Verb Semantics and Lexical Selection

TLDR

The approach aligns with knowledge‑based machine translation and can be integrated as a component in existing systems. The study proposes a novel verb representation scheme to improve lexical selection in machine translation. The authors examine English and Chinese verb groups, basing selection on sentence interpretation and argument restrictions, and compare the scheme to transfer‑based MT representations. Experimental results demonstrate that the scheme enables correct lexical selection even with inexact matches.

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.