Correction of Noisy Sentences using a Monolingual Corpus

TL;DR

This paper explores statistical methods for correcting noisy sentences using a monolingual corpus, focusing on phrase-based algorithms and error modeling to improve text quality in NLP applications.

Contribution

It introduces phrase-based correction algorithms utilizing only a target language model and analyzes their effectiveness on noisy machine translation data.

Findings

One algorithm successfully corrected errors, the other did not

Error modeling impacted correction performance

Analysis of algorithm failure reasons provided

Abstract

Correction of Noisy Natural Language Text is an important and well studied problem in Natural Language Processing. It has a number of applications in domains like Statistical Machine Translation, Second Language Learning and Natural Language Generation. In this work, we consider some statistical techniques for Text Correction. We define the classes of errors commonly found in text and describe algorithms to correct them. The data has been taken from a poorly trained Machine Translation system. The algorithms use only a language model in the target language in order to correct the sentences. We use phrase based correction methods in both the algorithms. The phrases are replaced and combined to give us the final corrected sentence. We also present the methods to model different kinds of errors, in addition to results of the working of the algorithms on the test set. We show that one of the approaches fail to achieve the desired goal, whereas the other succeeds well. In the end, we analyze the possible reasons for such a trend in performance.