Papers with Code 아카이브

Text Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 25
평가표: 155
보존된 평가 기록: 54

Text Generation is the task of generating text with the goal of appearing indistinguishable to human-written text. This task is more formally known as "natural language generation" in the literature.

Text generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include BART, GPT and other GAN-based approaches. Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU.

Further readings:

<span style="color:grey; opacity: 0.6">( Image credit: Adversarial Ranking for Language Generation )</span>

코드

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

https://github.com/zhudotexe/fireball

공식 코드

FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information

https://github.com/zhuohanx/deltascore

공식 코드

DeltaScore: Fine-Grained Story Evaluation with Perturbations

https://github.com/zhuyunqi96/LoraLPrun

공식 코드

Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling

https://github.com/zhwl2117/InstructCIR

공식 코드

Compositional Image Retrieval via Instruction-Aware Contrastive Learning

https://github.com/zhyack/SCC

공식 코드

Automated Chess Commentator Powered by Neural Chess Engine

https://github.com/zichenwen1/dija

공식 코드

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

https://github.com/zide05/mtg

공식 코드

MTG: A Benchmark Suite for Multilingual Text Generation

https://github.com/zihao-wang/rots

공식 코드

Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics

https://github.com/zihuaevan/acfmodel

공식 코드

Adaptively Clustering Neighbor Elements for Image-Text Generation

https://github.com/zijian678/FreeCtrl

공식 코드

FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation

https://github.com/zijian678/tdd

공식 코드

Unveiling and Manipulating Prompt Influence in Large Language Models

https://github.com/zipjiang/core

공식 코드

Core: Robust Factual Precision with Informative Sub-Claim Identification

https://github.com/ziweiji/Internal_States_Reveal_Hallucination

공식 코드

LLM Internal States Reveal Hallucination Risk Faced With a Query

https://github.com/zjlin2oo1/igd

공식 코드

IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation

https://github.com/zjr2000/gvl

공식 코드

Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos

https://github.com/zjs123/DTGB

공식 코드

DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs

https://github.com/zjunlp/DeepKE/tree/main/example/ner/cross

공식 코드

One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER

https://github.com/zjunlp/deepke

공식 코드

One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER

https://github.com/zjunlp/mol-instructions

공식 코드

Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

https://github.com/zjunlp/unlearn

공식 코드

ReLearn: Unlearning via Learning for Large Language Models

https://github.com/zli12321/qa_metrics

공식 코드

PEDANTS: Cheap but Effective and Interpretable Answer Equivalence

https://github.com/zlin7/contextsl

공식 코드

Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation

https://github.com/zlin7/uq-nlg

공식 코드

Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models

https://github.com/zlinao/VGLM

공식 코드

Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning

https://github.com/zlkqz/auto_eval

공식 코드

TALEC: Teach Your LLM to Evaluate in Specific Domain with In-house Criteria by Criteria Division and Zero-shot Plus Few-shot

https://github.com/zoeyou/patenteval

공식 코드

PatentEval: Understanding Errors in Patent Generation

https://github.com/zoeyyao27/sirllm

공식 코드

SirLLM: Streaming Infinite Retentive LLM

https://github.com/zohrehghaderi/vasta

공식 코드

Diverse Video Captioning by Adaptive Spatio-temporal Attention

https://github.com/zombbie/entity-synthetic-dataset

공식 코드

Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems

https://github.com/zouharvi/subset2evaluate

공식 코드

How to Select Datapoints for Efficient Human Evaluation of NLG Models?

https://github.com/zurichnlp/mbr

공식 코드

Linear-time Minimum Bayes Risk Decoding with Reference Aggregation

https://github.com/zurichnlp/nmtscore

공식 코드

NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures

https://github.com/zwhong714/adaptive_decoding

공식 코드

Improving Open-Ended Text Generation via Adaptive Decoding

https://github.com/zwhong714/penalty_decoding

공식 코드

Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation

https://github.com/zxy556677/easygen

공식 코드

EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs

https://github.com/zyang-ur/onestage_grounding

공식 코드

Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation

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