paper-with-me

Papers

Self-Attention with Structural Position Representations

2019-09-01 · IJCNLP 2019 11 · Xing Wang, Zhaopeng Tu, Long-Yue Wang, Shuming Shi

Although self-attention networks (SANs) have advanced the state-of-the-art on various NLP tasks, one criticism of SANs is their ability of encoding positions of input words (Shaw et al., 2018). In this work, we propose to augment SANs with structural position representations to model the latent structure of the input sentence, which is complementary to the standard sequential positional representations. Specifically, we use dependency tree to represent the grammatical structure of a sentence, and propose two strategies to encode the positional relationships among words in the dependency tree. Experimental results on NIST Chinese-to-English and WMT14 English-to-German translation tasks show that the proposed approach consistently boosts performance over both the absolute and relative sequential position representations.

📄 PDF Abstract BibTeX arXiv:1909.00383

Code (0)

등록된 구현이 없습니다.

Tasks

PositionSentenceTranslation

Similar Papers 제목 키워드 기반

Does Structural Attention Improve Compositional Representations in Vision-Language Models?

2022-12-03 · NeurIPS Workshop: Self-Supervised Learning - Theory and Practice 2022 12 · Rohan Pandey, Rulin Shao, Paul Pu Liang, Louis-Philippe Morency

Although scaling self-supervised approaches has gained widespread success in Vision-Language pre-training, a number of works providing structural knowledge of visually-grounded semantics have recently shown incremental…

Visual Reasoning

Discourse Self-Attention for Discourse Element Identification in Argumentative Student Essays

2020-11-01 · EMNLP 2020 11 · Wei Song, Ziyao Song, Ruiji Fu, Lizhen Liu 외

This paper proposes to adapt self-attention to discourse level for modeling discourse elements in argumentative student essays. Specifically, we focus on two issues. First, we propose structural sentence positional encod…

Sentence

Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders

2026-08-14 · Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa 외 arxiv

Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expressed in the representation used for pre…

Structure-Aware Transformer for Graph Representation Learning

2022-02-07 · Dexiong Chen, Leslie O'Bray, Karsten Borgwardt

The Transformer architecture has gained growing attention in graph representation learning recently, as it naturally overcomes several limitations of graph neural networks (GNNs) by avoiding their strict structural induc…

Emotion Recognition in ConversationGraph Representation LearningRepresentation Learning

Composition, Attention, or Both?

2022-10-24 · Ryo Yoshida, Yohei Oseki

In this paper, we propose a novel architecture called Composition Attention Grammars (CAGs) that recursively compose subtrees into a single vector representation with a composition function, and selectively attend to pre…