Papers with Code 아카이브
Word Sense Induction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 5
Word sense induction (WSI) is widely known as the “unsupervised version” of WSD. The problem states as: Given a target word (e.g., “cold”) and a collection of sentences (e.g., “I caught a cold”, “The weather is cold”) that use the word, cluster the sentences according to their different senses/meanings. We do not need to know the sense/meaning of each cluster, but sentences inside a cluster should have used the target words with the same sense.
Description from NLP Progress
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/akutuzov/russian_wsi
공식 코드Russian word sense induction by clustering averaged word embeddings
https://github.com/asafamr/SymPatternWSI
공식 코드Word Sense Induction with Neural biLM and Symmetric Patterns
https://github.com/asafamr/bertwsi
공식 코드https://github.com/bsheludko/lexical-substitution
공식 코드https://github.com/dingwc/multisense
공식 코드https://github.com/dustalov/watset
공식 코드Watset: Automatic Induction of Synsets from a Graph of Synonyms
https://github.com/elerisarsfield/semeval
공식 코드UoB at SemEval-2020 Task 1: Automatic Identification of Novel Word Senses
https://github.com/francescoperiti/cssdetection
공식 코드A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change
https://github.com/kategavrishina/rudsi
공식 코드https://github.com/lucy3/words_as_gatekeepers
공식 코드Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications
https://github.com/rktamplayo/AutoSense
공식 코드https://github.com/sbos/AdaGram.jl
공식 코드https://github.com/Garrafao/WUGs
https://github.com/SagarDollin/unsupervised_WSD_on_top_of_word2vec
https://github.com/hjian42/Geo-Twitter2019
https://github.com/lopuhin/python-adagram
https://github.com/lucy3/bertwsi
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.