paper-with-me

Papers

Novel positional encodings to enable tree-based transformers

2019-12-01 · NeurIPS 2019 12 · Vighnesh Shiv, Chris Quirk

Neural models optimized for tree-based problems are of great value in tasks like SQL query extraction and program synthesis. On sequence-structured data, transformers have been shown to learn relationships across arbitrary pairs of positions more reliably than recurrent models. Motivated by this property, we propose a method to extend transformers to tree-structured data, enabling sequence-to-tree, tree-to-sequence, and tree-to-tree mappings. Our approach abstracts the transformer's sinusoidal positional encodings, allowing us to instead use a novel positional encoding scheme to represent node positions within trees. We evaluated our model in tree-to-tree program translation and sequence-to-tree semantic parsing settings, achieving superior performance over both sequence-to-sequence transformers and state-of-the-art tree-based LSTMs on several datasets. In particular, our results include a 22% absolute increase in accuracy on a JavaScript to CoffeeScript translation dataset.

📄 PDF Abstract BibTeX

Code (1)

microsoft/icecaps 공식 구현 tf

Tasks

Program SynthesisSemantic ParsingTranslation

Similar Papers 제목 키워드 기반

Novel positional encodings to enable tree-structured transformers

2018-09-27 · Vighnesh Leonardo Shiv, Chris Quirk

With interest in program synthesis and similarly flavored problems rapidly increasing, neural models optimized for tree-domain problems are of great value. In the sequence domain, transformers can learn relationships acro…

Program SynthesisSemantic ParsingTranslation

Comparing Graph Transformers via Positional Encodings

2024-02-22 · Mitchell Black, Zhengchao Wan, Gal Mishne, Amir Nayyeri 외

The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of position…

Navigate

Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings

2026-08-31 · Zimo Yan, Yifan Li, Hao Li, Zheng Xie 외 arxiv

Graph positional encodings are widely used in graph neural networks and graph Transformers, yet it remains unclear when the code itself can identify nodes. We study a hybrid distance-spectral encoding that combines ancho…

Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings

2024-12-30 · Chunsheng Zuo, Pavel Guerzhoy, Michael Guerzhoy

Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis about how positional information can be…

Position

Breaking Symmetry When Training Transformers

2024-02-06 · Chunsheng Zuo, Michael Guerzhoy

As we show in this paper, the prediction for output token $n+1$ of Transformer architectures without one of the mechanisms of positional encodings and causal attention is invariant to permutations of input tokens $1, 2, …