paper-with-me

Papers

Systematic Generalization with Edge Transformers

2021-12-01 · NeurIPS 2021 12 · Leon Bergen, Timothy J. O'Donnell, Dzmitry Bahdanau

Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge, we propose Edge Transformer, a new model that combines inspiration from Transformers and rule-based symbolic AI. The first key idea in Edge Transformers is to associate vector states with every edge, that is, with every pair of input nodes -- as opposed to just every node, as it is done in the Transformer model. The second major innovation is a triangular attention mechanism that updates edge representations in a way that is inspired by unification from logic programming. We evaluate Edge Transformer on compositional generalization benchmarks in relational reasoning, semantic parsing, and dependency parsing. In all three settings, the Edge Transformer outperforms Relation-aware, Universal and classical Transformer baselines.

📄 PDF Abstract BibTeX arXiv:2112.00578

Code (1)

bergen/edgetransformer 공식 구현 pytorch

Tasks

Dependency ParsingNatural Language UnderstandingRelational ReasoningSemantic ParsingSystematic Generalization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers

2026-04-09 · Harsh Kohli, Srinivasan Parthasarathy, Huan Sun, Yuekun Yao arxiv

We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual knowledge and rules, they often fail to co…

Transformer Module Networks for Systematic Generalization in Visual Question Answering

2022-01-27 · Moyuru Yamada, Vanessa D'Amario, Kentaro Takemoto, Xavier Boix 외

Transformers achieve great performance on Visual Question Answering (VQA). However, their systematic generalization capabilities, i.e., handling novel combinations of known concepts, is unclear. We reveal that Neural Mod…

Question AnsweringSystematic GeneralizationVisual Question AnsweringVisual Question Answering (VQA)

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

2024-05-23 · Boshi Wang, Xiang Yue, Yu Su, Huan Sun

We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representative reasoning types, composition and co…

Systematicity Emerges in Transformers when Abstract Grammatical Roles Guide Attention

2022-07-01 · NAACL (ACL) 2022 7 · Ayush K Chakravarthy, Jacob Labe Russin, Randall O’Reilly

Systematicity is thought to be a key inductive bias possessed by humans that is lacking in standard natural language processing systems such as those utilizing transformers. In this work, we investigate the extent to whi…

Inductive BiasSystematic Generalization

Measuring Systematic Generalization in Neural Proof Generation with Transformers

2020-09-30 · NeurIPS 2020 12 · Nicolas Gontier, Koustuv Sinha, Siva Reddy, Christopher Pal

We are interested in understanding how well Transformer language models (TLMs) can perform reasoning tasks when trained on knowledge encoded in the form of natural language. We investigate their systematic generalization…

Automated Theorem ProvingLogical ReasoningSystematic Generalization