{"id":"https://openalex.org/W2794370141","doi":"https://doi.org/10.1145/3162957.3162973","title":"From character to document representation with global context awareness","display_name":"From character to document representation with global context awareness","publication_year":2017,"publication_date":"2017-11-24","ids":{"openalex":"https://openalex.org/W2794370141","doi":"https://doi.org/10.1145/3162957.3162973","mag":"2794370141"},"language":"en","primary_location":{"id":"doi:10.1145/3162957.3162973","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3162957.3162973","pdf_url":null,"source":{"id":"https://openalex.org/S4306523808","display_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100611600","display_name":"Zhenhua Wu","orcid":"https://orcid.org/0000-0003-4552-883X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenzhou Wu","raw_affiliation_strings":["SAP Research and Innovation Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Research and Innovation Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021246","display_name":"Xin Zheng","orcid":"https://orcid.org/0000-0001-7310-5397"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xin Zheng","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002373633","display_name":"Daniel Dahlmeier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Dahlmeier","raw_affiliation_strings":["SAP Research and Innovation Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Research and Innovation Singapore, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20478957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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":0.8259235620498657},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7013883590698242},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6801388263702393},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6225653290748596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6214870810508728},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5712897181510925},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.560656726360321},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5303528904914856},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5225455164909363},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5168776512145996},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48967674374580383},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.459489643573761},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.42866918444633484},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4161277711391449},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19931241869926453},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0786251425743103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259235620498657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7013883590698242},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6801388263702393},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6225653290748596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6214870810508728},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5712897181510925},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.560656726360321},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5303528904914856},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5225455164909363},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5168776512145996},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48967674374580383},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.459489643573761},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.42866918444633484},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4161277711391449},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19931241869926453},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0786251425743103},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3162957.3162973","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3162957.3162973","pdf_url":null,"source":{"id":"https://openalex.org/S4306523808","display_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1583837637","https://openalex.org/W1665214252","https://openalex.org/W1832693441","https://openalex.org/W1903029394","https://openalex.org/W1938755728","https://openalex.org/W2005708641","https://openalex.org/W2090042335","https://openalex.org/W2101609803","https://openalex.org/W2118463056","https://openalex.org/W2143612262","https://openalex.org/W2149684865","https://openalex.org/W2158899491","https://openalex.org/W2163605009","https://openalex.org/W2170240176","https://openalex.org/W2201092681","https://openalex.org/W2250966211","https://openalex.org/W2252215182","https://openalex.org/W2397291310","https://openalex.org/W2470673105","https://openalex.org/W2535737795","https://openalex.org/W2560674852","https://openalex.org/W2592562038","https://openalex.org/W2615063356","https://openalex.org/W2617837836","https://openalex.org/W2949547296","https://openalex.org/W2950133940","https://openalex.org/W2951527505","https://openalex.org/W2951701153","https://openalex.org/W2963595025","https://openalex.org/W2997617958"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2180954594","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2052835778","https://openalex.org/W2103419012","https://openalex.org/W2384498496","https://openalex.org/W4286432911","https://openalex.org/W2810682696","https://openalex.org/W3004518042"],"abstract_inverted_index":{"Bag-of-Words":[0],"with":[1],"TF-IDF":[2],"or":[3,20,53],"other":[4],"weighting":[5],"schemes":[6],"is":[7,62],"commonly":[8],"adopted":[9],"ways":[10],"for":[11],"document":[12,44,76],"representation.":[13],"However,":[14],"they":[15],"fail":[16],"to":[17,29,33,49],"capture":[18],"sequential":[19,85],"semantic":[21,52,83],"information":[22,86],"in":[23],"the":[24,51,57,60,68],"sentence,":[25],"and":[26,36,42,84,102],"would":[27],"lead":[28],"high-dimensional":[30],"vector":[31],"due":[32],"misspelling,":[34],"acronyms":[35],"so":[37],"on.":[38],"Distributed":[39],"word":[40,81,100],"embedding":[41,45],"even":[43],"methods":[46],"are":[47],"proposed":[48,93],"encode":[50],"contextual":[54],"information.":[55],"Whereas,":[56],"quality":[58],"of":[59,87],"representation":[61,77],"not":[63],"always":[64],"good.":[65],"To":[66],"relieve":[67],"above":[69],"mentioned":[70],"problems,":[71],"we":[72],"propose":[73],"a":[74],"high-quality":[75],"model,":[78],"which":[79],"takes":[80],"morphology,":[82],"global":[88],"context":[89],"into":[90],"consideration.":[91],"The":[92],"model":[94],"could":[95],"outperform":[96],"state-of-the-art":[97],"traditional":[98],"ways,":[99],"embedding-based":[101],"character-aware":[103],"models":[104],"on":[105],"text":[106],"classification":[107],"task.":[108]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}