Papers with Code 아카이브

Natural Language Inference

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 3
평가표: 43
보존된 평가 기록: 505

Natural language inference (NLI) is the task of determining whether a "hypothesis" is true (entailment), false (contradiction), or undetermined (neutral) given a "premise".

Example:

Premise	Label	Hypothesis
A man inspects the uniform of a figure in some East Asian country.	contradiction	The man is sleeping.
An older and younger man smiling.	neutral	Two men are smiling and laughing at the cats playing on the floor.
A soccer game with multiple males playing.	entailment	Some men are playing a sport.

Approaches used for NLI include earlier symbolic and statistical approaches to more recent deep learning approaches. Benchmark datasets used for NLI include SNLI, MultiNLI, SciTail, among others. You can get hands-on practice on the SNLI task by following this d2l.ai chapter.

Further readings:

Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches

코드

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

https://github.com/d-gurgurov/GrEmLIn-Green-Embeddings-LRLs

공식 코드

GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge

https://github.com/dalab/hyperbolic_nn

공식 코드

Hyperbolic Neural Networks

https://github.com/datngu/nli-artifacts

공식 코드

Dissecting vocabulary biases datasets through statistical testing and automated data augmentation for artifact mitigation in Natural Language Inference

https://github.com/dayihengliu/CRQDA

공식 코드

Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space

https://github.com/declare-lab/CICERO

공식 코드

CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues

https://github.com/declare-lab/CIDER

공식 코드

CIDER: Commonsense Inference for Dialogue Explanation and Reasoning

https://github.com/declare-lab/domadapter

공식 코드

UDApter -- Efficient Domain Adaptation Using Adapters

https://github.com/declare-lab/knot

공식 코드

KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks

https://github.com/declare-lab/sinkhorn-loss

공식 코드

KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks

https://github.com/deep-spin/spectra-rationalization

공식 코드

SPECTRA: Sparse Structured Text Rationalization

https://github.com/dengyang17/OAAG

공식 코드

Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce

https://github.com/dengyang17/tois-page

공식 코드

Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling

https://github.com/deqingfu/scene

공식 코드

SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples

https://github.com/derenlei/factcg

공식 코드

FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data

https://github.com/dericp/syntactic-entailment

공식 코드

Improving Natural Language Inference with a Pretrained Parser

https://github.com/didi/delta

공식 코드

DELTA: A DEep learning based Language Technology plAtform

https://github.com/diego-feijo/bertpt

공식 코드

Mono vs Multilingual Transformer-based Models: a Comparison across Several Language Tasks

https://github.com/dinghanshen/SWEM

공식 코드

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

https://github.com/dirkweissenborn/dual_am_rnn

공식 코드

Neural Associative Memory for Dual-Sequence Modeling

https://github.com/div290/dadee

공식 코드

DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs

https://github.com/dkaushik96/bizarro-data

공식 코드

Learning the Difference that Makes a Difference with Counterfactually-Augmented Data

https://github.com/dkaushik96/counterfactually-augmented-data

공식 코드

Learning the Difference that Makes a Difference with Counterfactually-Augmented Data

https://github.com/dmis-lab/bioasq8b

공식 코드

Transferability of Natural Language Inference to Biomedical Question Answering

https://github.com/dml-qom/FarsTail

공식 코드

FarsTail: A Persian Natural Language Inference Dataset

https://github.com/dmlc/dgl

공식 코드

Star-Transformer

https://github.com/dongxinshuai/ASCC

공식 코드

Towards Robustness Against Natural Language Word Substitutions

https://github.com/dongxinshuai/rift-neurips2021

공식 코드

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

https://github.com/dsgt-arc/checkthat-2025-numerical

공식 코드

DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification

https://github.com/dsn-2024/dsn

공식 코드

Don't Say No: Jailbreaking LLM by Suppressing Refusal

https://github.com/duygua/semeval2024_nli4ct

공식 코드

D-NLP at SemEval-2024 Task 2: Evaluating Clinical Inference Capabilities of Large Language Models

https://github.com/dykang/adventure

공식 코드

AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples

https://github.com/easonnie/ChaosNLI

공식 코드

What Can We Learn from Collective Human Opinions on Natural Language Inference Data?

https://github.com/easonnie/analyze-compositionality-sensitivity-NLI

공식 코드

Analyzing Compositionality-Sensitivity of NLI Models

https://github.com/easonnie/combine-FEVER-NSMN

공식 코드

Combining Fact Extraction and Verification with Neural Semantic Matching Networks

https://github.com/easonnie/multiNLI_encoder

공식 코드

Shortcut-Stacked Sentence Encoders for Multi-Domain Inference

https://github.com/eduard6421/ronli

공식 코드

A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus

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