Papers with Code 아카이브
Semantic Similarity
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 28
- 보존된 평가 기록
- 21
The main objective Semantic Similarity is to measure the distance between the semantic meanings of a pair of words, phrases, sentences, or documents. For example, the word “car” is more similar to “bus” than it is to “cat”. The two main approaches to measuring Semantic Similarity are knowledge-based approaches and corpus-based, distributional methods.
Source: Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/mxahan/nev-ncd
공식 코드Novel Categories Discovery Via Constraints on Empirical Prediction Statistics
https://github.com/namisan/mt-dnn
공식 코드https://github.com/nashrahhaque/sd-miae
공식 코드Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum
https://github.com/ncbi-nlp/BLUE_Benchmark
공식 코드https://github.com/ncbi-nlp/NCBI_BERT
공식 코드https://github.com/ng-j-p/rouge-we
공식 코드Better Summarization Evaluation with Word Embeddings for ROUGE
https://github.com/nheist/Cat2Ax
공식 코드https://github.com/nicolas-lair/AidMe
공식 코드User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant
https://github.com/nikosuenderhauf/graphConvNetsForNavigation
공식 코드https://github.com/nimajam41/3d-knn-defense
공식 코드KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Search
https://github.com/niuchuangnn/SPICE
공식 코드https://github.com/nl2g/effeval
공식 코드EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics
https://github.com/nlpub/watasense
공식 코드An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages
https://github.com/nmrksic/attract-repel
공식 코드https://github.com/nmrksic/counter-fitting
공식 코드https://github.com/nmrksic/lear
공식 코드https://github.com/nokia/code-compass
공식 코드https://github.com/nouhadziri/THRED
공식 코드Augmenting Neural Response Generation with Context-Aware Topical Attention
https://github.com/nusnlp/Self-J
공식 코드Self-Judge: Selective Instruction Following with Alignment Self-Evaluation
https://github.com/o-vigia/gma3d
공식 코드GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow
https://github.com/oaraque/moral-foundations
공식 코드MoralStrength: Exploiting a Moral Lexicon and Embedding Similarity for Moral Foundations Prediction
https://github.com/odedh/textual-pca
공식 코드https://github.com/omossad/fat-albert
공식 코드FAT ALBERT: Finding Answers in Large Texts using Semantic Similarity Attention Layer based on BERT
https://github.com/osome-iu/Rematch-RARE
공식 코드https://github.com/overwindows/semanticcodesearch
공식 코드Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus
https://github.com/ozzyou/3d-avs
공식 코드https://github.com/perceptioncomputinglab/medfilip
공식 코드https://github.com/phil0212/sgc-net
공식 코드SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection
https://github.com/phmeier/smaragd
공식 코드SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance
https://github.com/pilehvar/deconf
공식 코드https://github.com/pioneer-innovation/zero-shot-object-navigation
공식 코드https://github.com/pkargupta/epimine
공식 코드https://github.com/pkumod/vgstore
공식 코드VGStore: A Multimodal Extension to SPARQL for Querying RDF Scene Graph
https://github.com/poloclub/neuro-cartography
공식 코드NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks
https://github.com/poppinace/sapa
공식 코드SAPA: Similarity-Aware Point Affiliation for Feature Upsampling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.