{"id":"https://openalex.org/W2964093505","doi":"https://doi.org/10.18653/v1/p17-1078","title":"Neural Word Segmentation with Rich Pretraining","display_name":"Neural Word Segmentation with Rich Pretraining","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2964093505","doi":"https://doi.org/10.18653/v1/p17-1078","mag":"2964093505"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-1078","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1078","pdf_url":"https://www.aclweb.org/anthology/P17-1078.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-1078.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078108605","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0001-5696-363X"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jie Yang","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333738","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-6327-5023"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084527490","display_name":"Fei Dong","orcid":"https://orcid.org/0000-0002-1154-1350"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fei Dong","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084527490"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":16.8367,"has_fulltext":true,"cited_by_count":126,"citation_normalized_percentile":{"value":0.99274165,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/segmentation","display_name":"Segmentation","score":0.8345897197723389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7384234070777893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6470273733139038},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.630359411239624},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6166975498199463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5213952660560608},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5193799138069153},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4760850965976715},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4653298258781433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4391745924949646},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.4291008710861206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4237959086894989},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42117002606391907},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10837891697883606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08911940455436707}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8345897197723389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384234070777893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6470273733139038},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.630359411239624},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6166975498199463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5213952660560608},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5193799138069153},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4760850965976715},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4653298258781433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4391745924949646},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4291008710861206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4237959086894989},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42117002606391907},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10837891697883606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08911940455436707},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-1078","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1078","pdf_url":"https://www.aclweb.org/anthology/P17-1078.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-1078","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1078","pdf_url":"https://www.aclweb.org/anthology/P17-1078.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7651818231","display_name":null,"funder_award_id":"61572245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964093505.pdf","grobid_xml":"https://content.openalex.org/works/W2964093505.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W25062297","https://openalex.org/W1512811194","https://openalex.org/W1558333962","https://openalex.org/W1575907248","https://openalex.org/W1806891645","https://openalex.org/W2010576059","https://openalex.org/W2035304092","https://openalex.org/W2036516910","https://openalex.org/W2095705004","https://openalex.org/W2096204319","https://openalex.org/W2100649405","https://openalex.org/W2104917081","https://openalex.org/W2105908356","https://openalex.org/W2107419438","https://openalex.org/W2116983617","https://openalex.org/W2120661206","https://openalex.org/W2126504272","https://openalex.org/W2131417696","https://openalex.org/W2143026224","https://openalex.org/W2145905222","https://openalex.org/W2146502635","https://openalex.org/W2158899491","https://openalex.org/W2160097208","https://openalex.org/W2163377725","https://openalex.org/W2165664509","https://openalex.org/W2172221237","https://openalex.org/W2233994034","https://openalex.org/W2250451826","https://openalex.org/W2250623963","https://openalex.org/W2250675174","https://openalex.org/W2250739653","https://openalex.org/W2251362855","https://openalex.org/W2251627854","https://openalex.org/W2251736053","https://openalex.org/W2251811146","https://openalex.org/W2252225757","https://openalex.org/W2467575451","https://openalex.org/W2502289490","https://openalex.org/W2507296208","https://openalex.org/W2516334389","https://openalex.org/W2557387915","https://openalex.org/W2572408711","https://openalex.org/W2952230511","https://openalex.org/W2963572611","https://openalex.org/W2963620441","https://openalex.org/W2963628345","https://openalex.org/W3145501851","https://openalex.org/W4241108585","https://openalex.org/W4296130438"],"related_works":["https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2385598138","https://openalex.org/W2366925922","https://openalex.org/W2346578824","https://openalex.org/W2905950556","https://openalex.org/W2112534334","https://openalex.org/W2115592387","https://openalex.org/W120168696","https://openalex.org/W2153245103"],"abstract_inverted_index":{"Neural":[0],"word":[1,17,53],"segmentation":[2,24,37,54,59],"research":[3,25],"has":[4,26],"benefited":[5],"from":[6],"large-scale":[7],"raw":[8],"texts":[9],"by":[10,55],"leveraging":[11],"them":[12],"for":[13,51],"pretraining":[14,61,74],"character":[15],"and":[16,38],"embeddings.":[18],"On":[19],"the":[20,42,62,77,84],"other":[21],"hand,":[22],"statistical":[23],"exploited":[27],"richer":[28],"sources":[29,50],"of":[30,44,47],"external":[31,48,68],"information,":[32],"such":[33,73],"as":[34],"punctuation,":[35],"automatic":[36],"POS.":[39],"We":[40],"investigate":[41],"effectiveness":[43],"a":[45,57],"range":[46],"training":[49],"neural":[52],"building":[56],"modular":[58],"model,":[60,78],"most":[63],"important":[64],"submodule":[65],"using":[66],"rich":[67],"sources.":[69],"Results":[70],"show":[71],"that":[72],"significantly":[75],"improves":[76],"leading":[79],"to":[80,83],"accuracies":[81],"competitive":[82],"best":[85],"methods":[86],"on":[87],"six":[88],"benchmarks.":[89],"*":[90],"Equal":[91],"contribution.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}