---
title: "Learning for Deep Language Understanding"
authors:
  - "Smaranda Muresan"
doi: "10.5591/978-1-57735-516-8/IJCAI11-311"
url: "https://ijcai.org/proceedings/2011/311"
pdf: "https://ijcai.org/proceedings/2011/0311.pdf"
venue: "Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence"
year: 2011
pages: "1858-1864"
track: ""
keywords:
---

# Learning for Deep Language Understanding

Smaranda Muresan

*Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence*, pages 1858-1864. DOI: [10.5591/978-1-57735-516-8/IJCAI11-311](https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-311)

## Abstract

Lexicalized Well-Founded Grammar (LWFG) is a recently developed syntactic-semantic grammar formalism for deep language understanding, which balances expressiveness with provable learnability results. The learnability result for LWFGs assumes that the semantic composition constraints are learnable. In this paper, we show what are the properties and principles the semantic representation and grammar formalism require, in order to be able to learn these constraints from examples, and give a learning algorithm. We also introduce a LWFG parser as a deductive system, used as an inference engine during LWFG induction. An example for learning a grammar for noun compounds is given.