Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural Representations
arXiv:1910.02339
Abstract
Generating formal-language programs represented by relational tuples, such as Lisp programs or mathematical operations, to solve problems stated in natural language is a challenging task because it requires explicitly capturing discrete symbolic structural information implicit in the input. However, most general neural sequence models do not explicitly capture such structural information, limiting their performance on these tasks. In this paper, we propose a new encoder-decoder model based on a structured neural representation, Tensor Product Representations (TPRs), for mapping Natural-language problems to Formal-language solutions, called TP-N2F. The encoder of TP-N2F employs TPR `binding' to encode natural-language symbolic structure in vector space and the decoder uses TPR `unbinding' to generate, in symbolic space, a sequential program represented by relational tuples, each consisting of a relation (or operation) and a number of arguments. TP-N2F considerably outperforms LSTM-based seq2seq models on two benchmarks and creates new state-of-the-art results. Ablation studies show that improvements can be attributed to the use of structured TPRs explicitly in both the encoder and decoder. Analysis of the learned structures shows how TPRs enhance the interpretability of TP-N2F.
Cited by in corpus (6)
- Training Verifiers to Solve Math Word Problems
- Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
- Recent Developments in Program Synthesis with Evolutionary Algorithms
- End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks
- Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
- Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages