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

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

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.