Abstract
We introduce a new formal semantic model for annotating textual entailments that describes restrictive, intersective, and appositive modification. The model contains a formally defined interpreted lexicon, which specifies the inventory of symbols and the supported semantic operators, and an informally defined annotation scheme that instructs annotators in which way to bind words and constructions from a given pair of premise and hypothesis to the interpreted lexicon. We explore the applicability of the proposed model to the Recognizing Textual Entailment (RTE) 1–4 corpora and describe a first-stage annotation scheme on which we based the manual annotation work. The constructions we annotated were found to occur in 80.65% of the entailments in RTE 1–4 and were annotated with cross-annotator agreement of 68% on average. The annotated parts of the RTE corpora are publicly available for further research.
Highlights
The Recognizing Textual Entailment (RTE) challenges (Dagan et al 2006) aim to assess a system’s ability to automatically determine whether an entailment relation obtains between a naturally occur-LiLT Volume 9 Perspectives on Semantic Representations for Textual Inference
The model we propose in this work diverges from these approaches in two respects: (a) its first goal is to develop gold standard semantic annotations based on a general formal semantic model; (b) it does not aim to represent phenomena that are not accounted for in this model
We have described an on-going attempt to establish a model for analyzing entailment data as specified in the RTE challenges
Summary
The Recognizing Textual Entailment (RTE) challenges (Dagan et al 2006) aim to assess a system’s ability to automatically determine whether an entailment relation obtains between a naturally occur-. We aim to contribute toward creating a benchmark for modeling entailment recognition We presume that this goal is to be achieved incrementally by modeling increasingly complex semantic phenomena. To this end, we employ a standard model-theoretic approach to entailment that allows combining gold standard annotations with a computational framework. In the course of the development of this model, a narrower annotation scheme was adopted In this scheme, modification phenomena were annotated in all valid entailment pairs from RTE 1–4 without accounting for the way in which the annotated phenomena contributed to the inference being made.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
