FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102617222> ?p ?o ?g. }

• W3102617222 abstract "The ability to correctly model distinct meanings of a word is crucial for the effectiveness of semantic representation techniques. However, most existing evaluation benchmarks for assessing this criterion are tied to sense inventories (usually WordNet), restricting their usage to a small subset of knowledge-based representation techniques. The Word-in-Context dataset (WiC) addresses the dependence on sense inventories by reformulating the standard disambiguation task as a binary classification problem; but, it is limited to the English language. We put forward a large multilingual benchmark, XL-WiC, featuring gold standards in 12 new languages from varied language families and with different degrees of resource availability, opening room for evaluation scenarios such as zero-shot cross-lingual transfer. We perform a series of experiments to determine the reliability of the datasets and to set performance baselines for several recent contextualized multilingual models. Experimental results show that even when no tagged instances are available for a target language, models trained solely on the English data can attain competitive performance in the task of distinguishing different meanings of a word, even for distant languages. XL-WiC is available at https://pilehvar.github.io/xlwic/." @default.
• W3102617222 created "2020-11-23" @default.
• W3102617222 creator A5020321133 @default.
• W3102617222 creator A5053806445 @default.
• W3102617222 creator A5086289154 @default.
• W3102617222 creator A5091017313 @default.
• W3102617222 date "2020-01-01" @default.
• W3102617222 modified "2023-10-18" @default.
• W3102617222 title "XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization" @default.
• W3102617222 cites W1549944563 @default.
• W3102617222 cites W1599894580 @default.
• W3102617222 cites W1664002590 @default.
• W3102617222 cites W2041532239 @default.
• W3102617222 cites W2049303930 @default.
• W3102617222 cites W2051398498 @default.
• W3102617222 cites W2081580037 @default.
• W3102617222 cites W2101105183 @default.
• W3102617222 cites W2120699290 @default.
• W3102617222 cites W2127289991 @default.
• W3102617222 cites W2131540451 @default.
• W3102617222 cites W2159719802 @default.
• W3102617222 cites W2164019165 @default.
• W3102617222 cites W2167643563 @default.
• W3102617222 cites W2251529656 @default.
• W3102617222 cites W2251920838 @default.
• W3102617222 cites W2281909328 @default.
• W3102617222 cites W2293179254 @default.
• W3102617222 cites W2407403466 @default.
• W3102617222 cites W2436001372 @default.
• W3102617222 cites W2491063832 @default.
• W3102617222 cites W2595644810 @default.
• W3102617222 cites W2740782137 @default.
• W3102617222 cites W2753628379 @default.
• W3102617222 cites W2807217870 @default.
• W3102617222 cites W2918919089 @default.
• W3102617222 cites W2952682849 @default.
• W3102617222 cites W2956105246 @default.
• W3102617222 cites W2963341956 @default.
• W3102617222 cites W2963403868 @default.
• W3102617222 cites W2963506925 @default.
• W3102617222 cites W2964121744 @default.
• W3102617222 cites W2964174820 @default.
• W3102617222 cites W2986154550 @default.
• W3102617222 cites W2990704537 @default.
• W3102617222 cites W3034469191 @default.
• W3102617222 cites W3034675880 @default.
• W3102617222 cites W3034782826 @default.
• W3102617222 cites W3035257795 @default.
• W3102617222 cites W3035390927 @default.
• W3102617222 cites W3035497479 @default.
• W3102617222 cites W3037109418 @default.
• W3102617222 cites W3038047120 @default.
• W3102617222 cites W3045462440 @default.
• W3102617222 cites W3082793270 @default.
• W3102617222 cites W3082928416 @default.
• W3102617222 cites W3089269909 @default.
• W3102617222 cites W3101094968 @default.
• W3102617222 cites W3104033643 @default.
• W3102617222 cites W3204526376 @default.
• W3102617222 cites W45923878 @default.
• W3102617222 cites W630532510 @default.
• W3102617222 cites W1566049083 @default.
• W3102617222 doi "https://doi.org/10.18653/v1/2020.emnlp-main.584" @default.
• W3102617222 hasPublicationYear "2020" @default.
• W3102617222 type Work @default.
• W3102617222 sameAs 3102617222 @default.
• W3102617222 citedByCount "17" @default.
• W3102617222 countsByYear W31026172222020 @default.
• W3102617222 countsByYear W31026172222021 @default.
• W3102617222 countsByYear W31026172222022 @default.
• W3102617222 crossrefType "proceedings-article" @default.
• W3102617222 hasAuthorship W3102617222A5020321133 @default.
• W3102617222 hasAuthorship W3102617222A5053806445 @default.
• W3102617222 hasAuthorship W3102617222A5086289154 @default.
• W3102617222 hasAuthorship W3102617222A5091017313 @default.
• W3102617222 hasBestOaLocation W31026172221 @default.
• W3102617222 hasConcept C105795698 @default.
• W3102617222 hasConcept C13280743 @default.
• W3102617222 hasConcept C137293760 @default.
• W3102617222 hasConcept C138885662 @default.
• W3102617222 hasConcept C151730666 @default.
• W3102617222 hasConcept C154945302 @default.
• W3102617222 hasConcept C157659113 @default.
• W3102617222 hasConcept C162324750 @default.
• W3102617222 hasConcept C177264268 @default.
• W3102617222 hasConcept C17744445 @default.
• W3102617222 hasConcept C185798385 @default.
• W3102617222 hasConcept C187736073 @default.
• W3102617222 hasConcept C199360897 @default.
• W3102617222 hasConcept C199539241 @default.
• W3102617222 hasConcept C204321447 @default.
• W3102617222 hasConcept C205649164 @default.
• W3102617222 hasConcept C206345919 @default.
• W3102617222 hasConcept C23123220 @default.
• W3102617222 hasConcept C27158222 @default.
• W3102617222 hasConcept C2776359362 @default.
• W3102617222 hasConcept C2779343474 @default.
• W3102617222 hasConcept C2780451532 @default.
• W3102617222 hasConcept C2780712339 @default.
• W3102617222 hasConcept C31258907 @default.

• next