{"id":"https://openalex.org/W3106295233","doi":"https://doi.org/10.18653/v1/2020.coling-main.411","title":"Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities","display_name":"Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3106295233","doi":"https://doi.org/10.18653/v1/2020.coling-main.411","mag":"3106295233"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.411","doi":"https://doi.org/10.18653/v1/2020.coling-main.411","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.411","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.411.pdf","source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/2020.coling-main.411.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075278288","display_name":"Jae Hun Ro","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jae Ro","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063612469","display_name":"Richard Sproat","orcid":"https://orcid.org/0000-0002-9040-5196","observed_orcids":["https://orcid.org/0000-0002-9040-5196"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Sproat","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.5723,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.706287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4667","last_page":"4675"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5360999703407288,"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":0.5360999703407288,"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":0.4377000033855438,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0032999999821186066,"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/semi-supervised-learning","display_name":"semi-supervised learning","score":0.859000027179718},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.8930000066757202},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.7269999980926514},{"id":"https://openalex.org/keywords/chinese-word-segmentation","display_name":"Chinese word segmentation","score":0.8579999804496765},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.6690000295639038},{"id":"https://openalex.org/keywords/web-search","display_name":"web search","score":0.9139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457801938056946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6307031512260437},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5752660036087036},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.574721097946167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5191171169281006},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49852728843688965},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4947337806224823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46781444549560547},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4410945773124695},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4287698566913605},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4251534640789032},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.41309744119644165},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41028156876564026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3537176847457886},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.08895090222358704},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.411","doi":"https://doi.org/10.18653/v1/2020.coling-main.411","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.411","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.411.pdf","source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.03138","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.03138","pdf_url":"https://arxiv.org/pdf/2011.03138","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2011.03138","doi":"https://doi.org/10.48550/arxiv.2011.03138","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.03138","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.411","doi":"https://doi.org/10.18653/v1/2020.coling-main.411","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.411","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.411.pdf","source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7300000190734863,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3106295233.pdf","grobid_xml":"https://content.openalex.org/works/W3106295233.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1767083593","https://openalex.org/W2036516910","https://openalex.org/W2094728533","https://openalex.org/W2095880437","https://openalex.org/W2103085228","https://openalex.org/W2126377586","https://openalex.org/W2158551114","https://openalex.org/W2163353449","https://openalex.org/W2164107060","https://openalex.org/W2165664509","https://openalex.org/W2508899723","https://openalex.org/W2608207374","https://openalex.org/W2610748790","https://openalex.org/W2625720409","https://openalex.org/W2890761057","https://openalex.org/W2896457183","https://openalex.org/W2901997113","https://openalex.org/W2922018002","https://openalex.org/W2962885853","https://openalex.org/W2963341956","https://openalex.org/W2963609956"],"related_works":["https://openalex.org/W3167168225","https://openalex.org/W2962875366","https://openalex.org/W4288953919","https://openalex.org/W3193461931","https://openalex.org/W7223308433","https://openalex.org/W2358538244","https://openalex.org/W7131882588","https://openalex.org/W2402385743","https://openalex.org/W7027429494","https://openalex.org/W2274880506"],"abstract_inverted_index":{"Breaking":[0],"domain":[1],"names":[2,66],"such":[3],"as":[4,49],"openresearch":[5],"into":[6],"component":[7],"words":[8],"open":[9],"and":[10,19,33,77],"research":[11],"is":[12],"important":[13],"for":[14,52],"applications":[15],"like":[16],"Text-to-Speech":[17],"synthesis":[18],"web":[20],"search.We":[21],"link":[22],"this":[23],"problem":[24,28],"to":[25,82],"the":[26,35,53,73,79],"classic":[27],"of":[29,37,55],"Chinese":[30],"word":[31],"segmentation":[32],"show":[34],"effectiveness":[36],"a":[38,60,68],"tagging":[39],"model":[40,74],"based":[41],"on":[42,63],"Recurrent":[43],"Neural":[44],"Networks":[45],"(RNNs)":[46],"using":[47],"characters":[48],"input.To":[50],"compensate":[51],"lack":[54],"training":[56],"data,":[57],"we":[58],"propose":[59],"pre-training":[61],"method":[62],"concatenated":[64],"entity":[65],"in":[67],"large":[69],"knowledge":[70],"database.Pre-training":[71],"improves":[72],"by":[75],"33%":[76],"brings":[78],"sequence":[80],"accuracy":[81],"85%.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2020-11-23T00:00:00"}