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/ltu-machine-learning/bipolswedish

공식 코드

Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets

https://github.com/luffycodes/automated-long-answer-grading

공식 코드

Automated Long Answer Grading with RiceChem Dataset

https://github.com/luka-group/NLI_as_Indirect_Supervision

공식 코드

Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?

https://github.com/luka-group/lite

공식 코드

Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference

https://github.com/lukecq1231/generalized-pooling

공식 코드

Enhancing Sentence Embedding with Generalized Pooling

https://github.com/lukecq1231/kim

공식 코드

Neural Natural Language Inference Models Enhanced with External Knowledge

https://github.com/lukecq1231/nli

공식 코드

Enhanced LSTM for Natural Language Inference

https://github.com/luohongyin/esp

공식 코드

Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning

https://github.com/luoyuanlab/clinical-longformer

공식 코드

Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences

https://github.com/lxucs/multilingual-sl

공식 코드

Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation

https://github.com/m-almagro-cadiz/lea

공식 코드

LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias

https://github.com/m43/focal-loss-against-heuristics

공식 코드

Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference

https://github.com/machelreid/paradise

공식 코드

PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining

https://github.com/macleginn/semantic-subspaces-code

공식 코드

Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing

https://github.com/mainlp/litex

공식 코드

LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference

https://github.com/mainlp/mjd-estimator

공식 코드

"Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?

https://github.com/manga-uofa/epr

공식 코드

Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

https://github.com/marbr987/hypothesis_driven_analysis_of_self_rationalising_models

공식 코드

A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models

https://github.com/mariomeissner/AmbiNLI

공식 코드

Embracing Ambiguity: Shifting the Training Target of NLI Models

https://github.com/masashi-y/abduction_kbc

공식 코드

Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference

https://github.com/matejklemen/paraphrase-nli

공식 코드

Extracting and filtering paraphrases by bridging natural language inference and paraphrasing

https://github.com/matnlp/smedbert

공식 코드

SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining

https://github.com/mbouadeus/news-headline-event-linking

공식 코드

An Evaluation Framework for Mapping News Headlines to Event Classes in a Knowledge Graph

https://github.com/mbzuai-nlp/lamini-lm

공식 코드

LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions

https://github.com/michael-mersinias/nli_text_generation

공식 코드

For Generated Text, Is NLI-Neutral Text the Best Text?

https://github.com/michael-wzhu/PromptCBLUE

공식 코드

PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain

https://github.com/microsoft/DeBERTa

공식 코드

DeBERTa: Decoding-enhanced BERT with Disentangled Attention

https://github.com/microsoft/TaxiNLI

공식 코드

TaxiNLI: Taking a Ride up the NLU Hill

https://github.com/microsoft/batchprompt

공식 코드

BatchPrompt: Accomplish more with less

https://github.com/microsoft/conli_hallucination

공식 코드

Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations

https://github.com/microsoft/hi-ml/tree/main/hi-ml-multimodal

공식 코드

Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing

https://github.com/microsoft/promptbench

공식 코드

PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts

https://github.com/microsoft/taxixnli

공식 코드

Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer Performance

https://github.com/midas-research/data-free-uats

공식 코드

MINIMAL: Mining Models for Data Free Universal Adversarial Triggers

https://github.com/minieggz/effiara

공식 코드

Efficient Annotator Reliability Assessment and Sample Weighting for Knowledge-Based Misinformation Detection on Social Media

https://github.com/minieggz/ruc-misinfo

공식 코드

Efficient Annotator Reliability Assessment and Sample Weighting for Knowledge-Based Misinformation Detection on Social Media

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