# Logical Parsing from Natural Language Based on a Neural Translation   Model

**Authors:** Liang Li, Pengyu Li, Yifan Liu, Tao Wan, Zengchang Qin

arXiv: 1705.03389 · 2017-05-10

## TL;DR

This paper introduces a neural translation model for semantic parsing that learns to generate logical forms from natural language without relying on handcrafted resources, demonstrating success in the arithmetic domain.

## Contribution

It presents a Seq2Seq-based approach with attention and curriculum learning to infer logical forms from denotations, reducing reliance on domain-specific lexicons and grammars.

## Key findings

- Successfully infers correct logical forms in the arithmetic domain
- Learns word meanings, compositionality, and operation order simultaneously
- Reduces search space by leveraging similarity of utterances

## Abstract

Semantic parsing has emerged as a significant and powerful paradigm for natural language interface and question answering systems. Traditional methods of building a semantic parser rely on high-quality lexicons, hand-crafted grammars and linguistic features which are limited by applied domain or representation. In this paper, we propose a general approach to learn from denotations based on Seq2Seq model augmented with attention mechanism. We encode input sequence into vectors and use dynamic programming to infer candidate logical forms. We utilize the fact that similar utterances should have similar logical forms to help reduce the searching space. Under our learning policy, the Seq2Seq model can learn mappings gradually with noises. Curriculum learning is adopted to make the learning smoother. We test our method on the arithmetic domain which shows our model can successfully infer the correct logical forms and learn the word meanings, compositionality and operation orders simultaneously.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/1705.03389/full.md

## Figures

2 figures with captions in the complete paper: https://tomesphere.com/paper/1705.03389/full.md

## References

27 references — full list in the complete paper: https://tomesphere.com/paper/1705.03389/full.md

---
Source: https://tomesphere.com/paper/1705.03389