Acquiring a Lexicon by Actively Querying the User

نویسنده

  • Lars Asker
چکیده

We present a semi-automatic approach to lexical acquisition which utilizes experiences from earlier systems by the authors and others. The hybrid system combines the subsystems in the following way: a fully automatic approach (EBL 2 ) is extended with grammatical constraints (SWECG) which lters output hypotheses, thus improving on the accuracy of the automatic paradigm assignments. Candidate sentences are generated using paradigm patterns from a semiautomatic lexical acquistion tool (VEX). These are presented to and judged for grammaticality by the user. This hybrid approach has several advantages compared to using either of the subsystems in isolation. It does not require any linguistic knowledge on the part of the user. Possible extensions to an existing lexicon are automatically selected by the system. Due to the strength of the combined strategy a 100% accuracy guarantee should be quite feasible.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Tauira: A tool for acquiring unknown words in a dialogue context

This paper describes a tool for acquiring unknown words, which operates in a bilingual human-machine dialogue system. When the user’s utterance includes a word which is not in the system’s lexicon, the system initiates a subdialogue to find out about the new word, by querying the user about the syntactic validity of a number of example sentences generated automatically from the grammar’s test s...

متن کامل

Feature extraction in opinion mining through Persian reviews

Opinion mining deals with an analysis of user reviews for extracting their opinions, sentiments and demands in a specific area, which can play an important role in making major decisions in such area. In general, opinion mining extracts user reviews at three levels of document, sentence and feature. Opinion mining at the feature level is taken into consideration more than the other two levels d...

متن کامل

Semantic Lexical Resources Applied to Content-based Querying - the OntoQuery Project

This paper deals with the exploitation of the lexical and conceptual knowledge coded in the SIMPLE-DK lexicon in the methodology for content-based querying developed by the OntoQuery project. SIMPLE-DK has proven a rich and flexible lexical resource, which the project has taken advantage of in several ways. Firstly, the paper explains how the ontology provided by SIMPLE is used by the current p...

متن کامل

Sentiment Lexicon Generation for an Under-Resourced Language

Sentiment analysis and opinion mining are actively explored nowadays. One of the most important resources for the sentiment analysis task is sentiment lexicon. This paper presents our study in building domain-specific sentiment lexicon for Indonesian language. Our main contributions are (1) methods to expand sentiment lexicon using sentiment patterns and (2) a technique to classify the polarity...

متن کامل

Aspect-Oriented Opinion Mining from User Reviews in Croatian

Aspect-oriented opinion mining aims to identify product aspects (features of products) about which opinion has been expressed in the text. We present an approach for aspect-oriented opinion mining from user reviews in Croatian. We propose methods for acquiring a domain-specific opinion lexicon, linking opinion clues to product aspects, and predicting polarity and rating of reviews. We show that...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1995