PostHeaderIcon Open Problems In Natural Language Processing

Natural language processing is successful in meeting the challenges as far as syntax is concerned. But it still has to go a long way in the areas of semantics and pragmatics. The issues still unresolved in semantics are finding the meaning of a word or a word sense, determining scopes of quantifiers, finding referents of anaphora, relation of modifiers to nouns and identifying meaning of tenses to temporal objects.

First-order logic (FOL) and knowledge representation systems find it difficult to represent some issues such as time and modality. FOL also finds it too hard to deal with generalized quantifiers and exceptions. Representing and inferring world knowledge, commonsense knowledge in particular, is difficult. Semantics of discourse segments is a difficult problem.

There are challenges in pragmatics as well. A simple declarative sentence stating a fact, it is sunny for example, is not only a statement of fact but also serves some communication function. The function may be to inform, to mislead about fact or speaker’s belief about fact, to draw attention, to remind previously mentioned even or object related to fact, etc. So, the pragmatic interpretation seems to be open ended. Speech act theory and Schank’s work look suitable approaches.

Related Articles

Natural Language Processing – An Overview

Natural Language Understanding

Machine Translation