Academic Commons

Abstracts (Summaries)

Detecting and Correcting Syntactic Errors in Machine Translation Using Feature-Based Lexicalized Tree Adjoining Grammars

Ma, Wei-Yun; McKeown, Kathleen

Statistical machine translation has made tremendous progress over the past ten years. The output of even the best systems, however, is often ungrammatical because of the lack of sufficient linguistic knowledge. Even when systems incorporate syntax in the translation process, syntactic errors still result. To address this issue, we present a novel approach for detecting and correcting ungrammatical translations. In order to simultaneously detect
multiple errors and their corresponding words in a formal framework, we use feature-based lexicalized tree adjoining grammars (FB-LTAG). In FB-LTAG, each lexical item is associated with a syntactic elementary tree, in which each node is associated with a set of feature-value pairs, called Attribute Value Matrices (AVMs). AVMs define the lexical item’s syntactic usage. Our syntactic error detection works by checking the AVM values of all lexical items within a sentence using a unification framework. Thus, we use the feature structures in the AVMs to detect the error type and corresponding words. In order to simultaneously detect multiple error types and track their corresponding words, we propose a new unification method which allows the unification procedure to continue when unification fails and also to propagate the failure information to relevant words. We call the modified unification a fail propagation unification. Our approach features: 1) the use of XTAG grammar, a rule-based English grammar developed by linguists using the FB-LTAG formalism, 2) the ability to simultaneously detect multiple ungrammatical types and their corresponding words by using FB-LTAG’s feature unifications, and 3) the ability to simultaneously correct multiple ungrammatical types based on the detection information. Grammar checking methods are usually divided into three classes: statistic-based checking, rule-based checking and syntax-based checking. Our approach is a mix of rule-based checking and syntax-based checking: The XTAG English grammar is designed by linguists while the detecting procedure is based on syntactic operations which dynamically reference the grammar. In our procedure for syntactic error detection, we first decomposes each sentence hypothesis parse tree into elementary trees, followed by associating each elementary tree with AVMs through look-up in the XTAG grammar, and finally reconstruct the original parse tree out of the elementary trees using substitution and adjunction operations along with AVM unifications with fail propagation ability. Once error types and their corresponding words are detected, one is able to correct errors based on a unified consideration of all related words under the same error types. In this paper, we present some simple mechanism to handle part of the detected situations. We use our approach to detect and correct translations of six single statistical machine translation systems. The results show that most of the corrected translations are improved.

Files

More About This Work

Academic Units
Computer Science
Published Here
April 24, 2013
Academic Commons provides global access to research and scholarship produced at Columbia University, Barnard College, Teachers College, Union Theological Seminary and Jewish Theological Seminary. Academic Commons is managed by the Columbia University Libraries.