Papers with Code 아카이브

Semantic Textual Similarity

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 13
보존된 평가 기록: 280

Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.

Image source: Learning Semantic Textual Similarity from Conversations

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/ptarau/recursors

공식 코드

Full Automation of Goal-driven LLM Dialog Threads with And-Or Recursors and Refiner Oracles

https://github.com/puerrrr/Self-Paced-Adversarial-Training

공식 코드

Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting

https://github.com/puredefence/advbench4text

공식 코드

Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks

https://github.com/pytorch/fairseq

공식 코드

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/pytorch/fairseq/tree/main/examples/data2vec

공식 코드

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

https://github.com/qijimrc/robustoie

공식 코드

Syntactically Robust Training on Partially-Observed Data for Open Information Extraction

https://github.com/qiongwu86/semantic-aware-resource-management-for-c-v2x-platooning-via-multi-agent-reinforcement-learning

공식 코드

Semantic-Aware Resource Management for C-V2X Platooning via Multi-Agent Reinforcement Learning

https://github.com/rabeehk/compacter

공식 코드

Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning

https://github.com/racai-ai/romanian-distilbert

공식 코드

Distilling the Knowledge of Romanian BERTs Using Multiple Teachers

https://github.com/raphael-sch/HC_Sentence_Summarization

공식 코드

Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction

https://github.com/rashad101/rome

공식 코드

RoMe: A Robust Metric for Evaluating Natural Language Generation

https://github.com/rdenaux/acred

공식 코드

Linked Credibility Reviews for Explainable Misinformation Detection

https://github.com/recombee/beeformer

공식 코드

beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems

https://github.com/reinforest-team/reinforest

공식 코드

REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models

https://github.com/rhymesg/SRNN

공식 코드

Scalable Learning With a Structural Recurrent Neural Network for Short-Term Traffic Prediction

https://github.com/richermans/AudioCaption

공식 코드

Audio Caption in a Car Setting with a Sentence-Level Loss

https://github.com/rohitrai11/application-specific-compression-of-deep-learning-models

공식 코드

Application Specific Compression of Deep Learning Models

https://github.com/rongchengtu1/uhscm

공식 코드

Unsupervised Hashing with Semantic Concept Mining

https://github.com/ruathudo/tfw2v

공식 코드

TFW2V: An Enhanced Document Similarity Method for the Morphologically Rich Finnish Language

https://github.com/ruc-wjyu/iot-match

공식 코드

Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction

https://github.com/rucaibox/dclr

공식 코드

Debiased Contrastive Learning of Unsupervised Sentence Representations

https://github.com/rui-qian/read

공식 코드

Reasoning to Attend: Try to Understand How <SEG> Token Works

https://github.com/rulegreen/cue-cot

공식 코드

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

https://github.com/rulegreen/dialogue_cot

공식 코드

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

https://github.com/ruocwang/mixture-of-prompts

공식 코드

One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts

https://github.com/rupakdas18/fake-news-detection-after-llm-laundering

공식 코드

Fake News Detection After LLM Laundering: Measurement and Explanation

https://github.com/sara-rajaee/multilingual-isotropy

공식 코드

An Isotropy Analysis in the Multilingual BERT Embedding Space

https://github.com/satoshi-kosugi/powerful-attention

공식 코드

Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization

https://github.com/sayeh1994/medical-corpus-semantic-similarity-evaluation

공식 코드

Semantic Textual Similarity Assessment in Chest X-ray Reports Using a Domain-Specific Cosine-Based Metric

https://github.com/schen149/sub-sentence-encoder

공식 코드

Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations

https://github.com/sczwangxiao/radar-mm2022

공식 코드

Micro-video Tagging via Jointly Modeling Social Influence and Tag Relation

https://github.com/semantic-textual-relatedness/semantic_relatedness_semeval2024

공식 코드

SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages

https://github.com/sense-gvt/sncse

공식 코드

SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples

https://github.com/sgoel97/neurips-embedding-positional-bias

공식 코드

Quantifying Positional Biases in Text Embedding Models

https://github.com/sh0416/clrcmd

공식 코드

Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning

https://github.com/shanzhenren/PLE

공식 코드

Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.