Semantic parsing is the construction of a complete, formal, symbolic meaning representation of a sentence. While it is crucial to natural language understanding, the problem of semantic parsing has received relatively little attention from the machine learning community. Recent work on natural language understanding has mainly focused on shallow semantic analysis, such as word-sense disambiguation and semantic role labeling. Semantic parsing, on the other hand, involves deep semantic analysis in which word senses, semantic roles and other components are combined to produce useful meaning representations for a particular application domain (e.g. database query). Prior research in machine learning for semantic parsing is mainly based on inductive logic programming or deterministic parsing, which lack some of the robustness that characterizes statistical learning. Existing statistical approaches to semantic parsing, however, are mostly concerned with relatively simple application domains in which a meaning representation is no more than a single semantic frame. In this proposal, we present a novel statistical approach to semantic parsing, WASP, which can handle meaning representations with a nested structure. The WASP algorithm learns a semantic parser given a set of sentences annotated with their correct meaning representations. The parsing model is based on the

We demonstrate a proof-of-concept system that uses a shallow chunking-based technique for knowledge extraction from natural language text, in particular looking at the task of story understanding. This technique is extended with a reasoning engine that borrows techniques from dynamic ontology refinement to discover the semantic similarity of stories and to merge them together. 1

Most recent work on semantic analysis of natural language has focused on “shallow ” semantics such as word-sense disambiguation and semantic role labeling. Our work addresses a more ambitious task we call semantic parsing where natural language sentences are mapped to complete formal meaning representations. We present our system SCISSOR based on a statistical parser that generates a semanticallyaugmented parse tree (SAPT), in which each internal node has both a syntactic and semantic label. A compositional-semantics procedure is then used to map the augmented parse tree into a final meaning representation. Training the system requires sentences annotated with augmented parse trees. We evaluate the system in two domains, a natural-language database interface and an interpreter for coaching instructions in robotic soccer. We present experimental results demonstrating that SCISSOR produces more accurate semantic representations than several previous approaches on long sentences. In the future, we intend to pursue several directions in developing more accurate semantic parsing algorithms and automating the annotation process. This work will involve exploring alternative tree representations for better generalization in parsing. We also plan to apply discriminative reranking methods to semantic parsing, which allows exploring arbitrary, potentially correlated features not usable by the

This document explains the overall research direction of my dissertation. Because this direction is different from most research today in mainstream NLP, I spend a

Abstract. This paper shows how a controlled natural language can help to reconstruct a logic puzzle in a well-defined subset of natural language and discusses how this puzzle can then be processed and solved using a state of the art model generator. Our approach relies on a collaboration between humans and machines and bridges the gap between a (seemingly informal) problem description and an executable formal specification. 1

Abstract not found