{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":14,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":14,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"0f8f2e53290b","filters":{"venue":"Machine Translation"}},"results":[{"id":"W1982816048","doi":"10.1023/b:coat.0000010117.98933.a0","title":"Trans Type: Development-Evaluation Cycles to Boost Translator's Productivity","year":2002,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine translation; Productivity; Context (archaeology); Translation (biology); Process (computing); Set (abstract data type); Interface (matter); Artificial intelligence; Evaluation of machine translation; Natural language processing; Rule-based machine translation; Software engineering; Machine learning; Programming language; Example-based machine translation; Machine translation software usability","authors":[{"name":"Philippe Langlais","is_ca":true},{"name":"Guy Lapalme","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04654180184988662,"gpt":0.2987353309047347,"spread":0.2521935290548481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01018677,0.002019117,0.001299903,0.002422657,0.001317068,0.003430535,0.002484897,0.002320851,0.02442676],"category_scores_gemma":[0.05710834,0.001893364,0.001109247,0.002194168,0.0008757556,0.007805006,0.003531507,0.003389133,0.01416495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044147,"about_ca_system_score_gemma":0.004660259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001307568,"about_ca_topic_score_gemma":0.002781711,"domain_scores_codex":[0.9893287,0.005963135,0.0009776169,0.001184057,0.002067152,0.0004793916],"domain_scores_gemma":[0.9153705,0.0406106,0.003251699,0.01776073,0.02069916,0.002307285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002680412,0.001195152,0.007819721,0.001252683,0.0001336368,0.0005800332,0.001484764,0.006647133,0.0824338,0.009130913,0.05903308,0.8276086],"study_design_scores_gemma":[0.001234952,0.002750402,0.009457477,0.0004494901,0.0007932395,0.003325038,0.0012902,0.2936416,0.5118759,0.0344213,0.1402801,0.0004803438],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1010392,0.001061002,0.7478031,0.002724031,0.001140637,0.001031753,0.001242862,0.1248554,0.01910205],"genre_scores_gemma":[0.32697,0.0004554015,0.6143854,0.001321104,0.0004101532,0.0007957187,0.002489549,0.03023557,0.02293718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02442676,"threshold_uncertainty_score":0.08171564,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991522508","doi":"10.1007/s10590-008-9036-3","title":"Semi-supervised model adaptation for statistical machine translation","year":2007,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; National Research Council Canada","funders":"","keywords":"Machine translation; Computer science; Translation (biology); Artificial intelligence; Adaptation (eye); Computational linguistics; Natural language processing; Machine learning; Statistical analysis; Statistical model; Statistics; Mathematics; Psychology","authors":[{"name":"Nicola Ueffing","is_ca":true},{"name":"Gholamreza Haffari","is_ca":true},{"name":"Anoop Sarkar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03837286427808482,"gpt":0.3087072662634866,"spread":0.2703344019854018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00298191,0.00118833,0.001757035,0.001066688,0.0008568317,0.001310312,0.002085306,0.001635203,0.003116654],"category_scores_gemma":[0.01068354,0.001062826,0.001578929,0.001525205,0.0007327557,0.002192814,0.001819821,0.002909073,0.003369809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006053965,"about_ca_system_score_gemma":0.001380315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00288158,"about_ca_topic_score_gemma":0.004636925,"domain_scores_codex":[0.9964582,0.002217133,0.0001951431,0.0005478479,0.000445353,0.0001362645],"domain_scores_gemma":[0.9922271,0.004414101,0.0003919464,0.001666406,0.00118787,0.000112581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000558919,0.0003324482,0.0009888941,0.0003757323,0.0005720557,0.0003014666,0.0002068502,0.2845377,0.01803572,0.009712054,0.01840716,0.665971],"study_design_scores_gemma":[0.00001411423,0.00003371117,0.0001775496,0.000007801083,0.00002636368,0.00006138549,0.00001254275,0.9856309,0.004016127,0.008662061,0.00134218,0.00001529007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006437753,0.0004718833,0.9879223,0.000148267,0.0001199904,0.00005753136,0.0002072541,0.003953703,0.0006812831],"genre_scores_gemma":[0.3706477,0.0007788675,0.6145535,0.0004329,0.0002886534,0.0007162277,0.004095616,0.001631358,0.006855149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003116654,"threshold_uncertainty_score":0.01577008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132891320","doi":"10.1007/s10590-011-9112-y","title":"Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment","year":2011,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"University