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/DiwanshuShekhar/bi_encoder_lstm
공식 코드https://github.com/EducationalTestingService/CATS
공식 코드Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
https://github.com/Embedding/Chinese-Word-Vectors
공식 코드Analogical Reasoning on Chinese Morphological and Semantic Relations
https://github.com/EmpathYang/ADEPT
공식 코드https://github.com/FEE-Fair-Embedding-Engine/FEE
공식 코드Fair Embedding Engine: A Library for Analyzing and Mitigating Gender Bias in Word Embeddings
https://github.com/FelixFrohnertDB/arxiv_nlp
공식 코드Discovering emergent connections in quantum physics research via dynamic word embeddings
https://github.com/FilippoC/disc-span-parser-release
공식 코드https://github.com/Franck-Dernoncourt/model-theoretic
공식 코드Mapping distributional to model-theoretic semantic spaces: a baseline
https://github.com/FranxYao/Deep-Generative-Models-for-Natural-Language-Processing
공식 코드https://github.com/FranxYao/PoincareProbe
공식 코드https://github.com/FranxYao/dgm_latent_bow
공식 코드https://github.com/GanjinZero/CODER
공식 코드CODER: Knowledge infused cross-lingual medical term embedding for term normalization
https://github.com/HHansi/Embed2Detect
공식 코드Embed2Detect: Temporally Clustered Embedded Words for Event Detection in Social Media
https://github.com/HHansi/Semeval-2020-Task3
공식 코드https://github.com/HIT-SCIR/ELMoForManyLangs
공식 코드Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation
https://github.com/HKUNLP/instructor-embedding
공식 코드One Embedder, Any Task: Instruction-Finetuned Text Embeddings
https://github.com/HKUST-KnowComp/MWE
공식 코드Multiplex Word Embeddings for Selectional Preference Acquisition
https://github.com/HSLCY/VCWE
공식 코드https://github.com/Hazel1994/Visually_Grounded_Word_Embeddings
공식 코드Learning Zero-Shot Multifaceted Visually Grounded Word Embeddings via Multi-Task Training
https://github.com/HazyResearch/anchor-stability
공식 코드https://github.com/HazyResearch/smallfry
공식 코드https://github.com/HongyuGong/EnrichedWordRepresentation
공식 코드Enriching Word Embeddings with Temporal and Spatial Information
https://github.com/HongyuGong/Geometry-of-Compositionality
공식 코드https://github.com/Hrezaei/rhymes
공식 코드Word Embeddings Are Capable of Capturing Rhythmic Similarity of Words
https://github.com/IBM/WordMoversEmbeddings
공식 코드https://github.com/IBM/ne-table-datasets
공식 코드https://github.com/Institute-for-Artificial-Intelligence/Sparse-Interpretable-Word-Embeddings-For-Medical-Domain
공식 코드Evaluating Sparse Interpretable Word Embeddings for Biomedical Domain
https://github.com/IyatomiLab/CE-CLCNN
공식 코드End-to-End Text Classification via Image-based Embedding using Character-level Networks
https://github.com/JaTrev/unsupervised_graph-based
공식 코드GraphTMT: Unsupervised Graph-based Topic Modeling from Video Transcripts
https://github.com/JasonForJoy/DSTC7-ResponseSelection
공식 코드Building Sequential Inference Models for End-to-End Response Selection
https://github.com/JingqingZ/KG4ZeroShotText
공식 코드Integrating Semantic Knowledge to Tackle Zero-shot Text Classification
https://github.com/Jivnesh/EvalSan
공식 코드https://github.com/JohnGiorgi/DeCLUTR
공식 코드DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
https://github.com/JoyeBright/DeepSentiPers
공식 코드DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus
https://github.com/KRR-Oxford/DeepOnto
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.