A knowledge-free method for capitalized word disambiguation

Published 1 January 1999Open access

Andrei Mikheev

Citations55

TL;DR

An approach to the disambiguation of capitalized words when they are used in the positions where capitalization is expected, such as the first word in a sentence or after a period, quotes, etc.

Abstract

In this paper we present an approach to the disambiguation of capitalized words when they are used in the positions where capitalization is expected, such as the first word in a sentence or after a period, quotes, etc.. Such words can act as proper names or can be just capitalized vari- ants of common words. The main feature of our approach is that it uses a minimum of prebuilt resources and tries to dynamically infer the disambiguation clues from the entire document.

Keywords

Computer Science

Building a Large Annotated Corpus of English: The Penn Treebank

7,528 Citations1993Mitchell P. Marcus

Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging

1,531 Citations1995Eric Brill

This paper describes a simple rule-based approach to automated learning of linguistic knowledge that has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance.

A stochastic parts program and noun phrase parser for unrestricted text

974 Citations1988Kenneth Church

A program that tags each word in an input sentence with the most likely part of speech has been written and performance is encouraging; a 400-word sample is presented and is judged to be 99.5% correct.

View PDF

A maximum entropy approach to identifying sentence boundaries

393 Citations1997Jeffrey C. Reynar, Adwait Ratnaparkhi

A trainable model for identifying sentence boundaries in raw text that can be trained easily on any genre of English, and should be trainable on any other Romanalphabet language.

View PDF

Automatic rule induction for unknown-word guessing

260 Citations1997Andrei Mikheev

Using the proposed technique, unknown-word-guessing rule sets were induced and integrated into a stochastic tagger and a rule-based tagger, which were then applied to texts with unknown words.

Description of the LTG system used for MUC-7

163 Citations1998Andrei Mikheev, Claire Grover +1 more

The basic building blocks in this system are reusable text handling tools which are modular tools with stream input/output; each tool does a very speci c job, but can be combined with other tools in a unix pipeline.

Computational LinguisticsAdaptive multilingual sentence boundary disambiguation

152 Citations1997David D. Palmer, Marti A. Hearst

An efficient, trainable system for sentence boundary disambiguation, called Satz, that makes simple estimates of the parts of speech of the tokens immediately preceding and following each punctuation mark, and uses these estimates as input to a machine learning algorithm that then classifies the punctuation mark.

One term or two?

36 Citations1995Kenneth Church

Feature lattices for maximum entropy modelling

19 Citations1998Andrei Mikheev

This paper presents a novel approach for building maximum entropy models that uses the feature collocation lattice and builds complex candidate features without resorting to iterative scaling.

View PDF

Proceedings of the 17th international conference on Computational linguistics -Feature lattices for maximum entropy modelling

4 Citations1998Andrei M. Mikheev

View PDF