].countries | GB |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I4210164937 |
| authorships[0].affiliations[0].raw_affiliation_string | (Microsoft) |
| authorships[0].institutions[0].id | https://openalex.org/I4210164937 |
| authorships[0].institutions[0].ror | https://ror.org/05k87vq12 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I1290206253, https://openalex.org/I4210164937 |
| authorships[0].institutions[0].country_code | GB |
| authorships[0].institutions[0].display_name | Microsoft Research (United Kingdom) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Oren Barkan |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | (Microsoft) |
| authorships[1].author.id | https://openalex.org/A5030945372 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Noam Razin |
| authorships[1].countries | IL |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I16391192 |
| authorships[1].affiliations[0].raw_affiliation_string | Tel Aviv University * |
| authorships[1].institutions[0].id | https://openalex.org/I16391192 |
| authorships[1].institutions[0].ror | https://ror.org/04mhzgx49 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I16391192 |
| authorships[1].institutions[0].country_code | IL |
| authorships[1].institutions[0].display_name | Tel Aviv University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Noam Razin |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Tel Aviv University * |
| authorships[2].author.id | https://openalex.org/A5067773841 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4151-9119 |
| authorships[2].author.display_name | Itzik Malkiel |
| authorships[2].countries | IL |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I16391192 |
| authorships[2].affiliations[0].raw_affiliation_string | Tel Aviv University * |
| authorships[2].institutions[0].id | https://openalex.org/I16391192 |
| authorships[2].institutions[0].ror | https://ror.org/04mhzgx49 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I16391192 |
| authorships[2].institutions[0].country_code | IL |
| authorships[2].institutions[0].display_name | Tel Aviv University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Itzik Malkiel |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Tel Aviv University * |
| authorships[3].author.id | https://openalex.org/A5106732003 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7390-2406 |
| authorships[3].author.display_name | Ori Katz |
| authorships[3].countries | IL |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I174306211 |
| authorships[3].affiliations[0].raw_affiliation_string | Technion |
| authorships[3].institutions[0].id | https://openalex.org/I174306211 |
| authorships[3].institutions[0].ror | https://ror.org/03qryx823 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I174306211 |
| authorships[3].institutions[0].country_code | IL |
| authorships[3].institutions[0].display_name | Technion – Israel Institute of Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Ori Katz |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Technion |
| authorships[4].author.id | https://openalex.org/A5077903013 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0573-1075 |
| authorships[4].author.display_name | Avi Caciularu |
| authorships[4].countries | IL |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I13955877 |
| authorships[4].affiliations[0].raw_affiliation_string | Bar-Ilan University |
| authorships[4].institutions[0].id | https://openalex.org/I13955877 |
| authorships[4].institutions[0].ror | https://ror.org/03kgsv495 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I13955877 |
| authorships[4].institutions[0].country_code | IL |
| authorships[4].institutions[0].display_name | Bar-Ilan University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Avi Caciularu |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Bar-Ilan University |
| authorships[5].author.id | https://openalex.org/A5083002103 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-8219-4512 |
| authorships[5].author.display_name | Noam Koenigstein |
| authorships[5].countries | IL |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I16391192 |
| authorships[5].affiliations[0].raw_affiliation_string | Tel Aviv University * |
| authorships[5].institutions[0].id | https://openalex.org/I16391192 |
| authorships[5].institutions[0].ror | https://ror.org/04mhzgx49 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I16391192 |
| authorships[5].institutions[0].country_code | IL |
| authorships[5].institutions[0].display_name | Tel Aviv University |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Noam Koenigstein |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Tel Aviv University * |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ojs.aaai.org/index.php/AAAI/article/download/5722/5578 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Scalable Attentive Sentence Pair Modeling via Distilled Sentence Embedding |
