An NLP Assistant for Clide

TL;DR

This paper presents an NLP assistant integrated into Clide that visualizes semantic structures and mines information from text, aiding NLP application development through interactive visualization and querying.

Contribution

It introduces an NLP assistant that visualizes semantic graphs, coreference chains, and mined triples within a collaborative environment, enhancing NLP development tools.

Findings

Successfully visualizes semantic graphs and coreference chains

Enables querying of mined triples from text

Demonstrates translation of natural language descriptions into graphs

Abstract

This report describes an NLP assistant for the collaborative development environment Clide, that supports the development of NLP applications by providing easy access to some common NLP data structures. The assistant visualizes text fragments and their dependencies by displaying the semantic graph of a sentence, the coreference chain of a paragraph and mined triples that are extracted from a paragraph's semantic graphs and linked using its coreference chain. Using this information and a logic programming library, we create an NLP database which is used by a series of queries to mine the triples. The algorithm is tested by translating a natural language text describing a graph to an actual graph that is shown as an annotation in the text editor.