https://github.com/elerisarsfield/semeval
공식 코드UoB at SemEval-2020 Task 1: Automatic Identification of Novel Word Senses
Papers with Code 아카이브
Word Sense Disambiguation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 16
- 보존된 평가 기록
- 181
The task of Word Sense Disambiguation (WSD) consists of associating words in context with their most suitable entry in a pre-defined sense inventory. The de-facto sense inventory for English in WSD is WordNet.. For example, given the word “mouse” and the following sentence:
“A mouse consists of an object held in one's hand, with one or more buttons.”
we would assign “mouse” with its electronic device sense (the 4th sense in the WordNet sense inventory).
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/facebookresearch/wsd-biencoders
공식 코드Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders
https://github.com/fitz-like-coding/cwtm
공식 코드CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling
https://github.com/francescoperiti/cssdetection
공식 코드A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change
https://github.com/getalp/Flaubert
공식 코드FlauBERT: Unsupervised Language Model Pre-training for French
https://github.com/getalp/disambiguate
공식 코드https://github.com/google-research/google-research
공식 코드https://github.com/hazyresearch/h3
공식 코드Hungry Hungry Hippos: Towards Language Modeling with State Space Models
https://github.com/hrouhizadeh/SBU-WSD-Corpus
공식 코드Persian-WSD-Corpus: A Sense Annotated Corpus for Persian All-words Word Sense Disambiguation
https://github.com/idiap/sense_aware_NMT
공식 코드Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation
https://github.com/jadeleiyu/word_sense_extension
공식 코드https://github.com/jimiyulu/WSD_MemNN
공식 코드https://github.com/joeljang/elm
공식 코드Exploring the Benefits of Training Expert Language Models over Instruction Tuning
https://github.com/jorge-martinez-gil/uwsd
공식 코드Context-Aware Semantic Similarity Measurement for Unsupervised Word Sense Disambiguation
https://github.com/jpelhaW/incorporating_wsd_into_nlm
공식 코드Incorporating Word Sense Disambiguation in Neural Language Models
https://github.com/kaist-lklab/cot-collection
공식 코드https://github.com/kaistai/cot-collection
공식 코드https://github.com/kategavrishina/rudsi
공식 코드https://github.com/lawsonabs/pun
공식 코드A Dual-Attention Neural Network for Pun Location and Using Pun-Gloss Pairs for Interpretation
https://github.com/livnlp/npms
공식 코드Together We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings
https://github.com/lucy3/words_as_gatekeepers
공식 코드Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications
https://github.com/maxylee/3am
공식 코드3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
https://github.com/mbzuai-nlp/lamini-lm
공식 코드LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
https://github.com/mdtux89/amr-evaluation
공식 코드https://github.com/megagonlabs/SubjQA
공식 코드https://github.com/melzohbi/contrastwsd
공식 코드https://github.com/microsoft/DeBERTa
공식 코드https://github.com/mindful/mweaswsd
공식 코드MWE as WSD: Solving Multiword Expression Identification with Word Sense Disambiguation
https://github.com/mnn-001-p/lodlit
공식 코드How Contentious Terms About People and Cultures are Used in Linked Open Data
https://github.com/nlpub/watasense
공식 코드An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages
https://github.com/ntunlp/multisense_embedding_alignment
공식 코드Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
https://github.com/nusnlp/contextemb-wsd
공식 코드Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
https://github.com/openai/gpt-3
공식 코드https://github.com/paperswithcode/galai
공식 코드https://github.com/princeton-nlp/metric-wsd
공식 코드Non-Parametric Few-Shot Learning for Word Sense Disambiguation
https://github.com/rktamplayo/AutoSense
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.