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/c-juhwan/adverb-deletion-aug

공식 코드

Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletion

https://github.com/caisa-lab/llms-real-world-noise-robustness

공식 코드

Exploring Robustness of Multilingual LLMs on Real-World Noisy Data

https://github.com/cambridgeltl/visual-spatial-reasoning

공식 코드

Visual Spatial Reasoning

https://github.com/cather-chen/logical-reasoning-graph

공식 코드

Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension

https://github.com/cbluebenchmark/cblue

공식 코드

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark

https://github.com/cciiplab/persona_extend

공식 코드

Improving Personality Consistency in Conversation by Persona Extending

https://github.com/cestwc/universal-evasion

공식 코드

Universal Evasion Attacks on Summarization Scoring

https://github.com/chadlzx/nsp_qa

공식 코드

A Neural-Symbolic Approach to Natural Language Understanding

https://github.com/chenyiqun/mmoa-rag

공식 코드

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

https://github.com/chrisc36/autobias

공식 코드

Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles

https://github.com/chrisc36/debias

공식 코드

Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases

https://github.com/circle-ming/multicsr

공식 코드

Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning

https://github.com/cjf00000/StatQuant

공식 코드

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks

https://github.com/clarin-pl/chatgpt-evaluation-01-2023

공식 코드

ChatGPT: Jack of all trades, master of none

https://github.com/claudiogreco/coling18-gte

공식 코드

Grounded Textual Entailment

https://github.com/clement-lef/pr-ent

공식 코드

Rethinking the Event Coding Pipeline with Prompt Entailment

https://github.com/clip-vil/CLIP-ViL

공식 코드

How Much Can CLIP Benefit Vision-and-Language Tasks?

https://github.com/clovaai/ssmix

공식 코드

SSMix: Saliency-Based Span Mixup for Text Classification

https://github.com/cnai-lab/qlatent

공식 코드

Assessment and manipulation of latent constructs in pre-trained language models using psychometric scales

https://github.com/coling2022-depro/depro

공식 코드

Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective

https://github.com/compai-lab/miccai-2024-junli

공식 코드

Language Models Meet Anomaly Detection for Better Interpretability and Generalizability

https://github.com/cooelf/SemBERT

공식 코드

Semantics-aware BERT for Language Understanding

https://github.com/copenlu/X-MAML

공식 코드

Zero-Shot Cross-Lingual Transfer with Meta Learning

https://github.com/copenlu/fever-adversarial-attacks

공식 코드

Generating Label Cohesive and Well-Formed Adversarial Claims

https://github.com/copenlu/spanex

공식 코드

Explaining Interactions Between Text Spans

https://github.com/cosmaadrian/nli-stress-test

공식 코드

How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics

https://github.com/createmomo/instance-level-reliability

공식 코드

Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks

https://github.com/crherlihy/clinical_nli_artifacts

공식 코드

MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain

https://github.com/csalt-research/llm-based-augmentations-with-effective-data-selection

공식 코드

Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection

https://github.com/csebuetnlp/banglabert

공식 코드

BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla

https://github.com/csitfun/ConTRoL-dataset

공식 코드

Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts

https://github.com/csitfun/logieval

공식 코드

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

https://github.com/ctinfer/nli4pr

공식 코드

Am I eligible? Natural Language Inference for Clinical Trial Patient Recruitment: the Patient's Point of View

https://github.com/cxcscmu/ragviz

공식 코드

RAGViz: Diagnose and Visualize Retrieval-Augmented Generation

https://github.com/cyr19/menli

공식 코드

MENLI: Robust Evaluation Metrics from Natural Language Inference

https://github.com/czy1999/synthrag

공식 코드

An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms

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