of Pennsylvania","keywords":"Computer science; Machine translation; Natural language processing; Word order; Artificial intelligence; Phrase; Parsing; Word (group theory); Translation (biology); Speech recognition; Arabic; Computational linguistics; Linguistics","authors":[{"name":"Marine Carpuat","is_ca":true},{"name":"Yuval Marton","is_ca":false},{"name":"Nizar Habash","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01793620875493665,"gpt":0.2589407352169916,"spread":0.241004526462055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001236823,0.002108404,0.001146742,0.001704387,0.001123745,0.001994831,0.0008943033,0.0006976207,0.01394494],"category_scores_gemma":[0.005473094,0.0005519444,0.0009084572,0.00218349,0.0003872928,0.001600948,0.001227295,0.00181887,0.01604931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004973943,"about_ca_system_score_gemma":0.002425225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003656298,"about_ca_topic_score_gemma":0.007369354,"domain_scores_codex":[0.9983451,0.0006425359,0.0002477737,0.0003583229,0.000288697,0.0001174746],"domain_scores_gemma":[0.9949585,0.00133548,0.0002078441,0.0009093176,0.002481417,0.0001075901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008858418,0.0004157586,0.001275812,0.0008385934,0.0001782206,0.0007709028,0.0008544646,0.01141351,0.1349755,0.01323057,0.03786577,0.797295],"study_design_scores_gemma":[0.0003638729,0.0008872119,0.004217635,0.0001828245,0.0005208398,0.001544462,0.001192793,0.4632554,0.3407238,0.0264083,0.1603683,0.0003344363],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03865902,0.0008216235,0.9219839,0.0006267181,0.001312724,0.0003420261,0.003296159,0.02462273,0.008335003],"genre_scores_gemma":[0.1260379,0.0005232043,0.8511017,0.0002242226,0.0003180604,0.0002606301,0.008393636,0.003933043,0.009207746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01394494,"threshold_uncertainty_score":0.04665053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2081743236","doi":"10.1007/s10590-014-9166-8","title":"Introduction to special issue on post-editing","year":2014,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Computational linguistics; Natural language processing; Artificial intelligence","authors":[{"name":"Sharon O’Brien","is_ca":false},{"name":"Michel Simard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0073987869319434,"gpt":0.2583055012703789,"spread":0.2509067143384355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003020284,0.002346087,0.002351393,0.004696255,0.001893602,0.005204519,0.00233033,0.002931924,0.1690126],"category_scores_gemma":[0.01259396,0.0008125741,0.001581045,0.003548641,0.001022365,0.006336207,0.002973719,0.004559421,0.0948416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009567514,"about_ca_system_score_gemma":0.001786201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008977327,"about_ca_topic_score_gemma":0.0019543,"domain_scores_codex":[0.9970199,0.0005470018,0.0004219009,0.0006626668,0.001139743,0.0002087267],"domain_scores_gemma":[0.9865093,0.003901944,0.0006661525,0.002089217,0.005672957,0.001160434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005760478,0.0000420555,0.00008546298,0.0004319765,0.00002150881,0.0001363442,0.00003653421,0.0001605757,0.001260271,0.002523072,0.8803322,0.1149125],"study_design_scores_gemma":[0.000009940013,0.00005690445,0.000300209,0.0001509635,0.00002218491,0.0004288148,0.00003248747,0.0007188946,0.001227556,0.005117513,0.9919045,0.0000300246],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.001265698,0.02312748,0.07954898,0.03370966,0.7935155,0.0002800376,0.002038035,0.00557165,0.06094289],"genre_scores_gemma":[0.009118924,0.02065195,0.03709964,0.01304798,0.6072716,0.0002521099,0.005870548,0.007831653,0.2988557],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.1690126,"threshold_uncertainty_score":0.5654036,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118491422","doi":"10.1007/s10590-004-7693-4","title":"A