Text Summarization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 12
- 평가표
- 37
- 보존된 평가 기록
- 233
Text Summarization is a natural language processing (NLP) task that involves condensing a lengthy text document into a shorter, more compact version while still retaining the most important information and meaning. The goal is to produce a summary that accurately represents the content of the original text in a concise form.
There are different approaches to text summarization, including extractive methods that identify and extract important sentences or phrases from the text, and abstractive methods that generate new text based on the content of the original text.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/mayurnewase/Translation
https://github.com/megagonlabs/llm-longeval
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
https://github.com/meghu2791/DeepLearningModels
Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
https://github.com/mehdibenamorr/Token-Positional-Bias
https://github.com/mehdibenamorr/bert-positional-bias-ner
https://github.com/meizi1114/bert
https://github.com/mhamedLmarbouh/Attention-is-all-you-need
https://github.com/mhaseeb123/DeepMSim
https://github.com/michael-wzhu/mpnet_zh
MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/microcoder-py/attn-is-all-you-need
https://github.com/microsoft/MPNet
MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/microsoft/Table-Pretraining
https://github.com/microsoft/ar2
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
https://github.com/microsoft/dialoglm
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
https://github.com/microsoft/fastseq
https://github.com/microsoft/onnxruntime-training-examples
https://github.com/milmor/GPT
https://github.com/mim-solutions/bert_for_longer_texts
https://github.com/mim-solutions/roberta_for_longer_texts
https://github.com/mindspore-ai/models/blob/master/research/nlp/gpt2
https://github.com/mindspore-ai/models/tree/master/official/nlp/mass
MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/mindspore-ai/models/tree/master/official/nlp/pangu_alpha
https://github.com/mindspore-ai/models/tree/master/official/nlp/transformer
https://github.com/mindspore-courses/Deep-Tutorials-for-MindSpore
https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/SelfAttention.py
https://github.com/ming024/FastSpeech2
https://github.com/minimaxir/gpt-2-simple
https://github.com/mithunpaul08/bert_tensorflow
https://github.com/mitran27/Attention-is-all-you-Need
https://github.com/modelscope/modelscope
https://github.com/moein-shariatnia/Pix2Seq
https://github.com/monimoyd/NLPEnglishToPythonCodeUsingTransformer
https://github.com/monimoyd/NLPMachineTranslationUsingTransformer
https://github.com/monologg/kobigbird
https://github.com/moon23k/Scheduled_Sampling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.