| 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 | 0.9998999834060669 |
| 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/W2997051142, https://openalex.org/W3202009528, https://openalex.org/W3152569586, https://openalex.org/W3134942116, https://openalex.org/W3213956755, https://openalex.org/W3021534166, https://openalex.org/W2889830342, https://openalex.org/W3121954283, https://openalex.org/W3126835783, https://openalex.org/W2760753016, https://openalex.org/W2786028997, https://openalex.org/W2890032154, https://openalex.org/W1968228387, https://openalex.org/W2584932577, https://openalex.org/W10934236, https://openalex.org/W2415204069, https://openalex.org/W2575298912, https://openalex.org/W2740932779, https://openalex.org/W3006690199, https://openalex.org/W3102335248 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2020 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 4 |
| best_oa_location.id | doi:10.1609/aaai.v34i04.5722 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/5722/5578 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v34i04.5722 |
| primary_location.id | doi:10.1609/aaai.v34i04.5722 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/5722/5578 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v34i04.5722 |
| publication_date | 2020-04-03 |
| publication_year | 2020 |
| referenced_works | https://openalex.org/W6698213403, https://openalex.org/W2298765043, https://openalex.org/W1840435438, https://openalex.org/W6683738474, https://openalex.org/W2612953412, https://openalex.org/W2790235966, https://openalex.org/W6685158001, https://openalex.org/W2896457183, https://openalex.org/W131533222, https://openalex.org/W6638523607, https://openalex.org/W6631190155, https://openalex.org/W6629028937, https://openalex.org/W2153579005, https://openalex.org/W2131462252, https://openalex.org/W6748634344, https://openalex.org/W6718053083, https://openalex.org/W2786685006, https://openalex.org/W2950813464, https://openalex.org/W2170973209, https://openalex.org/W2963310665, https://openalex.org/W2158899491, https://openalex.org/W2962739339, https://openalex.org/W2963846996, https://openalex.org/W2963918774, https://openalex.org/W2251939518, https://openalex.org/W2963403868, https://openalex.org/W2964106018, https://openalex.org/W2964165804, https://openalex.org/W3104033643, https://openalex.org/W2963748441, https://openalex.org/W2964341035, https://openalex.org/W2761988601, https://openalex.org/W2963090765, https://openalex.org/W1821462560, https://openalex.org/W2937297214, https://openalex.org/W2963854351, https://openalex.org/W2963341956, https://openalex.org/W1486649854, https://openalex.org/W2964121744 |
| referenced_works_count | 39 |
| abstract_inverted_index.A | 32 |
| abstract_inverted_index.B | 39 |
| abstract_inverted_index.a | 12, 24, 44, 50, 54, 67, 92, 117, 140, 145, 150 |
| abstract_inverted_index.(A | 16 |
| abstract_inverted_index.As | 43 |
| abstract_inverted_index.B) | 18 |
| abstract_inverted_index.In | 86, 107 |
| abstract_inverted_index.We | 166 |
| abstract_inverted_index.an | 203 |
| abstract_inverted_index.as | 7, 137 |
| abstract_inverted_index.at | 235 |
| abstract_inverted_index.by | 162, 197 |
| abstract_inverted_index.in | 26, 30, 37 |
| abstract_inverted_index.is | 84, 120, 136, 231 |
| abstract_inverted_index.of | 14, 56, 62, 69, 81, 134, 171, 192, 200, 207 |
| abstract_inverted_index.on | 122, 129, 173, 224 |
| abstract_inverted_index.to | 34, 156, 210 |
| abstract_inverted_index.we | 110, 148, 213 |
| abstract_inverted_index.DSE | 135, 172, 178, 216 |
| abstract_inverted_index.Our | 229 |
| abstract_inverted_index.The | 132 |
| abstract_inverted_index.all | 35, 63 |
| abstract_inverted_index.and | 9, 17, 40, 53, 95, 184 |
| abstract_inverted_index.set | 55 |
| abstract_inverted_index.the | 47, 60, 79, 97, 100, 158, 163, 169, 193 |
| abstract_inverted_index.via | 103 |
| abstract_inverted_index.– | 23, 116 |
| abstract_inverted_index.4.6% | 208 |
| abstract_inverted_index.BERT | 8 |
| abstract_inverted_index.ELMO | 182 |
| abstract_inverted_index.GLUE | 175 |
| abstract_inverted_index.This | 72 |
| abstract_inverted_index.code | 230 |
| abstract_inverted_index.each | 28 |
| abstract_inverted_index.five | 174 |
| abstract_inverted_index.from | 125 |
| abstract_inverted_index.made | 232 |
| abstract_inverted_index.pair | 13 |
| abstract_inverted_index.show | 214 |
| abstract_inverted_index.such | 6 |
| abstract_inverted_index.that | 119, 215, 220 |
| abstract_inverted_index.this | 108 |
| abstract_inverted_index.vice | 41 |
| abstract_inverted_index.when | 78 |
| abstract_inverted_index.with | 202 |
| abstract_inverted_index.word | 29 |
| abstract_inverted_index.(DSE) | 115 |
| abstract_inverted_index.(e.g. | 144 |
| abstract_inverted_index.BERT. | 211 |
| abstract_inverted_index.Given | 139 |
| abstract_inverted_index.based | 121, 153 |
