DeepAI AI Chat
Log In Sign Up

Compositional Generalization for Primitive Substitutions

by   Yuanpeng Li, et al.
Baidu, Inc.

Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability. In this paper, we conduct fundamental research for encoding compositionality in neural networks. Conventional methods use a single representation for the input sentence, making it hard to apply prior knowledge of compositionality. In contrast, our approach leverages such knowledge with two representations, one generating attention maps, and the other mapping attended input words to output symbols. We reduce the entropy in each representation to improve generalization. Our experiments demonstrate significant improvements over the conventional methods in five NLP tasks including instruction learning and machine translation. In the SCAN domain, it boosts accuracies from 14.0 to 99.7 learning task. We hope the proposed approach can help ease future research towards human-level compositional language learning.


Concepts, Properties and an Approach for Compositional Generalization

Compositional generalization is the capacity to recognize and imagine a ...

Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures

While mainstream machine learning methods are known to have limited abil...

Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning

Compositional generalization is a basic mechanism in human language lear...

Compositional generalization in a deep seq2seq model by separating syntax and semantics

Standard methods in deep learning for natural language processing fail t...

Learning Compositional Neural Information Fusion for Human Parsing

This work proposes to combine neural networks with the compositional hie...

Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN

Despite their practical success, modern seq2seq architectures are unable...

Measuring Compositionality in Representation Learning

Many machine learning algorithms represent input data with vector embedd...