paper-with-me

Papers

Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale

2022-03-01 · Laurent Sartran, Samuel Barrett, Adhiguna Kuncoro, Miloš Stanojević, Phil Blunsom, Chris Dyer

We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are implemented through a special attention mask and deterministic transformation of the linearized tree. We find that TGs outperform various strong baselines on sentence-level language modeling perplexity, as well as on multiple syntax-sensitive language modeling evaluation metrics. Additionally, we find that the recursive syntactic composition bottleneck which represents each sentence as a single vector harms perplexity on document-level language modeling, providing evidence that a different kind of memory mechanism -- one that is independent of composed syntactic representations -- plays an important role in current successful models of long text.

📄 PDF Abstract BibTeX arXiv:2203.00633

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive BiasLanguage ModelingLanguage ModellingSentence

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Does Traversal Order Matter? A Systematic Study of Tree Traversal Methods in Transformer Grammars

2026-06-15 · Zongru Liu, Pengyu Ji, Pengcheng Wang, Kewei Tu arxiv

Transformer Grammars (TGs) enhance language modeling by incorporating syntactic tree structures. Despite the potentially significant impact on model performance of how syntactic trees are linearized in TGs, existing stud…

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

GiLT: Augmenting Transformer Language Models with Dependency Graphs

2026-05-15 · Tianyu Huang, Yida Zhao, Chuyan Zhou, Kewei Tu arxiv

Augmenting Transformers with linguistic structures effectively enhances the syntactic generalization performance of language models. Previous work in this direction focuses on syntactic tree structures of languages, in p…

An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars

2026-06-16 · Vinoth Nandakumar, Qiang Qu, Pramod Thebe, Sakshi Khachariya 외 arxiv

Deep neural networks are widely believed to derive their expressive power from their ability to form \textbf{hierarchical representations}, capturing progressively more abstract and compositional features across layers. …

Synchronous Syntactic Attention for Transformer Neural Machine Translation

2021-08-01 · ACL 2021 5 · Hiroyuki Deguchi, Akihiro Tamura, Takashi Ninomiya

This paper proposes a novel attention mechanism for Transformer Neural Machine Translation, {``}Synchronous Syntactic Attention,{''} inspired by synchronous dependency grammars. The mechanism synchronizes source-side and…

DecoderMachine TranslationTranslation