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/jaabmar/cp_fuse
공식 코드Copyright-Protected Language Generation via Adaptive Model Fusion
https://github.com/jackferrellncsu/drums-nlp-codesnapshot
공식 코드Conformal prediction for text infilling and part-of-speech prediction
https://github.com/jackjyzhang/pcfg-nl-interface
공식 코드PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation
https://github.com/jacklishufan/lavida
공식 코드LaViDa: A Large Diffusion Language Model for Multimodal Understanding
https://github.com/jacklishufan/omniflows
공식 코드OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
https://github.com/jacklxc/StandAloneSpellingCorrection
공식 코드https://github.com/jacklxc/cts4citationtextgeneration
공식 코드https://github.com/jacklxc/ms.wow
공식 코드A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
https://github.com/jacksonchen1998/Empowering-NLG
공식 코드Empowering NLG: Offline Reinforcement Learning for Informal Summarization in Online Domains
https://github.com/jacob-parnell-rozetta/longformer_coverage
공식 코드A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization
https://github.com/jacobandreas/pragma
공식 코드Reasoning About Pragmatics with Neural Listeners and Speakers
https://github.com/jadohu/LANTERN
공식 코드https://github.com/jainsameer06/ice
공식 코드Multi-Dimensional Evaluation of Text Summarization with In-Context Learning
https://github.com/james-flemings/dp_compress
공식 코드Differentially Private Knowledge Distillation via Synthetic Text Generation
https://github.com/jamesHargreaves12/incremental_beam_manipulation
공식 코드Incremental Beam Manipulation for Natural Language Generation
https://github.com/janenie/espn-nba-data
공식 코드Operations Guided Neural Networks for High Fidelity Data-To-Text Generation
https://github.com/jcyk/gtos
공식 코드https://github.com/jcyk/skeleton-to-response
공식 코드Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
https://github.com/jd-ai-research-nlp/sgg
공식 코드SGG: Learning to Select, Guide, and Generate for Keyphrase Generation
https://github.com/jeffhj/cdm
공식 코드Understanding Jargon: Combining Extraction and Generation for Definition Modeling
https://github.com/jeknov/RankME
공식 코드RankME: Reliable Human Ratings for Natural Language Generation
https://github.com/jeremyleiliu/xlingudial
공식 코드https://github.com/jfzhouyoo/case
공식 코드CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
https://github.com/jhcircle/less-is-more
공식 코드https://github.com/jhu-clsp/ettin-encoder-vs-decoder
공식 코드https://github.com/jhuapl-fomo/burst-sampling
공식 코드To Burst or Not to Burst: Generating and Quantifying Improbable Text
https://github.com/jiacheng-xu/lattice-generation
공식 코드https://github.com/jiacheng-xu/text-sum-uncertainty
공식 코드Understanding Neural Abstractive Summarization Models via Uncertainty
https://github.com/jiachengli1995/ucepic
공식 코드https://github.com/jiachenwestlake/oodpl
공식 코드Generalizing Reward Modeling for Out-of-Distribution Preference Learning
https://github.com/jiahechen2002/dlc
공식 코드Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration
https://github.com/jiahuei/sparse-image-captioning
공식 코드https://github.com/jialin-yu/latent-sequence-paraphrase
공식 코드Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation
https://github.com/jianguda/afm4acs
공식 코드https://github.com/jianxiangyu/llm4ng
공식 코드Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.