Posts Tagged ‘Natural Language Processing’

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

PostHeaderIcon Natural Language Processing: Overview

Natural Language Processing (NLP) aims to acquire, understand and generate the human languages such as English, French, Tamil, Hindi, etc.

Symbolic Approaches to Natural Language Processing

Symbolic Approaches also known as Rationalist approaches believe that  significant part of the knowledge in the human mind is not derived by the senses but is fixed in advance, presumably by genetic inheritance. Noam Chomsky was the strong advocate of this approach. It was believed that machine can be made to function like human brain by giving some basic knowledge and reasoning mechanisms Linguistic knowledge is explicitly encoded in rule or other forms of representation. This helps automatic process of natural languages.

Natural Language analysis

It runs into many stages, namely tokenization, lexical analysis,  syntactic analysis, semantic analysis, and pragmatic analysis.

Syntactic analysis provides an order and structure of each sentence in the text. Semantic analysis is to find the literal meaning, and pragmatic analysis is to determine the meaning of the text in context. These major tasks are further broken down into, parsing and so on.

Natural Language Generation

This is to generate fluent and coherent multi-sentential texts from an underlying source of information. The kind of text generated ranging from a single word or a phrase as an answer to a question to full-page explanations and even to the extent of speech depending upon the context.

Empirical Approaches to Natural Language Processing

Empirical Approaches focus on the use of large amounts of data and the procedures involving statistical manipulations. Corpus, bulk of data in a particular format, comes handy for analysis. Crucial tasks using these approaches are POS tagging, alignment, collacations, word-sense-disambiguation, etc.

Challenges In Natural Language Processing

Still a perfect natural language processing system is developed. There are many problems like flexibility in the structure of sentences, ambiguity, etc.

Natural language processing applications require the availability of Lexical Resources, Corpora and Computational Models.

For Further Study

Foundations of Statistical Natural Language Processing


Handbook of Natural Language Processing, Second Edition (Chapman & Hall/CRC Machine Learning & Pattern Recognition)


Natural Language Understanding (2nd Edition)


Natural Language Processing with Python

Related Articles

Natural Language Understanding

Natural Language Generation

Open Problems

Linguistics: Overview

Tokenization: Overview

Parts Of Speech Tagging

Machine Translation

References