{"id":"https://openalex.org/W2250553586","doi":"https://doi.org/10.3115/v1/p14-1014","title":"Tagging The Web: Building A Robust Web Tagger with Neural Network","display_name":"Tagging The Web: Building A Robust Web Tagger with Neural Network","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250553586","doi":"https://doi.org/10.3115/v1/p14-1014","mag":"2250553586"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-1014","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-1014","pdf_url":"https://doi.org/10.3115/v1/p14-1014","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for 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://doi.org/10.3115/v1/p14-1014","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046993861","display_name":"Ji Ma","orcid":"https://orcid.org/0000-0002-0912-2632"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ji Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328212","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0003-4012-537X"},"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/A5100370155","display_name":"Jingbo Zhu","orcid":"https://orcid.org/0000-0002-6537-7007"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046993861"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7522,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96860159,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.8843073844909668},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.685429036617279},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6339740753173828},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6294107437133789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6098992824554443},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5856180191040039},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5429013967514038},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5338457822799683},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47190481424331665},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.46749556064605713},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42975419759750366},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13502264022827148},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0842847228050232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8843073844909668},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.685429036617279},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6339740753173828},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6294107437133789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098992824554443},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5856180191040039},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5429013967514038},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5338457822799683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47190481424331665},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.46749556064605713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42975419759750366},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13502264022827148},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0842847228050232},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/p14-1014","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-1014","pdf_url":"https://doi.org/10.3115/v1/p14-1014","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.635.4424","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.635.4424","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/P/P14/P14-1014.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-1014","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-1014","pdf_url":"https://doi.org/10.3115/v1/p14-1014","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250553586.pdf","grobid_xml":"https://content.openalex.org/works/W2250553586.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W22861983","https://openalex.org/W108437174","https://openalex.org/W129942754","https://openalex.org/W1498436455","https://openalex.org/W1500431650","https://openalex.org/W1572401739","https://openalex.org/W1595917421","https://openalex.org/W1660460062","https://openalex.org/W1773803948","https://openalex.org/W1966026565","https://openalex.org/W2008652694","https://openalex.org/W2072128103","https://openalex.org/W2105103433","https://openalex.org/W2107789863","https://openalex.org/W2110798204","https://openalex.org/W2111362445","https://openalex.org/W2116064496","https://openalex.org/W2118535827","https://openalex.org/W2123925574","https://openalex.org/W2130325614","https://openalex.org/W2136922672","https://openalex.org/W2139621418","https://openalex.org/W2141443306","https://openalex.org/W2155169782","https://openalex.org/W2158108973","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2170986599","https://openalex.org/W2172174689","https://openalex.org/W2172251087","https://openalex.org/W2250516627","https://openalex.org/W2251395256","https://openalex.org/W2251811146","https://openalex.org/W2950500591"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W2083429127","https://openalex.org/W2358855848","https://openalex.org/W2142145894","https://openalex.org/W2033808215","https://openalex.org/W2359307945","https://openalex.org/W4388176285"],"abstract_inverted_index":{"In":[0],"this":[1,86],"paper,":[2],"we":[3],"address":[4],"the":[5,48,57,62,79],"problem":[6],"of":[7,47],"web-domain":[8],"POS":[9,44],"tagging":[10,75],"using":[11,53],"a":[12,33,39],"two-phase":[13],"approach.":[14],"The":[15,26],"first":[16],"phase":[17],"learns":[18],"rep-resentations":[19],"that":[20,36,68],"capture":[21],"regularities":[22],"un-derlying":[23],"web":[24],"text.":[25],"representation":[27],"is":[28,78],"integrated":[29],"as":[30,38],"features":[31],"into":[32],"neural":[34,49],"network":[35,50],"serves":[37],"scorer":[40],"for":[41],"an":[42],"easy-first":[43],"tagger.":[45],"Parameters":[46],"are":[51],"trained":[52],"guided":[54],"learning":[55],"in":[56],"second":[58],"phase.":[59],"Experiment":[60],"on":[61,85],"SANCL":[63],"2012":[64],"shared":[65],"task":[66],"show":[67],"our":[69],"approach":[70],"achieves":[71],"93.15":[72],"%":[73],"average":[74],"accu-racy,":[76],"which":[77],"best":[80],"accuracy":[81],"reported":[82],"so":[83],"far":[84],"data":[87],"set,":[88],"higher":[89],"than":[90],"those":[91],"given":[92],"by":[93],"ensembled":[94],"syntactic":[95],"parsers.":[96],"1":[97]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}