Morphological Tagger for Korean: Statistical Tagging Combined with Corpus-Based Morphological Rule Application","year":2004,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; University of Pennsylvania; Yale University","keywords":"Agglutinative language; Computer science; Artificial intelligence; Natural language processing; Lemma (botany); Trigram; Part-of-speech tagging; Part of speech; Component (thermodynamics); Tag system; Rule-based system; Word (group theory); Precision and recall; Computational linguistics; Speech recognition; Linguistics; Parsing; Algorithm; Biology","authors":[{"name":"Chung–hye Han","is_ca":true},{"name":"Martha Palmer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01525715266378229,"gpt":0.2739101294085907,"spread":0.2586529767448084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002606715,0.001642745,0.001444645,0.003068774,0.001005826,0.002586088,0.002144214,0.001302507,0.009194428],"category_scores_gemma":[0.005729469,0.001502299,0.001239003,0.003511168,0.0006625989,0.003548004,0.00214659,0.001511082,0.01392195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004765277,"about_ca_system_score_gemma":0.002173773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001739354,"about_ca_topic_score_gemma":0.003774135,"domain_scores_codex":[0.9985713,0.0003203049,0.0003586714,0.000387969,0.0002776164,0.00008413343],"domain_scores_gemma":[0.9940685,0.00187592,0.0005137195,0.00159202,0.001755396,0.000194548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006477623,0.000425882,0.004569471,0.001410642,0.0002923441,0.002026009,0.0006909586,0.007575568,0.1689234,0.009498956,0.05038342,0.7535557],"study_design_scores_gemma":[0.0003464982,0.0005225249,0.008789343,0.0002993366,0.0008724215,0.00502225,0.0009232895,0.4045576,0.3822188,0.02779903,0.1681628,0.000486039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02271048,0.000422714,0.9047409,0.0002822604,0.0003989277,0.0003901769,0.00667253,0.06057926,0.003802694],"genre_scores_gemma":[0.06732234,0.0003689145,0.9075293,0.0002243136,0.00008684397,0.0003159331,0.01480748,0.006024958,0.003319915],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009194428,"threshold_uncertainty_score":0.03075844,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145084016","doi":"10.1023/a:1012262211784","title":"Unit Completion for a Computer-aided Translation Typing System","year":2000,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computational linguistics; Natural language processing; Context (archaeology); Word (group theory); Artificial intelligence; Machine translation; Linguistics; History","authors":[{"name":"Philippe Langlais","is_ca":true},{"name":"George Foster","is_ca":true},{"name":"Guy Lapalme","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0330547707272114,"gpt":0.2821371979595065,"spread":0.2490824272322951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001623235,0.001119489,0.001871046,0.001095794,0.001753035,0.002206412,0.001576109,0.001520572,0.02534121],"category_scores_gemma":[0.005571602,0.0008745156,0.001139657,0.001486428,0.0006753654,0.002098595,0.001631008,0.001734584,0.01273013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007660081,"about_ca_system_score_gemma":0.002220989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003402582,"about_ca_topic_score_gemma":0.004037228,"domain_scores_codex":[0.9981798,0.0005128578,0.0002596083,0.0004292446,0.0004446229,0.000173761],"domain_scores_gemma":[0.9963876,0.001509484,0.0001460993,0.0006463086,0.001167184,0.0001432504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003353601,0.0005277111,0.001166186,0.001183949,0.0001330747,0.001612805,0.001342484,0.0257754,0.08657429,0.06262113,0.07692749,0.7387819],"study_design_scores_gemma":[0.0005186457,0.0008543474,0.001063494,0.0001696722,0.000281637,0.001197632,0.0005434793,0.6724846,0.1865951,0.06535114,0.07068934,0.0002509626],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02571415,0.0001782164,0.9366975,0.000302633,0.0002549176,0.0002104175,0.0008450493,0.03213843,0.003658564],"genre_scores_gemma":[0.1837533,0.0001562761,0.7893629,0.000159797,0.0001434401,0.0003278669,0.002910571,0.003843074,0.01934265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02534121,"threshold_uncertainty_score":0.08477479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1594980056","doi":"10.1023/a:1012244918183","title":"Machine