paper-with-me

홈 › Papers

Have Attention Heads in BERT Learned Constituency Grammar?

2021-02-16 · EACL 2021 2 · Ziyang Luo

With the success of pre-trained language models in recent years, more and more researchers focus on opening the "black box" of these models. Following this interest, we carry out a qualitative and quantitative analysis of constituency grammar in attention heads of BERT and RoBERTa. We employ the syntactic distance method to extract implicit constituency grammar from the attention weights of each head. Our results show that there exist heads that can induce some grammar types much better than baselines, suggesting that some heads act as a proxy for constituency grammar. We also analyze how attention heads' constituency grammar inducing (CGI) ability changes after fine-tuning with two kinds of tasks, including sentence meaning similarity (SMS) tasks and natural language inference (NLI) tasks. Our results suggest that SMS tasks decrease the average CGI ability of upper layers, while NLI tasks increase it. Lastly, we investigate the connections between CGI ability and natural language understanding ability on QQP and MNLI tasks.

📄 PDF Abstract BibTeX arXiv:2102.07926

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language InferenceNatural Language UnderstandingQQPSentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Multi-Head Attention 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
WordPiece 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Better heads do not guarantee better binarized constituency parsing

2026-05-27 · Zeyao Qi, Yige Chen, Eitan Klinger, Vivaan Wadhwa 외 arxiv

We revisit punctuation-aware tree binarization for constituency parsing and ask whether dependency-induced headedness improves binary parser supervision. Although learned heads substantially outperform rule-based heads i…

Constituency Parsing

Heads-up! Unsupervised Constituency Parsing via Self-Attention Heads

2020-10-19 · Asian Chapter of the Association for Computational Linguistics 2020 · Bowen Li, Taeuk Kim, Reinald Kim Amplayo, Frank Keller

Transformer-based pre-trained language models (PLMs) have dramatically improved the state of the art in NLP across many tasks. This has led to substantial interest in analyzing the syntactic knowledge PLMs learn. Previou…

Constituency Parsing

Do Transformers Parse while Predicting the Masked Word?

2023-03-14 · Haoyu Zhao, Abhishek Panigrahi, Rong Ge, Sanjeev Arora

Pre-trained language models have been shown to encode linguistic structures, e.g. dependency and constituency parse trees, in their embeddings while being trained on unsupervised loss functions like masked language model…

Constituency ParsingLanguage ModelingLanguage ModellingMasked Language Modeling

ConvBERT: Improving BERT with Span-based Dynamic Convolution

2020-08-06 · NeurIPS 2020 12 · Zi-Hang Jiang, Weihao Yu, Daquan Zhou, Yunpeng Chen 외

Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies on the global self-attention block and th…

Natural Language Understanding

An Empirical Study for Vietnamese Constituency Parsing with Pre-training

2020-10-19 · Tuan-Vi Tran, Xuan-Thien Pham, Duc-Vu Nguyen, Kiet Van Nguyen 외

In this work, we use a span-based approach for Vietnamese constituency parsing. Our method follows the self-attention encoder architecture and a chart decoder using a CKY-style inference algorithm. We present analyses of…

Constituency ParsingDecoderVietnamese DatasetsVietnamese Parsing