Papers with Code 아카이브
Natural Language Inference
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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:
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/skywalker023/pragmatic-consistency
공식 코드https://github.com/skywalkerzhang/Defeasible_Visual_Entailment
공식 코드Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization
https://github.com/slanglab/IndiaPoliceEvents
공식 코드https://github.com/sleeepeer/poisonedrag
공식 코드PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
https://github.com/snowood1/zero-shot-plover
공식 코드Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification
https://github.com/socsys/graphnli
공식 코드GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates
https://github.com/sohojoe/clip_visual-spatial-reasoning
공식 코드https://github.com/songhaoyu/RCDG
공식 코드Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
https://github.com/songrise/mope
공식 코드MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
https://github.com/sonlam1102/vimmrc2
공식 코드A Multiple Choices Reading Comprehension Corpus for Vietnamese Language Education
https://github.com/stanfordnlp/contract-nli-bert
공식 코드ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts
https://github.com/stanfordnlp/spinn
공식 코드https://github.com/stareru/csqa_debertav3
공식 코드https://github.com/stergioscha/oyxoy
공식 코드https://github.com/strong-ai-lab/logical-equivalence-driven-amr-data-augmentation-for-representation-learning
공식 코드Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning
https://github.com/sunipa/On-Measuring-and-Mitigating-Biased-Inferences-of-Word-Embeddings
공식 코드On Measuring and Mitigating Biased Inferences of Word Embeddings
https://github.com/sushmaakoju/acl2023-nlrse-clulab-sicck-dataset
공식 코드Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference
https://github.com/swarnaHub/ConjNLI
공식 코드ConjNLI: Natural Language Inference Over Conjunctive Sentences
https://github.com/symanto-research/few-shot-learning-label-tuning
공식 코드https://github.com/synapse-developpement/DiscEval
공식 코드A Pragmatics-Centered Evaluation Framework for Natural Language Understanding
https://github.com/synapse-developpement/pragmeval
공식 코드A Pragmatics-Centered Evaluation Framework for Natural Language Understanding
https://github.com/szhang42/Calibration_qa
공식 코드Knowing More About Questions Can Help: Improving Calibration in Question Answering
https://github.com/szhang42/uneven_training_data
공식 코드Learning with Different Amounts of Annotation: From Zero to Many Labels
https://github.com/tagoyal/dae-factuality
공식 코드Evaluating Factuality in Generation with Dependency-level Entailment
https://github.com/tanay2001/core
공식 코드CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
https://github.com/taokz/biomedgpt
공식 코드BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks
https://github.com/taoshen58/DiSAN
공식 코드DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
https://github.com/tau-nlp/scrolls
공식 코드SCROLLS: Standardized CompaRison Over Long Language Sequences
https://github.com/technion-cs-nlp/generative-nli
공식 코드A Generative Approach for Mitigating Structural Biases in Natural Language Inference
https://github.com/teddy-li/llm-nli-analysis
공식 코드Sources of Hallucination by Large Language Models on Inference Tasks
https://github.com/tensorflow/lingvo
공식 코드https://github.com/tensorflow/mesh
공식 코드ST-MoE: Designing Stable and Transferable Sparse Expert Models
https://github.com/tensorflow/models/tree/master/official/nlp/projects/mobilebert
공식 코드MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
https://github.com/theo2023/coco-bert-longformer
공식 코드Code Comment Inconsistency Detection with BERT and Longformer
https://github.com/thinklab-sjtu/awesome-llm4eda
공식 코드LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.