Translation of Closed Captions","year":2000,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Closed captioning; Speech translation; Computational linguistics","authors":[{"name":"Fred Popowich","is_ca":true},{"name":"Paul McFetridge","is_ca":true},{"name":"Davide Turcato","is_ca":true},{"name":"Janine Toole","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01603385525805243,"gpt":0.2694640035533037,"spread":0.2534301482952512,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001506694,0.001861228,0.001972511,0.002908287,0.00215224,0.00444157,0.001965328,0.002502593,0.02289673],"category_scores_gemma":[0.01359867,0.001158863,0.001633353,0.003511428,0.001431201,0.004635796,0.00280218,0.002777642,0.01244089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001226939,"about_ca_system_score_gemma":0.001845842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001502286,"about_ca_topic_score_gemma":0.001593498,"domain_scores_codex":[0.9968874,0.001205446,0.0002786055,0.0007499731,0.0006841851,0.0001944425],"domain_scores_gemma":[0.9895068,0.005235067,0.0005020602,0.00176801,0.002816213,0.0001718365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008882449,0.0004855333,0.0006481786,0.003346038,0.0002342603,0.003235782,0.001665476,0.0213104,0.04890677,0.1466612,0.1811715,0.5914466],"study_design_scores_gemma":[0.0003570398,0.0004514375,0.001311408,0.0008153106,0.0003763013,0.002735996,0.001006519,0.3425392,0.1040153,0.268793,0.2773664,0.0002320971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03812276,0.004848077,0.8620152,0.003312792,0.005205445,0.0006429694,0.01029918,0.02153709,0.05401655],"genre_scores_gemma":[0.2592015,0.003640495,0.6669,0.000954556,0.001553422,0.0005857863,0.03495652,0.005610681,0.026597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02289673,"threshold_uncertainty_score":0.07659721,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1496822098","doi":"10.1023/a:1013136005350","title":"Towards a Lexicographic Approach to Lexical Transfer in Machine Translation (Illustrated by the German–Russian Language Pair)","year":2001,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computational linguistics; Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","authors":[{"name":"Igor Mel’čuk","is_ca":true},{"name":"Leo Wanner","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02119614656579054,"gpt":0.2848283274894695,"spread":0.263632180923679,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002319196,0.0006491313,0.0006879511,0.002908816,0.001662549,0.005000312,0.001126557,0.001706946,0.008440513],"category_scores_gemma":[0.004196079,0.0008869142,0.0009805453,0.003269722,0.005242516,0.007426756,0.002824201,0.001984753,0.004532853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001022244,"about_ca_system_score_gemma":0.001510561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001485166,"about_ca_topic_score_gemma":0.001890923,"domain_scores_codex":[0.9984131,0.001026206,0.0001039582,0.000160183,0.0002258661,0.00007068352],"domain_scores_gemma":[0.9986364,0.0008390363,0.00006651165,0.0002142508,0.0002126003,0.00003111689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008089958,0.00005814488,0.0002261242,0.0003841294,0.00002503809,0.0002945836,0.001096268,0.003911075,0.005376738,0.8478625,0.006335361,0.1343491],"study_design_scores_gemma":[0.00003393363,0.00005373856,0.0002371549,0.0001300504,0.00002345894,0.0004406623,0.000533872,0.02864846,0.00721441,0.9127493,0.04989502,0.00003984054],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004344325,0.002739817,0.9649716,0.003472989,0.0004383662,0.00007217452,0.0001012507,0.0006847415,0.02317475],"genre_scores_gemma":[0.1091044,0.004484294,0.8728415,0.000817676,0.0005634691,0.0002275932,0.0003536938,0.000497307,0.01111009],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008440513,"threshold_uncertainty_score":0.02823639,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159939228","doi":"10.1007/s10590-011-9089-6","title":"TransSearch: from a bilingual concordancer to a translation finder","year":2010,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Translation (biology); Artificial intelligence; Sentence; Word (group theory); Example-based machine translation; Computer-assisted