https://github.com/kpkqwq/lspg
공식 코드Multilingual Lexical Simplification via Paraphrase Generation
Papers with Code 아카이브
Text Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/krafton-ai/LaPael
공식 코드Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
https://github.com/krishnap25/mauve
공식 코드MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
https://github.com/krishnap25/mauve-experiments
공식 코드MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
https://github.com/kristylht/Human-LLM-Paraphrase-Collection-HLPC
공식 코드Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection
https://github.com/krystalan/chatgpt_as_nlg_evaluator
공식 코드https://github.com/kssteven418/biglittledecoder
공식 코드https://github.com/kstanghere/gendercare-ccs24
공식 코드https://github.com/ktlktl/eval-gcsc
공식 코드Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction
https://github.com/ktxlh/TrajGPT
공식 코드https://github.com/kushalarora/quantifying_exposure_bias
공식 코드https://github.com/kyriemao/llm4cs
공식 코드https://github.com/kyriemao/llmcs
공식 코드https://github.com/l-zhe/btmpg
공식 코드Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
https://github.com/l-zhe/corpg
공식 코드Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering
https://github.com/l-zhe/vipg
공식 코드https://github.com/laihuiyuan/Pre-trained-formality-transfer
공식 코드Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
https://github.com/laihuiyuan/eval-formality-transfer
공식 코드Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
https://github.com/laihuiyuan/mflag
공식 코드https://github.com/laihuiyuan/multilingual-tst
공식 코드Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
https://github.com/laituan245/el-dockers
공식 코드Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking
https://github.com/lancopku/AMM
공식 코드https://github.com/lancopku/Augmented_Data_for_FST
공식 코드https://github.com/lancopku/DPGAN
공식 코드https://github.com/lancopku/Pivot
공식 코드Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation
https://github.com/lancopku/Skeleton-Based-Generation-Model
공식 코드A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
https://github.com/lancopku/WEAN
공식 코드https://github.com/lancopku/unpaired-sentiment-translation
공식 코드Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
https://github.com/land-fbk/prodigy-dataset
공식 코드https://github.com/langus0/critic-aware-decoding
공식 코드Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation
https://github.com/laohur/gur
공식 코드https://github.com/lapalme/pyrealb
공식 코드https://github.com/laquabe/know3rag
공식 코드Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering
https://github.com/lara-martin/ASTER
공식 코드Event Representations for Automated Story Generation with Deep Neural Nets
https://github.com/lara-martin/StoryPlot-RewardShaping
공식 코드Controllable Neural Story Plot Generation via Reward Shaping
https://github.com/lashoun/hanna-benchmark-asg
공식 코드Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.