{"id":"https://openalex.org/W2251665349","doi":"https://doi.org/10.18653/v1/w15-2520","title":"Novel Document Level Features for Statistical Machine Translation","display_name":"Novel Document Level Features for Statistical Machine Translation","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251665349","doi":"https://doi.org/10.18653/v1/w15-2520","mag":"2251665349"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-2520","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2520","pdf_url":"https://www.aclweb.org/anthology/W15-2520.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 Second Workshop on Discourse in Machine Translation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-2520.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100451786","display_name":"Rong Zhang","orcid":"https://orcid.org/0000-0002-2288-2847"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rong Zhang","raw_affiliation_strings":["IBM T.J. Watson Research Center Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center Yorktown Heights, NY 10598, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112897636","display_name":"Abraham Ittycheriah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abraham Ittycheriah","raw_affiliation_strings":["IBM T.J. Watson Research Center Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center Yorktown Heights, NY 10598, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100451786"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2943,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86439056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"157"},"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9873999953269958,"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":0.8262730836868286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6913001537322998},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6765372157096863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6326271295547485},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.61868816614151},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5774855613708496},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.49613747000694275},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.47799649834632874},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4441480040550232},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4301791489124298},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06906130909919739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262730836868286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6913001537322998},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6765372157096863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6326271295547485},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.61868816614151},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5774855613708496},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.49613747000694275},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.47799649834632874},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4441480040550232},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4301791489124298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06906130909919739},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-2520","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2520","pdf_url":"https://www.aclweb.org/anthology/W15-2520.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 Second Workshop on Discourse in Machine Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-2520","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2520","pdf_url":"https://www.aclweb.org/anthology/W15-2520.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 Second Workshop on Discourse in Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251665349.pdf","grobid_xml":"https://content.openalex.org/works/W2251665349.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1707559977","https://openalex.org/W1901714926","https://openalex.org/W2067815623","https://openalex.org/W2110295509","https://openalex.org/W2115030595","https://openalex.org/W2115056464","https://openalex.org/W2117045850","https://openalex.org/W2138477841","https://openalex.org/W2139183784","https://openalex.org/W2141895568","https://openalex.org/W2159882563","https://openalex.org/W2160131015","https://openalex.org/W2162429782","https://openalex.org/W2166545452","https://openalex.org/W2180952760","https://openalex.org/W2250761393","https://openalex.org/W2250861721","https://openalex.org/W3203909556"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2962780935","https://openalex.org/W4387896177","https://openalex.org/W4385557855","https://openalex.org/W2883671469","https://openalex.org/W2154124206","https://openalex.org/W3041490575","https://openalex.org/W2970690932"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"document":[5,46,78],"level":[6],"features":[7,39,82],"that":[8],"capture":[9],"necessary":[10],"information":[11],"to":[12,28,54,68,86],"help":[13],"MT":[14,91],"system":[15],"perform":[16],"better":[17],"word":[18],"sense":[19],"disambiguation":[20],"in":[21,76,100],"the":[22,42,56,59,70,73],"translation":[23,33,61,74],"process.":[24],"We":[25],"describe":[26],"enhancements":[27],"a":[29,77,94],"Maximum":[30],"Entropy":[31],"based":[32],"model,":[34],"utilizing":[35],"long":[36],"distance":[37],"contextual":[38],"identified":[40],"from":[41,48],"span":[43],"of":[44,58,72,90,96,102],"entire":[45],"and":[47,51,67],"both":[49],"source":[50],"target":[52],"sides,":[53],"improve":[55,69],"likelihood":[57],"correct":[60],"for":[62],"words":[63],"with":[64],"multiple":[65],"meanings,":[66],"consistency":[71],"output":[75],"setting.":[79],"The":[80],"proposed":[81],"have":[83],"been":[84],"observed":[85],"achieve":[87],"substantial":[88],"improvement":[89],"performance":[92],"on":[93],"variety":[95],"standard":[97],"test":[98],"sets":[99],"terms":[101],"TER/BLEU":[103],"score.":[104]},"counts_by_year":[{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
