https://github.com/seungheondoh/lp-music-dialog
공식 코드Music Discovery Dialogue Generation Using Human Intent Analysis and Large Language Models
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/seyoungsong/mugeval
공식 코드MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language
https://github.com/sf-wa-326/phrase-bert-topic-model
공식 코드Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration
https://github.com/sfanxiang/nano
공식 코드Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control
https://github.com/sfeucht/annotation_evaluation
공식 코드A Novel Corpus of Discourse Structure in Humans and Computers
https://github.com/shadowkiller33/parascore
공식 코드https://github.com/shafnehal/samcares
공식 코드https://github.com/shaily99/eecc
공식 코드Extrinsic Evaluation of Cultural Competence in Large Language Models
https://github.com/shailzajolly/fsdt
공식 코드Search and Learn: Improving Semantic Coverage for Data-to-Text Generation
https://github.com/shainarazavi/safe-responsible-llm
공식 코드https://github.com/shalei120/OxCTE
공식 코드Controlling Text Edition by Changing Answers of Specific Questions
https://github.com/shallinan1/steerstyletransfer
공식 코드https://github.com/shangdatalab/smooth-control
공식 코드Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
https://github.com/shanghai-digital-brain-laboratory/bdm-db1
공식 코드https://github.com/shaochenze/scoringruleslm
공식 코드https://github.com/shaojiejiang/ct-loss
공식 코드A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration
https://github.com/shaojintian/power_law_decay
공식 코드https://github.com/shaoshuo-ss/eaaw
공식 코드https://github.com/sharan21/epaae
공식 코드https://github.com/sharif-slpl/se-2024-task-06-shroom
공식 코드SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
https://github.com/shark-nlp/cont
공식 코드https://github.com/sharonlevy/Conspiracy-Theory-Memorization
공식 코드Investigating Memorization of Conspiracy Theories in Text Generation
https://github.com/shawnlimn/ScaleGrad
공식 코드Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation
https://github.com/shawnricecake/fast-car
공식 코드FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
https://github.com/sheffieldnlp/AMR2Text-summ
공식 코드https://github.com/sheikhshafayat/multi-fact
공식 코드Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
https://github.com/shen-chenhui/mred
공식 코드MReD: A Meta-Review Dataset for Structure-Controllable Text Generation
https://github.com/shen-chenhui/sentbs
공식 코드SentBS: Sentence-level Beam Search for Controllable Summarization
https://github.com/shentao-yang/preference_grounded_guidance
공식 코드Preference-grounded Token-level Guidance for Language Model Fine-tuning
https://github.com/shentianxiao/language-style-transfer
공식 코드https://github.com/shentianxiao/text-autoencoders
공식 코드Educating Text Autoencoders: Latent Representation Guidance via Denoising
https://github.com/shikib/fed
공식 코드https://github.com/shikib/usr
공식 코드USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation
https://github.com/shin285/KOMORAN
공식 코드Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja
https://github.com/shininglab/action-controlled-paraphrasing
공식 코드https://github.com/shiquanyang/ns-dial
공식 코드An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.