{"id":"https://openalex.org/W2250565861","doi":"https://doi.org/10.18653/v1/d13-1090","title":"Discriminative Improvements to Distributional Sentence Similarity","display_name":"Discriminative Improvements to Distributional Sentence Similarity","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2250565861","doi":"https://doi.org/10.18653/v1/d13-1090","mag":"2250565861"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1090","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1090","pdf_url":"https://aclanthology.org/D13-1090.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1090.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085302513","display_name":"Yangfeng Ji","orcid":"https://orcid.org/0000-0002-7793-486X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210152658","display_name":"Active Technologies (Italy)","ror":"https://ror.org/03zp7nb85","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210152658"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Yangfeng Ji","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology School of Interactive Computing Georgia Institute of Technology","#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology School of Interactive Computing Georgia Institute of Technology","institution_ids":["https://openalex.org/I4210152658"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210152658","display_name":"Active Technologies (Italy)","ror":"https://ror.org/03zp7nb85","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210152658"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology School of Interactive Computing Georgia Institute of Technology","#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology School of Interactive Computing Georgia Institute of Technology","institution_ids":["https://openalex.org/I4210152658"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":136,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"891","last_page":"896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8406388759613037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7276040315628052},{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.7252980470657349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7187237739562988},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5656354427337646},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5562046766281128},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5423896908760071},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.539576530456543},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.5144162774085999},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.49307820200920105},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45967960357666016},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4423758387565613},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42900392413139343},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4184091091156006}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8406388759613037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7276040315628052},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.7252980470657349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7187237739562988},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5656354427337646},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5562046766281128},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5423896908760071},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.539576530456543},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.5144162774085999},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.49307820200920105},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45967960357666016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4423758387565613},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42900392413139343},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4184091091156006},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/d13-1090","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1090","pdf_url":"https://aclanthology.org/D13-1090.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.3235","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.3235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/~jeisenst/papers/ji-emnlp-2013.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.75","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.75","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D13/D13-1090.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1090","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1090","pdf_url":"https://aclanthology.org/D13-1090.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250565861.pdf","grobid_xml":"https://content.openalex.org/works/W2250565861.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W97201605","https://openalex.org/W1493309689","https://openalex.org/W1503398984","https://openalex.org/W1566018662","https://openalex.org/W1662133657","https://openalex.org/W1980776243","https://openalex.org/W2013029404","https://openalex.org/W2016172157","https://openalex.org/W2099884836","https://openalex.org/W2103305545","https://openalex.org/W2118585731","https://openalex.org/W2128521126","https://openalex.org/W2132019450","https://openalex.org/W2135029798","https://openalex.org/W2135875128","https://openalex.org/W2139728183","https://openalex.org/W2140427797","https://openalex.org/W2158997610","https://openalex.org/W2165109647","https://openalex.org/W2250305120","https://openalex.org/W2251044566","https://openalex.org/W2624444395","https://openalex.org/W2964057329","https://openalex.org/W3143596294","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2028080169","https://openalex.org/W2111020819","https://openalex.org/W2588002110","https://openalex.org/W2033116442","https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138"],"abstract_inverted_index":{"Matrix":[0],"and":[1],"tensor":[2],"factorization":[3,67],"have":[4],"been":[5],"applied":[6],"to":[7],"a":[8,48,71],"number":[9],"of":[10,40],"semantic":[11,27],"relatedness":[12],"tasks,":[13],"including":[14],"paraphrase":[15,44],"identification.The":[16],"key":[17],"idea":[18],"is":[19,89],"that":[20,60,88],"similarity":[21],"in":[22,32,70],"the":[23,38,62,94],"latent":[24,63,79],"space":[25],"implies":[26],"relatedness.We":[28],"describe":[29],"three":[30],"ways":[31],"which":[33,55],"labeled":[34],"data":[35],"can":[36],"improve":[37],"accuracy":[39],"these":[41],"approaches":[42],"on":[43],"classification.First,":[45],"we":[46,58,77],"design":[47],"new":[49],"discriminative":[50],"term-weighting":[51],"metric":[52],"called":[53],"TF-KLD,":[54],"outperforms":[56],"TF-IDF.Next,":[57],"show":[59],"using":[61],"representation":[64],"from":[65],"matrix":[66],"as":[68],"features":[69,80],"classification":[72],"algorithm":[73],"substantially":[74],"improves":[75],"accuracy.Finally,":[76],"combine":[78],"with":[81],"fine-grained":[82],"n-gram":[83],"overlap":[84],"features,":[85],"yielding":[86],"performance":[87],"3%":[90],"more":[91],"accurate":[92],"than":[93],"prior":[95],"state-of-the-art.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}