Papers with Code 아카이브
Word Embeddings
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 0
- 보존된 평가 기록
- 0
Word embedding is the collective name for a set of language modeling and feature learning techniques in natural language processing (NLP) where words or phrases from the vocabulary are mapped to vectors of real numbers.
Techniques for learning word embeddings can include Word2Vec, GloVe, and other neural network-based approaches that train on an NLP task such as language modeling or document classification.
<span style="color:grey; opacity: 0.6">( Image credit: Dynamic Word Embedding for Evolving Semantic Discovery )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/epapagia/RVA
공식 코드https://github.com/epfml/Bi-Sent2Vec
공식 코드https://github.com/epfml/X2Static
공식 코드Obtaining Better Static Word Embeddings Using Contextual Embedding Models
https://github.com/epfml/sent2vec
공식 코드Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
https://github.com/ethanhezhao/MetaLDA
공식 코드MetaLDA: a Topic Model that Efficiently Incorporates Meta information
https://github.com/exploration-lab/iitk-semeval-2024-task-1
공식 코드https://github.com/explosion/projects/tree/v3/benchmarks/ner_embeddings
공식 코드https://github.com/f-almeman/3d-ex
공식 코드3D-EX : A Unified Dataset of Definitions and Dictionary Examples
https://github.com/facebookresearch/DME
공식 코드Dynamic Meta-Embeddings for Improved Sentence Representations
https://github.com/facebookresearch/InferSent
공식 코드Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
https://github.com/facebookresearch/MUSE
공식 코드https://github.com/facebookresearch/SentEval
공식 코드Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
https://github.com/facebookresearch/StarSpace
공식 코드https://github.com/facebookresearch/fastText
공식 코드https://github.com/facebookresearch/randsent
공식 코드No Training Required: Exploring Random Encoders for Sentence Classification
https://github.com/facebookresearch/vissl
공식 코드Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
https://github.com/federated-learning-experiments/fl-text-models
공식 코드https://github.com/fereshtehjafarii/StructuralSentenceRepresentation
공식 코드A Self-supervised Representation Learning of Sentence Structure for Authorship Attribution
https://github.com/fhou80/EntEmb
공식 코드Improving Entity Linking through Semantic Reinforced Entity Embeddings
https://github.com/fhshubho/cgs-zsl
공식 코드https://github.com/filby89/NTUA-BEEU-eccv2020
공식 코드Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss
https://github.com/firstdayofjune/aire-20
공식 코드https://github.com/fitz-like-coding/cwtm
공식 코드CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling
https://github.com/florianmai/word2mat
공식 코드CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
https://github.com/foger3/arc_deeplearning
공식 코드Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method
https://github.com/forest-snow/clime-ui
공식 코드https://github.com/francescoperiti/cssdetection
공식 코드A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change
https://github.com/francesita/CS-Embed-SemEval2020
공식 코드https://github.com/franciscovargas/Bias_space_study
공식 코드Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation
https://github.com/ftvalentini/biaspmi
공식 코드On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach
https://github.com/ftvalentini/embeddingsbiasfrequency
공식 코드The Undesirable Dependence on Frequency of Gender Bias Metrics Based on Word Embeddings
https://github.com/ftvalentini/embeddingsfrequency
공식 코드Investigating the Frequency Distortion of Word Embeddings and Its Impact on Bias Metrics
https://github.com/fvialibre/edia
공식 코드https://github.com/gchronis/features_in_context
공식 코드https://github.com/gchrupala/imaginet
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.