Dialog Natural Language Understanding using a Generic Textual Inference System
نویسندگان
چکیده
One of the components of a dialog system is the Natural Language Understanding (NLU) component. This component accepts natural language text, and returns the meaning of that text, in some formal application-specific meaning representation. One of the difficulties in building NLU components is the variability in natural language the many different ways by which a human can express the same meaning. We propose to tackle this difficulty by using a generic Textual Entailment (TE) system a system that can calculate, for each pair of texts, whether the meaning of one of them can be inferred from the other. A single TE system can be used for various NLU components in various domains.
منابع مشابه
Xdisease occur in Ycountry Xdisease common in Ycountry Xdisease frequent in Ycountry Xdisease begin in Ycountry Xdisease epidemic in Ycountry
The goal of my research is to develop natural language understanding algorithms, that is, algorithms that induce a representation of meaning from natural language, and allow machines to understand text and reason over it. I focus on developing methods that learn to predict such meaning representations from data, rather than hand-coding meaning translation rules, as is common for instance in com...
متن کاملDeeper Natural Language Processing for Evaluating Student Answers in Intelligent Tutoring Systems
This paper addresses the problem of evaluating students’ answers in intelligent tutoring environments with mixed-initiative dialogue by modelling it as a textual entailment problem. The problem of meaning representation and inference is a pervasive challenge in any integrated intelligent system handling communication. For intelligent tutorial dialogue systems, we show that entailment cases can ...
متن کاملKnowledge-Based Textual Inference via Parse-Tree Transformations
Textual inference is an important component in many applications for understanding natural language. Classical approaches to textual inference rely on logical representations for meaning, which may be regarded as “external” to the natural language itself. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, which correspond closely to language st...
متن کاملTextual Inference and Meaning Representation in Human Robot Interaction
This paper provides a first investigation over existing textual inference paradigms in order to propose a generic framework able to capture major semantic aspects in Human Robot Interaction (HRI). We investigate the use of general semantic paradigms used in Natural Language Understanding (NLU) tasks, such as Semantic Role Labeling, over typical robot commands. The semantic information obtained ...
متن کاملComprehension across Application Domains and Languages
This work demonstrates that our natural language understanding framework can be applied across application domains and languages with ease. Approaches towards language understanding generally involve much handcrafting, e.g. in writing grammars or annotating corpora, hence portability is a desirable trait in the development of language understanding systems. Our framework for natural language un...
متن کامل