The development of natural language interfaces (NLI's) for databases has been a challenging problem in natural language processing (NLP) since the 1970's. The need for NLI's has become more pronounced due to the widespread access to complex databases now available through the Internet. A challenging problem for empirical NLP is the automated acquisition of NLI's from training examples. We present a method for integrating statistical and relational learning techniques for this task which exploits the strength of both approaches. Experimental results from three different domains suggest that such an approach is more robust than a previous purely logic-based approach.

Computational systems that learn to transform naturallanguage sentences into semantic representations have important practical applications in building naturallanguage interfaces. They can also provide insight into important issues in human language acquisition. However, within AI, computational linguistics, and machine learning, there has been relatively little research on developing systems that learn such semantic parsers.

Providing a natural language interface to ontologies will not only offer ordinary users the convenience of acquiring needed information from ontologies, but also expand the influence of ontologies and the semantic web consequently. This paper presents PANTO, a Portable nAtural laNguage inTerface to Ontologies, which accepts generic natural language queries and outputs SPARQL queries. Based on a special consideration on nominal phrases, it adopts a triple-based data model to interpret the parse trees output by an off-the-shelf parser. Complex modifications in natural language queries such as negations, superlative and comparative are investigated. The experiments have shown that PANTO provides state-of-the-art results.

Most recent research in learning approaches to natural language have studied fairly "low-level" tasks such as morphology, part-of-speech tagging, and syntactic parsing. However, I believe that logical approaches may have the most relevance and impact at the level of semantic interpretation, where a logical representation of sentence meaning is important and useful. We have explored the use of inductive logic programming for learning parsers that map naturallanguage database queries into executable logical form. This work goes against the growing trend in computational linguistics of focusing on shallow but broad-coverage natural language tasks ("scaling up by dumbing down") and instead concerns using logic-based learning to develop narrower, domain-specific systems that perform relatively deep processing. I first present a historical view of the shifting emphasis of research on various tasks in natural language processing and then briefly review our own work on learning for semantic interpretation. I will then attempt to encourage others to study such problems and explain why I believe logical approaches have the most to offer at the level of producing semantic interpretations of complete sentences.

Research on ontology is becoming increasingly widespread in the computer science community. The major problems in building ontologies are the bottleneck of knowledge acquisition and time-consuming construction of various ontologies for various domains/applications. Meanwhile moving toward automation of ontology construction is a solution. We proposed an automatic ontology building approach. In this approach the system starts form a small ontology kernel and constructs the ontology through text understanding automatically. The kernel contains the primitive concepts, relations and operators to build an ontology. The features of our proposed model are being domain / application independent, building ontologies upon a small primary kernel, learning words, concepts, taxonomic and non-taxonomic relations and axioms and applying a symbolic, hybrid ontology learning approach consisting of logical, linguistic based, template driven and semantic analysis methods. Hasti is an ongoing project to implement and test the automatic ontology building approach. It extracts lexical and ontological knowledge from Persian (Farsi) texts. In this paper at first we will describe some ontology engineering problems, which motivated our approach. In the next sections, after a brief description of Hasti, its features and its architecture, we will discuss its components in detail. In each part the learning algorithms will be described. Then some experimental results will be discussed and at last we will have an overview of related works and will introduce a general framework to compare ontology learning systems and will compare Hasti with related works according to the framework. 1.

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

Automated Question- Answering aims at delivering concise information that contains answers to user questions. This paper reviews and compares three main question-answering approaches based on Natural Language Processing, Information Retrieval, and question templates, eliciting their differences and the context of application that best suits each of them. 1.

To my father, the force behind my work, if only he could share with me the joy... To my mother who always believes in me even when I don’t. Also to Christ Jesus without whom the days would have been much harder if possible. Acknowledgments The completion of this thesis hinges on many factors. The most important of which would be the advice, besides patience, of my supervisor Dr. Raymond J. Mooney. I would like to take this opportunity to thank Prem Melville for his assistance on data preparation. He has been a valuable partner on the EELD project and a very helpful friend in our research group. My thanks also goes to Sugato Basu, my officemate and friend, who has been a valuable companion in the course of completing my thesis. We had many stimulating discussions on various topics in Artifical Intelligence, particularly in Machine Learning. He’s an interesting person to talk to and share research ideas with. Much of thanks go to Vitor Santos Costa who has gone many extra miles to

Abstract not found

The development of natural language interfaces (NLIs) for databases has been an interesting problem in natural language processing since the 70's. The need for NLIs has become more pronounced given the widespread access to complex databases now available through the Internet. However, such systems are difficult to build and must be tailored to each application. A current research topic involves using machine learning methods to automate the development of NLI's. This proposal presents a method for learning semantic parsers (systems for mapping natural language to logical form) that integrates logic-based and probabilistic methods in order to exploit the complementary strengths of these competing approaches. More precisely, an inductive logic programming (ILP) method, TABULATE, is developed for learning multiple models that are integrated via linear weighted combination to produce probabilistic models for statistical semantic parsing. Initial experimental results from three d...