translation; Bilingual dictionary; Feature (linguistics); Machine translation software usability; Identification (biology); Computational linguistics; Linguistics","authors":[{"name":"Julien Bourdaillet","is_ca":true},{"name":"Stéphane Huet","is_ca":true},{"name":"Philippe Langlais","is_ca":true},{"name":"Guy Lapalme","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02954497783423231,"gpt":0.3163444565220911,"spread":0.2867994786878588,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003481609,0.001844699,0.00221966,0.005649629,0.002097857,0.003849475,0.003199465,0.00251119,0.03019715],"category_scores_gemma":[0.01248252,0.001479702,0.001754583,0.005228509,0.001055996,0.005715107,0.005807175,0.002323795,0.02291792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009175123,"about_ca_system_score_gemma":0.002910228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003257722,"about_ca_topic_score_gemma":0.005131732,"domain_scores_codex":[0.9956759,0.001287344,0.0004209819,0.00137765,0.001014665,0.0002234611],"domain_scores_gemma":[0.9932213,0.002411848,0.0002683086,0.00194207,0.001880341,0.0002761135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001549314,0.0003774013,0.001541174,0.001018491,0.0002935797,0.00163734,0.001223687,0.006150317,0.04298118,0.03176836,0.1080451,0.803414],"study_design_scores_gemma":[0.0006118783,0.0006732421,0.002116475,0.0004255575,0.0006060239,0.003502704,0.002408043,0.4500469,0.1624558,0.1671071,0.2096254,0.000420866],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01680697,0.0006879927,0.9000599,0.0007089375,0.0005561421,0.0003345689,0.004713112,0.0659029,0.01022949],"genre_scores_gemma":[0.1085142,0.000508148,0.850247,0.0003978573,0.0002919882,0.0003225587,0.01671437,0.008270195,0.0147337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03019715,"threshold_uncertainty_score":0.1010195,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2037632172","doi":"10.1023/b:coat.0000010116.83274.c3","title":"Construction of a Chinese–English Verb Lexicon for Machine Translation and Embedded Multilingual Applications","year":2002,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Directorate for Computer and Information Science and Engineering; National Science Foundation","keywords":"Computer science; Lexicon; Natural language processing; Machine translation; Artificial intelligence; Verb; Lexical database; WordNet","authors":[{"name":"Bonnie J. Dorr","is_ca":false},{"name":"Gina‐Anne Levow","is_ca":false},{"name":"Dekang Lin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01915247602154042,"gpt":0.2812119978952083,"spread":0.2620595218736679,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007147299,0.001214669,0.001222895,0.003514862,0.001601082,0.002459423,0.001188123,0.0006695343,0.01333141],"category_scores_gemma":[0.002789313,0.001110666,0.001171416,0.003478239,0.0006847969,0.002538842,0.002256913,0.001414814,0.007554062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001227423,"about_ca_system_score_gemma":0.003939759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0046816,"about_ca_topic_score_gemma":0.007886292,"domain_scores_codex":[0.9992855,0.0001581113,0.0001154787,0.0002055071,0.0001507893,0.00008466229],"domain_scores_gemma":[0.9988625,0.0002661614,0.00006950476,0.0001501041,0.0005819851,0.00006962332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006964793,0.0004362007,0.003989907,0.002126161,0.0001993543,0.004111498,0.002695431,0.01460752,0.1502956,0.1490709,0.08710958,0.5846614],"study_design_scores_gemma":[0.00035848,0.000444053,0.004691276,0.0004257676,0.0006945234,0.00264085,0.002133946,0.3754455,0.1916105,0.0999506,0.3213098,0.0002947336],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03065477,0.0003691104,0.9287533,0.0004648471,0.0003688736,0.0008602518,0.005851702,0.01590016,0.01677707],"genre_scores_gemma":[0.213377,0.0005254701,0.7441595,0.0002082116,0.0001220183,0.0009348615,0.02685332,0.003931476,0.009888169],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01333141,"threshold_uncertainty_score":0.04459804,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063381274","doi":"10.1007/s10590-006-9017-3","title":"EBMT by tree-phrasing","year":2006,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Universität Stuttgart","keywords":"Computer science; Machine translation; Natural language processing; Exploit; Phrase; Artificial