paper-with-me

Papers

Differentiable Tree Operations Promote Compositional Generalization

2023-06-01 · Paul Soulos, Edward Hu, Kate McCurdy, Yunmo Chen, Roland Fernandez, Paul Smolensky, Jianfeng Gao

In the context of structure-to-structure transformation tasks, learning sequences of discrete symbolic operations poses significant challenges due to their non-differentiability. To facilitate the learning of these symbolic sequences, we introduce a differentiable tree interpreter that compiles high-level symbolic tree operations into subsymbolic matrix operations on tensors. We present a novel Differentiable Tree Machine (DTM) architecture that integrates our interpreter with an external memory and an agent that learns to sequentially select tree operations to execute the target transformation in an end-to-end manner. With respect to out-of-distribution compositional generalization on synthetic semantic parsing and language generation tasks, DTM achieves 100% while existing baselines such as Transformer, Tree Transformer, LSTM, and Tree2Tree LSTM achieve less than 30%. DTM remains highly interpretable in addition to its perfect performance.

📄 PDF Abstract BibTeX arXiv:2306.00751

Code (1)

psoulos/dtm 공식 구현 pytorch

Tasks

Semantic ParsingText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Residual Connection 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…
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 $x$…
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…

Similar Papers 제목 키워드 기반

Compositional Generalization with Tree Stack Memory Units

2019-11-05 · Forough Arabshahi, Zhichu Lu, Pranay Mundra, Sameer Singh 외

We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent on compositional learning. We propose Tr…

Mathematical ReasoningZero-shot Generalization

Compositional Generalization Across Distributional Shifts with Sparse Tree Operations

2024-12-18 · Paul Soulos, Henry Conklin, Mattia Opper, Paul Smolensky 외

Neural networks continue to struggle with compositional generalization, and this issue is exacerbated by a lack of massive pre-training. One successful approach for developing neural systems which exhibit human-like comp…

NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization

2024-12-20 · Danial Kamali, Elham J. Barezi, Parisa Kordjamshidi

Compositional generalization is crucial for artificial intelligence agents to solve complex vision-language reasoning tasks. Neuro-symbolic approaches have demonstrated promise in capturing compositional structures, but …

Compositional Generalization (AVG)Novel ConceptsVisual Question AnsweringVisual Question Answering (VQA)+2

Toward Compositional Generalization in Object-Oriented World Modeling

2022-04-28 · Linfeng Zhao, Lingzhi Kong, Robin Walters, Lawson L. S. Wong

Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modelin…

Decision MakingObjectreinforcement-learningReinforcement Learning (RL)

Span-based Semantic Parsing for Compositional Generalization

2020-09-13 · ACL 2021 5 · Jonathan Herzig, Jonathan Berant

Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new structures built of component…

Semantic Parsing