Decomp

The Decompositional Semantics Initiative (Decomp), which is joint work with Ben Van Durme and Kyle Rawlins at Johns Hopkins University, is a collection of efforts aimed at collecting and modeling human annotations of meaning via the decomposition of lexical and phrasal meanings into a small set of component parts. Decomp is supported by a DARPA AIDA grant (HR001117S0026-AIDA-FP-013).

Decomp is a large project and so only research products authored by core FACTS.lab members are listed below. A full list of publications, presentations, and available data can be found at decomp.net.

Papers

Rudinger, R., A. S. White, & B. Van Durme. (2018). Neural Models of Factuality. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics, New Orleans, LA, June 1 – June 6, 2018.

Poliak, A., A. Haldar, R. Rudinger, J.E. Hu, E. Pavlick, A. S. White, & B. Van Durme. (2018). Towards a Unified Natural Language Inference Framework to Evaluate Sentence Representations. arXiv:1804.08207v1 [cs.CL]

White, A. S., P. Rastogi, K. Duh, & B. Van Durme. (2017). Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework. Proceedings of the The 8th International Joint Conference on Natural Language Processing, pages 996–1005, Taipei, Taiwan, November 27 – December 1, 2017.

White, A. S., K. Rawlins, & B. Van Durme. (2017). The Semantic Proto-Role Linking Model. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pages 92–98, Valencia, Spain, April 3-7, 2017.

White, A. S., D. Reisinger, K. Sakaguchi, T. Vieira, S. Zhang, R. Rudinger, K. Rawlins, & B. Van Durme. (2016). Universal decompositional semantics on universal dependencies. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1713–1723, Austin, Texas, November 1-5, 2016.

Presentations

Rudinger, R., A. S. White, & B. Van Durme. (2018). Neural Models of Factuality. To be given at the 2018 Conference of the North American Chapter of the Association for Computational Linguistics, New Orleans, LA, June 1 – June 6, 2018.

White, A. S., P. Rastogi, K. Duh, & B. Van Durme. (2017). Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework. Presented at the 8th International Joint Conference on Natural Language Processing. Taipei, Taiwan, November 27-December 1, 2017.

White, A. S., K. Rawlins, & B. Van Durme. (2017). The Semantic Proto-Role Linking Model. Presented at the 15th Conference of the European Chapter of the Association for Computational Linguistics. Valencia, Spain. April 3-7, 2017.

MegaAttitude

The MegaAttitude Project, which is joint work with Kyle Rawlins at Johns Hopkins University, aims to collect large-scale annotation sets of the selectional behavior of clause-embedding verbs, adjectives, and nouns, based on human acceptability, veridicality, and similarity judgments. It is supported by a National Science Foundation collaborative grant (BCS-1748969/BCS-1749025).

Papers

White, A. S. & K. Rawlins. (2018). The role of veridicality and factivity in clause selection. To appear in the Proceedings of the 48th Meeting of the North East Linguistic Society.

White, A. S. & K. Rawlins. (2016). A computational model of S-selection. In Semantics and Linguistic Theory 26, 641-663. Ithaca, NY: CLC Publications.

Presentations

White, A. S. (2017). Computational approaches to clause selection. Invited talk given at Selectionfest 2017. Humboldt University of Berlin and ZAS Berlin. Berlin, Germany. November 10-11, 2017.

White, A. S. & K. Rawlins. (2017). The role of veridicality and factivity in clause selection. Presented at the 48th annual meeting of the North East Linguistic Society, University of Iceland. October 27-29, 2017.

White, A. S. & K. Rawlins. (2017). Entropy predicts uncertainty in subcategorization frame distributions. Presented at the 39th Annual Conference of the German Linguistic Society, AG1: Information-theory based modeling of linguistic variation in context, Saarland University. March 8-10, 2017.

White, A. S. & K. Rawlins. (2016). A computational model of S-selection. Presented at Semantics and Linguistic Theory 26, University of Texas, Austin. May 12-15, 2016.