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/google-research/google-research
공식 코드Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach
https://github.com/google-research/google-research/tree/master/etcsum
공식 코드Stepwise Extractive Summarization and Planning with Structured Transformers
https://github.com/google-research/language
공식 코드https://github.com/google-research/lasertagger
공식 코드https://github.com/google-research/longt5
공식 코드LongT5: Efficient Text-To-Text Transformer for Long Sequences
https://github.com/google-research/true
공식 코드https://github.com/google-research/url-nlp
공식 코드TaTa: A Multilingual Table-to-Text Dataset for African Languages
https://github.com/google/storybench
공식 코드StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
https://github.com/goru001/inltk
공식 코드https://github.com/gptutor/gptutor-extension
공식 코드GPTutor: a ChatGPT-powered programming tool for code explanation
https://github.com/gringham/bmx
공식 코드BMX: Boosting Natural Language Generation Metrics with Explainability
https://github.com/gringham/explainable-metrics-machine-translation
공식 코드Towards Explainable Evaluation Metrics for Natural Language Generation
https://github.com/gringham/prexme
공식 코드https://github.com/grmarco/the-reader-is-the-metric
공식 코드https://github.com/gsarti/ETC-NLG
공식 코드ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation
https://github.com/gsarti/it5
공식 코드IT5: Text-to-text Pretraining for Italian Language Understanding and Generation
https://github.com/gsoykan/comics_text_plus
공식 코드A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition
https://github.com/gt-salt/positive-frames
공식 코드https://github.com/gtfintechlab/kg-qagen
공식 코드https://github.com/guangyliu/EISL
공식 코드Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
https://github.com/guangyliu/latentops
공식 코드https://github.com/gunny97/DEBATE
공식 코드DEBATE: Devil's Advocate-Based Assessment and Text Evaluation
https://github.com/guokan-shang/ami-and-icsi-corpora
공식 코드https://github.com/guokan-shang/elitr-minuting-corpus
공식 코드https://github.com/guopeiming/E2E_PSDG
공식 코드An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation
https://github.com/guxd/c-dnpg
공식 코드Continuous Decomposition of Granularity for Neural Paraphrase Generation
https://github.com/gximinglu/ipa
공식 코드Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
https://github.com/gximinglu/quark
공식 코드Quark: Controllable Text Generation with Reinforced Unlearning
https://github.com/gyxxyg/trace
공식 코드TRACE: Temporal Grounding Video LLM via Causal Event Modeling
https://github.com/h-shahidi/2birds-gen
공식 코드https://github.com/h2oai/h2o-llmstudio
공식 코드https://github.com/ha-lins/DTG-SI
공식 코드https://github.com/ha-lins/GEML-MDG
공식 코드Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
https://github.com/hackerchenzhuo/LaKo
공식 코드LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection
https://github.com/haikangdeng/RAD
공식 코드Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.