mlsanityData to 14 Oct 2026

Investigating Non-local Features for Neural Constituency Parsing

arXiv 2109.12814 ↗First posted 27 Sep 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Thanks to the strong representation power of neural encoders, neural chart-based parsers have achieved highly competitive performance by using local features. Recently, it has been shown that non-local features in CRF structures lead to improvements. In this paper, we investigate injecting non-local features into the training process of a local span-based parser, by predicting constituent n-gram non-local patterns and ensuring consistency between non-local patterns and local constituents. Results show that our simple method gives better results than the self-attentive parser on both PTB and CTB. Besides, our method achieves state-of-the-art BERT-based performance on PTB (95.92 F1) and strong performance on CTB (92.31 F1). Our parser also achieves better or competitive performance in multilingual and zero-shot cross-domain settings compared with the baseline.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 24 of its 42 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

24 of 42 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  3. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  4. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  5. 2016Enhanced LSTM for Natural Language Inferencecited by 200
  6. 2018Constituency Parsing with a Self-Attentive Encodercited by 199
  7. 2018Multilingual Constituency Parsing with Self-Attention and Pre-Trainingcited by 117
  8. 2017A Minimal Span-Based Neural Constituency Parsercited by 59
  9. 2020Fast and Accurate Neural CRF Constituency Parsingcited by 50
  10. 2020Efficient Second-Order TreeCRF for Neural Dependency Parsingcited by 48
  11. 2019Head-Driven Phrase Structure Grammar Parsing on Penn Treebankcited by 43
  12. 2019Neural Extractive Text Summarization with Syntactic Compressioncited by 37
12 more
  1. 2019Hierarchically-Refined Label Attention Network for Sequence Labelingcited by 25
  2. 2017In-Order Transition-based Constituent Parsingcited by 23
  3. 2018What's Going On in Neural Constituency Parsers? An Analysiscited by 22
  4. 2016Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oraclescited by 20
  5. 2018A Tree-based Decoder for Neural Machine Translationcited by 18
  6. 2019Cross-Domain Generalization of Neural Constituency Parserscited by 17
  7. 2020Improving Constituency Parsing with Span Attentioncited by 17
  8. 2020Uncertainty-Aware Label Refinement for Sequence Labelingcited by 11
  9. 2015Neural CRF Parsingcited by 10
  10. 2020Efficient Constituency Parsing by Pointingcited by 7
  11. 2018Two Local Models for Neural Constituent Parsingcited by 6
  12. 2020Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levelscited by 3

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 2.

4 papers.

  1. 2021Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networkscited by 21
  2. 2022Cross-domain Generalization for AMR Parsingcited by 2
  3. 2023Constituency Parsing using LLMscited by 2
  4. 2023Opinion Tree Parsing for Aspect-based Sentiment Analysiscited by 0