Multi-Level Alignments As An Extensible Representation Basis for Textual Entailment Algorithms

Tae-Gil Noh, Sebastian Padó, Vered Shwartz, Ido Dagan, Vivi Nastase, Kathrin Eichler, Lili Kotlerman, Meni Adler

In: Proceedings of *SEM 2015. Joint Conference on Lexical and Computational Semantics (*SEM-15) located at NAACL 2015 June 4-5 Denver Colorado United States ACL 2015.


A major problem in research on Textual Entailment (TE) is the high implementation effort for TE systems. Recently, interoperable standards for annotation and preprocessing have been proposed. In contrast, the algorithmic level remains unstandardized, which makes component re-use in this area very difficult in practice. In this paper, we introduce multi-level alignments as a central, powerful representation for TE algorithms that encourages modular, reusable, multilingual algorithm development. We demonstrate that a pilot open-source implementation of multi-level alignment with minimal features competes with state-of-theart open-source TE engines in three languages.


German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz