https://github.com/tsinghua-fib-lab/citygpt
공식 코드CityGPT: Empowering Urban Spatial Cognition of 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/tuetschek/e2e-cleaning
공식 코드Semantic Noise Matters for Neural Natural Language Generation
https://github.com/tuetschek/ratpred
공식 코드Referenceless Quality Estimation for Natural Language Generation
https://github.com/tuhinjubcse/enthymemesemnlp2021
공식 코드Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models
https://github.com/tum-ai/number-token-loss
공식 코드Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models
https://github.com/turboLJY/CapsGNN-Review-Generation
공식 코드Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network
https://github.com/turboLJY/Coarse-to-Fine-Review-Generation
공식 코드Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
https://github.com/turingmotors/nuscenes-mqa
공식 코드https://github.com/tushar117/Transformer-Models-for-Text-Coherence-Assessment
공식 코드https://github.com/tushar117/xalign
공식 코드XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages
https://github.com/twidddj/tokmangan
공식 코드Token Manipulation Generative Adversarial Network for Text Generation
https://github.com/twinters/gitta
공식 코드Discovering Textual Structures: Generative Grammar Induction using Template Trees
https://github.com/twinters/torfs-bot
공식 코드Generating Philosophical Statements using Interpolated Markov Models and Dynamic Templates
https://github.com/txsun1997/metric-fairness
공식 코드BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
https://github.com/tylerachang/goldfish
공식 코드https://github.com/tyliupku/wiki2bio
공식 코드Table-to-text Generation by Structure-aware Seq2seq Learning
https://github.com/tyxsspa/anytext
공식 코드https://github.com/tyxsspa/anytext2
공식 코드AnyText2: Visual Text Generation and Editing With Customizable Attributes
https://github.com/ubc-nlp/arastories
공식 코드Arabic Automatic Story Generation with Large Language Models
https://github.com/ubc-nlp/cheetah
공식 코드Cheetah: Natural Language Generation for 517 African Languages
https://github.com/ubc-vision/make-a-story
공식 코드Make-A-Story: Visual Memory Conditioned Consistent Story Generation
https://github.com/uber-research/FSDM
공식 코드https://github.com/uber-research/PPLM
공식 코드Plug and Play Language Models: A Simple Approach to Controlled Text Generation
https://github.com/ucfnlp/cascaded-summ
공식 코드A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion
https://github.com/ucfnlp/endorser-summ
공식 코드Modeling Endorsement for Multi-Document Abstractive Summarization
https://github.com/ucfnlp/multidoc_summarization
공식 코드Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
https://github.com/ucfnlp/summarization-dpp-capsnet
공식 코드https://github.com/ucfnlp/summarization-sing-pair-mix
공식 코드Scoring Sentence Singletons and Pairs for Abstractive Summarization
https://github.com/ucla-starai/gelato
공식 코드https://github.com/uclaml/dndm
공식 코드Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
https://github.com/uclanlp/paraamr
공식 코드ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation
https://github.com/uclanlp/pip
공식 코드PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation
https://github.com/uclanlp/synpg
공식 코드Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs
https://github.com/uds-lsv/author-profiling-prevention-bt
공식 코드Preventing Author Profiling through Zero-Shot Multilingual Back-Translation
https://github.com/uds-lsv/llm_eval_pi-spin
공식 코드Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?
https://github.com/ufal/nlgi_eval
공식 코드Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.