Constituency Parsing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 4
- 보존된 평가 기록
- 40
Constituency parsing aims to extract a constituency-based parse tree from a sentence that represents its syntactic structure according to a phrase structure grammar.
Example:
Sentence (S)
|
+-------------+------------+
| |
Noun (N) Verb Phrase (VP)
| |
John +-------+--------+
| |
Verb (V) Noun (N)
| |
sees Bill
Recent approaches convert the parse tree into a sequence following a depth-first traversal in order to be able to apply sequence-to-sequence models to it. The linearized version of the above parse tree looks as follows: (S (N) (VP V N)).
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yanqi1811/attention-is-all-you-need
https://github.com/yeeeqichen/Bert
https://github.com/yiyc-kor/bert-study
https://github.com/ykrmm/ICLR_2020
https://github.com/ykrmm/TREMBA
https://github.com/yoongtr/Grammar-Error-Correction-with-OpenNMT-tf
https://github.com/ypeleg/MinimalIsAllYouNeed
https://github.com/yuanmu97/secure-transformer-inference
https://github.com/yueyongjiao/Transformer-Contextual
https://github.com/yueyongjiao/attention_is_all_you_need_pytorch
https://github.com/yuhangT/tf_bert
https://github.com/yumoh/speech-keras
https://github.com/yv/rnng
https://github.com/yydai/bert_test
https://github.com/yzhangcs/parser
Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference
https://github.com/zankner/Transformer
https://github.com/zapplea/bert
https://github.com/zer0sh0t/artificial_intelligence/tree/master/transformer
https://github.com/zhang-huihui/git-repository
https://github.com/zhangbo2008/best_pytorch_transformer
https://github.com/zhangzibin/char-rnn-chinese
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
https://github.com/zi-lin/on-lstm-tensorflow
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
https://github.com/zipeiyang/DeepSpeechRecognition
https://github.com/zsweet/BERT_zsw
https://github.com/zysite/post
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.