intelligence; Example-based machine translation; Machine translation software usability; Translation (biology); Dependency (UML); Tree (set theory); Simple (philosophy); Computational linguistics; Transfer-based machine translation","authors":[{"name":"Philippe Langlais","is_ca":true},{"name":"Fabrizio Gotti","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007206483007843711,"gpt":0.2440312977121587,"spread":0.236824814704315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001708256,0.00081687,0.0008194618,0.001436329,0.001244123,0.002389636,0.00112333,0.001609628,0.0366308],"category_scores_gemma":[0.01041015,0.0006894449,0.0007784416,0.002564799,0.0009700379,0.004203098,0.002598793,0.001634307,0.01955499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005463238,"about_ca_system_score_gemma":0.001150266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001127724,"about_ca_topic_score_gemma":0.001348861,"domain_scores_codex":[0.9970066,0.00148399,0.0002632462,0.0004838211,0.0005977761,0.0001645238],"domain_scores_gemma":[0.9954853,0.001706941,0.0001305994,0.001664084,0.0009538697,0.00005918067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002367796,0.0001300301,0.0003553996,0.0009086974,0.00008635313,0.0007212556,0.0007983934,0.007300141,0.01671211,0.2378679,0.06973868,0.6651443],"study_design_scores_gemma":[0.0001155373,0.0001479934,0.0005345639,0.0003132684,0.0002029623,0.00187961,0.0003294011,0.1449592,0.05756665,0.561829,0.2320216,0.0001002147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006968914,0.0005699559,0.9352546,0.001036245,0.0008720128,0.0002000451,0.001256424,0.009676233,0.04416563],"genre_scores_gemma":[0.2386493,0.0008941324,0.7154241,0.001134174,0.000496116,0.0003015856,0.003125495,0.005371304,0.03460387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0366308,"threshold_uncertainty_score":0.1225423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034060496","doi":"10.1007/s10590-008-9048-z","title":"METIS-II: low resource machine translation","year":2008,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Metis; Scope (computer science); Computer science; German; Machine translation; Computational linguistics; Natural language processing; Resource (disambiguation); Linguistics; Artificial intelligence; Programming language; World Wide Web","authors":[{"name":"Michaël Carl","is_ca":false},{"name":"Maite Melero","is_ca":false},{"name":"Toni Badía","is_ca":false},{"name":"Vincent Vandeghinste","is_ca":false},{"name":"Peter Dirix","is_ca":false},{"name":"Ineke Schuurman","is_ca":false},{"name":"Στέλλα Μαρκαντωνάτου","is_ca":false},{"name":"Sokratis Sofianopoulos","is_ca":false},{"name":"Marina Vassiliou","is_ca":false},{"name":"Olga Yannoutsou","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02024545271093636,"gpt":0.256454324211225,"spread":0.2362088715002887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001519521,0.002954629,0.002379322,0.002769242,0.001671201,0.004063199,0.002857562,0.001813803,0.04627828],"category_scores_gemma":[0.004462415,0.00138073,0.001510804,0.002731382,0.0006051487,0.003093654,0.003686173,0.002461175,0.04960048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006811377,"about_ca_system_score_gemma":0.001985114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001074052,"about_ca_topic_score_gemma":0.001887062,"domain_scores_codex":[0.9978363,0.0006851826,0.0001951216,0.0005130584,0.0005361754,0.0002341271],"domain_scores_gemma":[0.9979941,0.000573864,0.000111847,0.0007876165,0.0004116913,0.00012102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001932453,0.0004486385,0.0008207777,0.001441666,0.0003602485,0.0007699004,0.0002785976,0.004491558,0.05622046,0.03734394,0.3501199,0.5457718],"study_design_scores_gemma":[0.001571777,0.001366934,0.002033742,0.0003481946,0.0004220315,0.002372865,0.0003906607,0.2766467,0.1783472,0.1008797,0.4353184,0.0003018108],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01287076,0.001222801,0.7013592,0.0008727535,0.001713272,0.0008545605,0.02172454,0.2251254,0.0342568],"genre_scores_gemma":[0.06998738,0.0005688576,0.7980129,0.0006351957,0.0006676859,0.001484287,0.07932874,0.01899421,0.03032085],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04627828,"threshold_uncertainty_score":0.1548162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005440678","doi":"10.1007/s10590-005-2403-4","title":"The Long-Term