| abstract_inverted_index.learn | 91 |
| abstract_inverted_index.model | 118, 143, 155 |
| abstract_inverted_index.other | 185 |
| abstract_inverted_index.query | 51 |
| abstract_inverted_index.reach | 221 |
| abstract_inverted_index.score | 11 |
| abstract_inverted_index.stack | 68 |
| abstract_inverted_index.train | 149 |
| abstract_inverted_index.using | 19 |
| abstract_inverted_index.which | 27 |
| abstract_inverted_index.while | 189 |
| abstract_inverted_index.words | 36 |
| abstract_inverted_index.BERT), | 147 |
| abstract_inverted_index.Recent | 0 |
| abstract_inverted_index.XLNet, | 10 |
| abstract_inverted_index.large. | 85 |
| abstract_inverted_index.model. | 165 |
| abstract_inverted_index.number | 80 |
| abstract_inverted_index.orders | 199 |
| abstract_inverted_index.paper, | 109 |
| abstract_inverted_index.scores | 160 |
| abstract_inverted_index.simple | 104 |
| abstract_inverted_index.tasks. | 131, 177 |
| abstract_inverted_index.versa. | 42 |
| abstract_inverted_index.attends | 33 |
| abstract_inverted_index.average | 204 |
| abstract_inverted_index.becomes | 75 |
| abstract_inverted_index.between | 49, 99 |
| abstract_inverted_index.compute | 96 |
| abstract_inverted_index.layers. | 71 |
| abstract_inverted_index.mapping | 94 |
| abstract_inverted_index.models, | 5, 127 |
| abstract_inverted_index.natural | 2 |
| abstract_inverted_index.outline | 133 |
| abstract_inverted_index.process | 25, 74 |
| abstract_inverted_index.result, | 45 |
| abstract_inverted_index.several | 181, 198 |
| abstract_inverted_index.student | 154 |
| abstract_inverted_index.teacher | 142, 164 |
| abstract_inverted_index.vectors | 102 |
| abstract_inverted_index.Sentence | 113 |
| abstract_inverted_index.compared | 209 |
| abstract_inverted_index.focusing | 128 |
| abstract_inverted_index.follows: | 138 |
| abstract_inverted_index.language | 3 |
| abstract_inverted_index.methods, | 188 |
| abstract_inverted_index.multiple | 20 |
| abstract_inverted_index.obtained | 161 |
| abstract_inverted_index.produces | 217 |
| abstract_inverted_index.publicly | 233 |
| abstract_inverted_index.relative | 205 |
| abstract_inverted_index.requires | 59 |
| abstract_inverted_index.sentence | 31, 38, 52, 88, 101, 151, 186, 218, 226 |
| abstract_inverted_index.variants | 183 |
| abstract_inverted_index.Distilled | 112 |
| abstract_inverted_index.Embedding | 114 |
| abstract_inverted_index.available | 234 |
| abstract_inverted_index.candidate | 57, 82 |
| abstract_inverted_index.computing | 46 |
| abstract_inverted_index.contrast, | 87 |
| abstract_inverted_index.embedding | 89, 152, 187 |
| abstract_inverted_index.introduce | 111 |
| abstract_inverted_index.knowledge | 123 |
| abstract_inverted_index.sentences | 15, 83 |
| abstract_inverted_index.universal | 225 |
| abstract_inverted_index.elementary | 105 |
| abstract_inverted_index.embeddings | 219 |
| abstract_inverted_index.exhaustive | 73 |
| abstract_inverted_index.fine-tuned | 146 |
| abstract_inverted_index.magnitude, | 201 |
| abstract_inverted_index.operations | 22 |
| abstract_inverted_index.sentences, | 58 |
| abstract_inverted_index.similarity | 48, 98 |
| abstract_inverted_index.techniques | 90 |
| abstract_inverted_index.throughout | 66 |
| abstract_inverted_index.benchmarks. | 228 |
| abstract_inverted_index.computation | 191 |
| abstract_inverted_index.degradation | 206 |
| abstract_inverted_index.demonstrate | 168 |
| abstract_inverted_index.empirically | 167 |
| abstract_inverted_index.operations. | 106 |
| abstract_inverted_index.outperforms | 180 |
| abstract_inverted_index.performance | 223 |
| abstract_inverted_index.prohibitive | 77 |
| abstract_inverted_index.propagation | 61 |
| abstract_inverted_index.reconstruct | 157 |
| abstract_inverted_index.Furthermore, | 212 |
| abstract_inverted_index.accelerating | 190 |
| abstract_inverted_index.distillation | 124 |
| abstract_inverted_index.similarities | 196 |
| abstract_inverted_index.effectiveness | 170 |
| abstract_inverted_index.sentence-pair | 130, 159, 176 |
| abstract_inverted_index.significantly | 179 |
| abstract_inverted_index.understanding | 4 |
| abstract_inverted_index.representation | 227 |
| abstract_inverted_index.sentence-pairs | 65, 195 |
| abstract_inverted_index.computationally | 76 |
| abstract_inverted_index.cross-attention | 21, 70 |
| abstract_inverted_index.cross-attentive | 126, 141 |
| abstract_inverted_index.query-candidate | 64, 194 |
| abstract_inverted_index.state-of-the-art | 1, 222 |
| abstract_inverted_index.sentence-to-vector | 93 |
| abstract_inverted_index.https://github.com/microsoft/Distilled-Sentence-Embedding. | 236 |
| cited_by_percentile_year.max | 94 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 6 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.5099999904632568 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile.value | 0.47374702 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |