{"id":"https://openalex.org/W2134511576","doi":"https://doi.org/10.3115/1034678.1034686","title":"Cohesion and collocation","display_name":"Cohesion and collocation","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2134511576","doi":"https://doi.org/10.3115/1034678.1034686","mag":"2134511576"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034686","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034686","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034686","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034686","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078255655","display_name":"Stefan Kaufmann","orcid":"https://orcid.org/0000-0002-3280-0884"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stefan Kaufmann","raw_affiliation_strings":["CSLI, Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"CSLI, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078255655"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":4.078,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.93975543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"591","last_page":"595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9972000122070312,"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/cohesion","display_name":"Cohesion (chemistry)","score":0.8732872605323792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7378038167953491},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6696452498435974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6237500309944153},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.5744996666908264},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5730924010276794},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5510542392730713},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4968283474445343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48468735814094543},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4352720081806183},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4145331084728241},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2359248697757721},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16526654362678528},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1433427929878235},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08210158348083496}],"concepts":[{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.8732872605323792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378038167953491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6696452498435974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237500309944153},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.5744996666908264},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5730924010276794},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5510542392730713},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4968283474445343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48468735814094543},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4352720081806183},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4145331084728241},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2359248697757721},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16526654362678528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1433427929878235},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08210158348083496},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1034678.1034686","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034686","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034686","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1034678.1034686","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034686","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034686","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2134511576.pdf","grobid_xml":"https://content.openalex.org/works/W2134511576.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1489616935","https://openalex.org/W1495373554","https://openalex.org/W1499182410","https://openalex.org/W1552626377","https://openalex.org/W1593106025","https://openalex.org/W1604285433","https://openalex.org/W1710422233","https://openalex.org/W1828401780","https://openalex.org/W1969787028","https://openalex.org/W1986307766","https://openalex.org/W2004810878","https://openalex.org/W2005313804","https://openalex.org/W2010523086","https://openalex.org/W2015933299","https://openalex.org/W2049492419","https://openalex.org/W2107402508","https://openalex.org/W2130337399","https://openalex.org/W2167702024","https://openalex.org/W2296009152","https://openalex.org/W2333893391","https://openalex.org/W2798909945","https://openalex.org/W3100435646"],"related_works":["https://openalex.org/W2362350383","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2115592387","https://openalex.org/W2905950556","https://openalex.org/W2112534334","https://openalex.org/W120168696"],"abstract_inverted_index":{"Collocational":[0],"word":[1,32],"similarity":[2,33,49],"is":[3,11,68],"considered":[4],"a":[5,27],"source":[6],"of":[7,24,57,61,65,74],"text":[8,40],"cohesion":[9],"that":[10,73],"hard":[12],"to":[13,70],"measure":[14],"and":[15,34],"quantify.":[16],"The":[17,63],"work":[18],"presented":[19],"here":[20],"explores":[21],"the":[22,36,39,45,58,75],"use":[23],"information":[25],"from":[26],"training":[28],"corpus":[29],"in":[30,38],"measuring":[31],"evaluates":[35],"method":[37],"segmentation":[41],"task.":[42],"An":[43],"implementation,":[44],"<b>VecTile</b>":[46],"system,":[47],"produces":[48],"curves":[50],"over":[51,72],"texts":[52],"using":[53],"pre-compiled":[54],"vector":[55],"representations":[56],"contextual":[59],"behavior":[60],"words.":[62],"performance":[64],"this":[66],"system":[67],"shown":[69],"improve":[71],"purely":[76],"string-based":[77],"<b>TextTiling":[78],"algorithm</b>":[79],"(Hearst,":[80],"1997).":[81]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}