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/araag2/SemEval2024-Task2

공식 코드

Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation

https://github.com/archiki/receval

공식 코드

ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness

https://github.com/arjun-254/veritas-nli

공식 코드

VERITAS-NLI : Validation and Extraction of Reliable Information Through Automated Scraping and Natural Language Inference

https://github.com/artetxem/esxnli

공식 코드

Translation Artifacts in Cross-lingual Transfer Learning

https://github.com/asaakyan/V-FLUTE

공식 코드

Understanding Figurative Meaning through Explainable Visual Entailment

https://github.com/asaakyan/socnormnli

공식 코드

Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment

https://github.com/asahi417/lm-question-generation

공식 코드

An Empirical Comparison of LM-based Question and Answer Generation Methods

https://github.com/asappresearch/scale-score

공식 코드

Fast and Accurate Factual Inconsistency Detection Over Long Documents

https://github.com/asnijders/multi_source_al

공식 코드

Investigating Multi-source Active Learning for Natural Language Inference

https://github.com/astonzhang/Parameterization-of-Hypercomplex-Multiplications

공식 코드

Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters

https://github.com/asu-apg/vli_sdro

공식 코드

Semantically Distributed Robust Optimization for Vision-and-Language Inference

https://github.com/atticusg/MoNLI

공식 코드

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation

https://github.com/atul04/Explainable-Latent-Structures-Using-Attention

공식 코드

Unsupervised Learning of Explainable Parse Trees for Improved Generalisation

https://github.com/awebson/prompt_semantics

공식 코드

Do Prompt-Based Models Really Understand the Meaning of their Prompts?

https://github.com/azpoliak/hypothesis-only-NLI

공식 코드

Hypothesis Only Baselines in Natural Language Inference

https://github.com/azpoliak/robust-nli

공식 코드

Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference

https://github.com/bangliu/ACS-QG

공식 코드

Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus

https://github.com/batsresearch/bonito

공식 코드

Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation

https://github.com/bbn-e/zs4ie

공식 코드

ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations

https://github.com/bernardoleite/fairytaleqa-translated

공식 코드

FairytaleQA Translated: Enabling Educational Question and Answer Generation in Less-Resourced Languages

https://github.com/bernardoleite/few-shot-prompting-qg-control

공식 코드

On Few-Shot Prompting for Controllable Question-Answer Generation in Narrative Comprehension

https://github.com/bgGLUE/bgglue

공식 코드

bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark

https://github.com/bgglue/bgglue.github.io

공식 코드

bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark

https://github.com/bigai-nlco/docgnre

공식 코드

Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models

https://github.com/billptw/fasttrees

공식 코드

FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding

https://github.com/blcunlp/RTE

공식 코드

Multi-turn Inference Matching Network for Natural Language Inference

https://github.com/blinkdl/chatrwkv

공식 코드

RWKV: Reinventing RNNs for the Transformer Era

https://github.com/blitzprecision/ficle

공식 코드

Neural models for Factual Inconsistency Classification with Explanations

https://github.com/boknilev/nmt-repr-analysis

공식 코드

On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference

https://github.com/boleima/profit

공식 코드

Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding

https://github.com/boschresearch/external-knowledge-explainable-nli

공식 코드

Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings

https://github.com/boun-tabi/NLI-TR

공식 코드

Data and Representation for Turkish Natural Language Inference

https://github.com/brmson/dataset-sts

공식 코드

Sentence Pair Scoring: Towards Unified Framework for Text Comprehension

https://github.com/buaadreamer/easyrag

공식 코드

EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations

https://github.com/bzhangGo/ATR

공식 코드

Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks

https://github.com/bzhangGo/zero

공식 코드

Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks

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