paper-with-me

Papers

Tree Transformer: Integrating Tree Structures into Self-Attention

2019-09-14 · IJCNLP 2019 11 · Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen

Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by attention heads seems not to match human intuitions about hierarchical structures. This paper proposes Tree Transformer, which adds an extra constraint to attention heads of the bidirectional Transformer encoder in order to encourage the attention heads to follow tree structures. The tree structures can be automatically induced from raw texts by our proposed "Constituent Attention" module, which is simply implemented by self-attention between two adjacent words. With the same training procedure identical to BERT, the experiments demonstrate the effectiveness of Tree Transformer in terms of inducing tree structures, better language modeling, and further learning more explainable attention scores.

📄 PDF Abstract BibTeX arXiv:1909.06639

Code (3)

yaushian/Tree-Transformer 공식 구현 pytorch
iceraionly/Tree-Transformer pytorch
itzpankajpanwar/Tree-transform pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Weight Decay 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…
WordPiece 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

Integrating Dependency Tree Into Self-attention for Sentence Representation

2022-03-11 · Junhua Ma, Jiajun Li, Yuxuan Liu, Shangbo Zhou 외

Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly encode tree structures recursively, which is not conducive to parallelization. On the other hand, these w…

Computational EfficiencyRepresentation LearningSentence

Tree Transformers are an Ineffective Model of Syntactic Constituency

2024-11-25 · Michael Ginn

Linguists have long held that a key aspect of natural language syntax is the recursive organization of language units into constituent structures, and research has suggested that current state-of-the-art language models …

Language ModelingLanguage Modelling

Trees in transformers: a theoretical analysis of the Transformer's ability to represent trees

2021-12-16 · Qi He, João Sedoc, Jordan Rodu

Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of T…

Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models

2024-07-24 · Yida Zhao, Chao Lou, Kewei Tu

Syntactic Transformer language models aim to achieve better generalization through simultaneously modeling syntax trees and sentences. While prior work has been focusing on adding constituency-based structures to Transfo…

ARCInductive BiasLanguage ModelingLanguage Modelling

Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision

2024-02-20 · Ryo Yoshida, Taiga Someya, Yohei Oseki

Syntactic Language Models (SLMs) can be trained efficiently to reach relatively high performance; however, they have trouble with inference efficiency due to the explicit generation of syntactic structures. In this paper…

Continual Learning