Verb Semantics and Lexical Selection

TL;DR

This paper proposes a new semantic representation scheme for verbs to improve lexical selection in machine translation, demonstrating that inexact matches can yield correct translations by considering sentence interpretation.

Contribution

A novel semantic representation approach for verbs that enhances lexical selection accuracy in machine translation systems, especially for inexact matches.

Findings

Inexact matches can lead to correct lexical selection using the new scheme.

The approach aligns with knowledge-based MT and can be integrated into existing systems.

Experimental results support the effectiveness of the proposed representation.

Abstract

This paper will focus on the semantic representation of verbs in computer systems and its impact on lexical selection problems in machine translation (MT). Two groups of English and Chinese verbs are examined to show that lexical selection must be based on interpretation of the sentence as well as selection restrictions placed on the verb arguments. A novel representation scheme is suggested, and is compared to representations with selection restrictions used in transfer-based MT. We see our approach as closely aligned with knowledge-based MT approaches (KBMT), and as a separate component that could be incorporated into existing systems. Examples and experimental results will show that, using this scheme, inexact matches can achieve correct lexical selection.