Papers with Code 아카이브

Natural Language Understanding

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 6
보존된 평가 기록: 42

Natural Language Understanding is an important field of Natural Language Processing which contains various tasks such as text classification, natural language inference and story comprehension. Applications enabled by natural language understanding range from question answering to automated reasoning.

Source: Find a Reasonable Ending for Stories: Does Logic Relation Help the Story Cloze Test?

코드

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

https://github.com/stanford-futuredata/ColBERT

공식 코드

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

https://github.com/stephanieschoch/ts-dshapley

공식 코드

Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values

https://github.com/sufianj/fast-camembert

공식 코드

Fine-tuning BERT-based models for Plant Health Bulletin Classification

https://github.com/sweetalyssum/Seq2Seq-DU

공식 코드

A Sequence-to-Sequence Approach to Dialogue State Tracking

https://github.com/synapse-developpement/DiscEval

공식 코드

A Pragmatics-Centered Evaluation Framework for Natural Language Understanding

https://github.com/synapse-developpement/pragmeval

공식 코드

A Pragmatics-Centered Evaluation Framework for Natural Language Understanding

https://github.com/syoung7388/ccl

공식 코드

Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding

https://github.com/sz128/few_shot_slot_tagging_and_NER

공식 코드

Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding

https://github.com/szeider/mcp-solver

공식 코드

MCP-Solver: Integrating Language Models with Constraint Programming Systems

https://github.com/tan92hl/complex-question-answering-evaluation-of-chatgpt

공식 코드

Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family

https://github.com/tan92hl/complex-question-answering-evaluation-of-gpt-family

공식 코드

Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family

https://github.com/tau-nlp/zero_scrolls

공식 코드

ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding

https://github.com/technion-cs-nlp/bias-probing

공식 코드

Debiasing Methods in Natural Language Understanding Make Bias More Accessible

https://github.com/tensorflow/models

공식 코드

Neural Architecture Search with Reinforcement Learning

https://github.com/tensorflow/tensor2tensor

공식 코드

Attention Is All You Need

https://github.com/terryqj0107/RiSAWOZ

공식 코드

RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling

https://github.com/text-machine-lab/xword_benchmark

공식 코드

Down and Across: Introducing Crossword-Solving as a New NLP Benchmark

https://github.com/thibaultdouzon/long-range-document-transformer

공식 코드

Long-Range Transformer Architectures for Document Understanding

https://github.com/thomason-jesse/grounded_dialog_agent

공식 코드

Improving Grounded Natural Language Understanding through Human-Robot Dialog

https://github.com/thu-coai/ConvLab-2

공식 코드

Robustness Testing of Language Understanding in Task-Oriented Dialog

https://github.com/thu-coai/LAUG

공식 코드

Robustness Testing of Language Understanding in Task-Oriented Dialog

https://github.com/thu-keg/chatlog

공식 코드

ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time

https://github.com/thu-keg/maven-argument

공식 코드

MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation

https://github.com/thu-ml/lm-calibration

공식 코드

Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models

https://github.com/thudm/efficient-head-finetuning

공식 코드

Parameter-Efficient Tuning Makes a Good Classification Head

https://github.com/thuiar/textoir

공식 코드

Learning Discriminative Representations and Decision Boundaries for Open Intent Detection

https://github.com/thunlp-mt/dbkd-plm

공식 코드

Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models

https://github.com/thunlp/Prompt-Transferability

공식 코드

On Transferability of Prompt Tuning for Natural Language Processing

https://github.com/thunlp/dect

공식 코드

Decoder Tuning: Efficient Language Understanding as Decoding

https://github.com/tianhongzxy/qaap

공식 코드

Question Answering as Programming for Solving Time-Sensitive Questions

https://github.com/tigerchen52/gladis

공식 코드

GLADIS: A General and Large Acronym Disambiguation Benchmark

https://github.com/timoschick/fewglue

공식 코드

It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners

https://github.com/timoschick/pet

공식 코드

It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners

https://github.com/tingofurro/headline_grouping

공식 코드

News Headline Grouping as a Challenging NLU Task

https://github.com/tjunlp-lab/awesome-llm-safety-papers

공식 코드

Large Language Model Safety: A Holistic Survey

https://github.com/trapoom555/language-model-sts-cft

공식 코드

Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning

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