Forecast for Weather Bulletin Translation","year":2005,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Machine translation; Computer science; Phrase; Task (project management); Sentence; Focus (optics); Natural language processing; Term (time); Artificial intelligence; Translation (biology); Rule-based machine translation; Computational linguistics; Artificial neural network; Machine learning; Engineering","authors":[{"name":"Philippe Langlais","is_ca":true},{"name":"Simona Gandrabur","is_ca":true},{"name":"Thomas Leplus","is_ca":true},{"name":"Guy Lapalme","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01957454266199084,"gpt":0.2810361951975129,"spread":0.2614616525355221,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001005612,0.0007730615,0.0005257946,0.001665402,0.001325597,0.002480092,0.0005921983,0.0009403474,0.03354944],"category_scores_gemma":[0.00587005,0.0005928354,0.0005515387,0.002043778,0.0004533566,0.002712412,0.001263691,0.001352743,0.0214766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008273,"about_ca_system_score_gemma":0.002340042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007959601,"about_ca_topic_score_gemma":0.007262327,"domain_scores_codex":[0.9990426,0.000315778,0.00009389056,0.0002565211,0.0002104711,0.00008081446],"domain_scores_gemma":[0.9977561,0.0007075338,0.0001231669,0.0004655005,0.0008795362,0.00006808102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007920467,0.0001594455,0.003011707,0.0009198116,0.000114578,0.001263115,0.001097011,0.01165664,0.0290195,0.05375557,0.3208661,0.5773444],"study_design_scores_gemma":[0.0002526252,0.0003302205,0.00821831,0.0003425138,0.0002850874,0.001256627,0.001370919,0.3372474,0.06864852,0.06104325,0.5208083,0.0001961826],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1031025,0.003473831,0.6523643,0.008625738,0.007385571,0.000509668,0.06862,0.04923404,0.1066844],"genre_scores_gemma":[0.5250072,0.002303271,0.3358281,0.0006536253,0.0009922974,0.0003168089,0.07504172,0.006300353,0.05355654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03354944,"threshold_uncertainty_score":0.112234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1702922849","doi":"10.1007/s10590-015-9172-5","title":"Complexity of alignment and decoding problems: restrictions and approximations","year":2015,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decoding methods; Viterbi algorithm; Computer science; Parameterized complexity; Computational complexity theory; Sentence; Sequential decoding; Algorithm; Word (group theory); Polynomial; Iterative Viterbi decoding; List decoding; Theoretical computer science; Mathematics; Artificial intelligence; Block code","authors":[{"name":"Noah Fleming","is_ca":true},{"name":"Antonina Kolokolova","is_ca":true},{"name":"Renesa Nizamee","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08034618598023999,"gpt":0.2992751910534103,"spread":0.2189290050731703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01006818,0.001891587,0.003931131,0.003218443,0.002405343,0.009407007,0.0049419,0.004281409,0.01322206],"category_scores_gemma":[0.1000432,0.002105214,0.003775869,0.005510364,0.004954841,0.02423318,0.006180656,0.01015623,0.001979402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00520528,"about_ca_system_score_gemma":0.004695951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005218279,"about_ca_topic_score_gemma":0.005499694,"domain_scores_codex":[0.9847564,0.006953578,0.000905888,0.002347145,0.003299385,0.001737565],"domain_scores_gemma":[0.7760564,0.2066484,0.003301672,0.008820168,0.003634064,0.001539215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001334746,0.0006514283,0.004574554,0.0012579,0.0002364887,0.0005119529,0.001170884,0.4043621,0.001588876,0.4336743,0.03366266,0.1169739],"study_design_scores_gemma":[0.00006436505,0.00003850956,0.000514509,0.00005751204,0.00003906355,0.0001592699,0.0001480708,0.4812514,0.000597914,0.5154575,0.001634606,0.00003734607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08368531,0.004751166,0.8683016,0.01350511,0.0005752726,0.0002537823,0.002042134,0.001004671,0.02588087],"genre_scores_gemma":[0.6980473,0.004990638,0.269344,0.00190987,0.003389953,0.0008609836,0.004942419,0.001769095,0.01474582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01322206,"threshold_uncertainty_score":0.05324626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}