{"id":"https://openalex.org/W4416034525","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1317","title":"Estimating Machine Translation Difficulty","display_name":"Estimating Machine Translation Difficulty","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034525","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1317"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1317","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1317","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1317.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1317.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107454193","display_name":"Lorenzo Proietti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Proietti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107423635","display_name":"Stefano Perrella","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefano Perrella","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056284717","display_name":"Vil\u00e9m Zouhar","orcid":"https://orcid.org/0000-0001-9874-2069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vil\u00e9m Zouhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026648049","display_name":"Roberto Navigli","orcid":"https://orcid.org/0000-0003-3831-9706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Navigli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035898384","display_name":"Tom Kocmi","orcid":"https://orcid.org/0000-0002-7993-9859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Kocmi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29887508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24261","last_page":"24285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.824999988079071,"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":0.824999988079071,"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/T13629","display_name":"Text Readability and Simplification","score":0.0142000000923872,"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/T14347","display_name":"Big Data and Digital Economy","score":0.011800000444054604,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/machine-translation","display_name":"Machine translation","score":0.8073999881744385},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.779699981212616},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.633400022983551},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6129999756813049},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5759000182151794}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8073999881744385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.779699981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6412000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6401000022888184},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.633400022983551},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6129999756813049},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5914999842643738},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1317","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1317","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1317.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1317","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1317","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1317.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8779474850","display_name":null,"funder_award_id":"PE0000013-FAIR","funder_id":"https://openalex.org/F4320322510","funder_display_name":"Sapienza Universit\u00e0 di Roma"}],"funders":[{"id":"https://openalex.org/F4320322510","display_name":"Sapienza Universit\u00e0 di Roma","ror":"https://ror.org/02be6w209"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034525.pdf","grobid_xml":"https://content.openalex.org/works/W4416034525.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"translation":[1,39,64,164],"quality":[2,75],"has":[3],"steadily":[4],"improved":[5,137],"over":[6],"the":[7,61,73,99,131],"years,":[8],"achieving":[9,130],"near-perfect":[10],"translations":[11],"in":[12],"recent":[13],"benchmarks.These":[14],"highquality":[15],"outputs":[16],"make":[17],"it":[18,89],"difficult":[19],"to":[20,26,83,90,108,149,160],"distinguish":[21],"between":[22],"state-of-the-art":[23],"models":[24,120,138],"and":[25,49,87,94,125,143,155],"identify":[27],"areas":[28],"for":[29,44,113,139],"future":[30,51],"improvement.In":[31],"this":[32,53,57],"context,":[33],"automatically":[34],"identifying":[35],"texts":[36,154],"where":[37],"machine":[38,114,163],"systems":[40],"struggle":[41],"holds":[42],"promise":[43],"developing":[45],"more":[46,110],"discriminative":[47],"evaluations":[48],"guiding":[50],"research.In":[52],"work,":[54],"we":[55,97,134],"address":[56],"gap":[58],"by":[59,105],"formalizing":[60],"task":[62],"of":[63,76,102,153],"difficulty":[65,70,85,103,140],"estimation,":[66,141],"defining":[67],"a":[68,80],"text's":[69],"based":[71],"on":[72],"expected":[74],"its":[77],"translations.We":[78],"introduce":[79],"new":[81],"metric":[82],"evaluate":[84],"estimators":[86,104],"use":[88],"assess":[91],"both":[92,122],"baselines":[93],"novel":[95],"approaches.Finally,":[96],"demonstrate":[98],"practical":[100],"utility":[101],"using":[106],"them":[107],"construct":[109],"challenging":[111],"benchmarks":[112],"translation.Our":[115],"results":[116],"show":[117],"that":[118],"dedicated":[119],"outperform":[121],"heuristic-based":[123],"methods":[124],"LLM-asa-judge":[126],"approaches,":[127],"with":[128],"sentinel-src":[129],"best":[132],"performance.Thus,":[133],"release":[135],"two":[136],"sentinel-src-24":[142],"sentinel-src-25,":[144],"which":[145],"can":[146],"be":[147],"used":[148],"scan":[150],"large":[151],"collections":[152],"select":[156],"those":[157],"most":[158],"likely":[159],"challenge":[161],"contemporary":[162],"systems.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}