https://github.com/danielabweiss/qa-align
공식 코드QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions
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/danielfperez/castillo
공식 코드CASTILLO: Characterizing Response Length Distributions of Large Language Models
https://github.com/dannigt/mid-align
공식 코드Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
https://github.com/dapangliu/lamer
공식 코드Non-Parallel Text Style Transfer with Self-Parallel Supervision
https://github.com/dapascual/DirectedBeamSearch
공식 코드Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation
https://github.com/dapascual/k2t
공식 코드https://github.com/dapurv5/alignmark
공식 코드Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
https://github.com/darsh10/Nutribullets
공식 코드Nutri-bullets: Summarizing Health Studies by Composing Segments
https://github.com/darthreca/segmentation-losses-nlp
공식 코드Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning
https://github.com/datascienceuibk/hintqa
공식 코드Exploring Hint Generation Approaches in Open-Domain Question Answering
https://github.com/datascienceuibk/triviahg
공식 코드TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions
https://github.com/dayihengliu/Fine-Grained-Style-Transfer
공식 코드Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
https://github.com/dayihengliu/KeyMultiHeadline
공식 코드Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
https://github.com/dayihengliu/Mu-Forcing-VRAE
공식 코드mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation
https://github.com/dayihengliu/Text-Infilling-Gradient-Search
공식 코드TIGS: An Inference Algorithm for Text Infilling with Gradient Search
https://github.com/dbrainio/cyrillichandwritingpoc
공식 코드Data Generation for Post-OCR correction of Cyrillic handwriting
https://github.com/dcu-nlg/dcu-nlg-pbn
공식 코드https://github.com/ddddwy/Reinforce-Paraphrase-Generation
공식 코드An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation
https://github.com/ddindidu/atomic-persona-evaluation
공식 코드https://github.com/debugml/adversarial_prompting
공식 코드https://github.com/declare-lab/MELD
공식 코드MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
https://github.com/declare-lab/dialogue-understanding
공식 코드https://github.com/declare-lab/red-instruct
공식 코드Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
https://github.com/declare-lab/wikides
공식 코드WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions from Paragraphs
https://github.com/declipsonator/gptzzzs
공식 코드Authorship Obfuscation in Multilingual Machine-Generated Text Detection
https://github.com/deekshavarshney/cdialog
공식 코드CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog Generation
https://github.com/deekshavarshney/cntf
공식 코드Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation
https://github.com/deep-spin/crest
공식 코드CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
https://github.com/deep-spin/infinite-former
공식 코드https://github.com/deep-spin/sparse_text_generation
공식 코드https://github.com/deep-symbolic-mathematics/TPSR
공식 코드https://github.com/deepmind/card2code
공식 코드https://github.com/deepmind/deepmind-research
공식 코드https://github.com/deepmind/deepmind-research/tree/master/wikigraphs
공식 코드WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
https://github.com/deepmind/dsprites-dataset
공식 코드https://github.com/deqiankong/spi
공식 코드Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.