Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.Knowledge Enhanced Contextual Word Representations. Peters, Mark Neumann, Robert Logan, Roy Schwartz, Vidur Joshi, Sameer Singh, Noah A. Yoav Levine, Barak Lenz, Or Dagan, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, Yoav Shoham.LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items. Davide Colla, Enrico Mensa and Daniele P.This dataset is licensed under a Creative Commons Attribution-NonCommercial 4.0 License. You have a two-hour window of clear weather to finish working on the lawn The expanded window will give us time to catch the thieves The enemy landed several of our aircraftsĪgassi beat Becker in the tennis championship The pilot managed to land the airplane safely I keep a glass of water next to my bed when I sleep There's a lot of trash on the bed of the river Please take results in the Arxiv version, which is more up to date, as baseline for your evaluations. Note: Results slightly differ between NAACL and Arxiv versions of the paper. Camacho-Collados, NAACL 2019 (Minneapolis, USA). WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations.WiC was also used for a shared task at SemDeep-5 IJCAI workshop. WiC is featured as a part of the SuperGLUE benchmark. Participate in WiC's CodaLab competition: submit your results on the test set and see where you stand in the leaderboard! It is constructed using high quality annotations curated by experts.It is framed asa binary classification dataset, in which, unlike Stanford Contextual Word Similarity (SCWS), identical words are paired with each other (in different contexts) hence, a context-insensitive word embedding model would perform similarly to a random baseline.It is suitable for evaluating a wide range of applications, including contextualized word and sense representation and Word Sense Disambiguation.WiC features multiple interesting characteristics: In fact, the dataset can also be viewed as an application of Word Sense Disambiguation in practise. The task is to identify if the occurrences of w in the two contexts correspond to the same meaning or not. Each of these contexts triggers a specific meaning of w. Each instance in WiC has a target word w, either a verb or a noun, for which two contexts are provided. WiC is framed as a binary classification task. Contextualised word embeddings are an attempt at addressing this limitation by computing dynamic representations for words which can adapt based on context.Ī system's task on the WiC dataset is to identify the intended meaning of words. Mainstream static word embeddings, such as Word2vec and GloVe, are unable to reflect this dynamic semantic nature. Depending on its context, an ambiguous word can refer to multiple, potentially unrelated, meanings.
0 kommentar(er)
