Knowledge Enhanced Contextual Word Representations
- Matthew E. Peters, Mark Neumann, Noah A. Smith
- Computer ScienceConference on Empirical Methods in Natural…
- 9 September 2019
After integrating WordNet and a subset of Wikipedia into BERT, the knowledge enhanced BERT (KnowBert) demonstrates improved perplexity, ability to recall facts as measured in a probing task and downstream performance on relationship extraction, entity typing, and word sense disambiguation.
Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples
- V. Joshi, Matthew E. Peters, Mark Hopkins
- Computer ScienceAnnual Meeting of the Association for…
- 16 May 2018
It is shown that recent advances in word representations greatly diminish the need for domain adaptation when the target domain is syntactically similar to the source domain, and a simple way to adapt a parser using only dozens of partial annotations is provided.
Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers
- Mark Hopkins, Cristian Petrescu-Prahova, Roie Levin, Ronan Le Bras, Alvaro Herrasti, V. Joshi
- Computer ScienceConference on Empirical Methods in Natural…
- 1 September 2017
We present an approach for answering questions that span multiple sentences and exhibit sophisticated cross-sentence anaphoric phenomena, evaluating on a rich source of such questions – the math…
Interactive Visualization for Linguistic Structure
- A. Sarnat, V. Joshi, Cristian Petrescu-Prahova, Alvaro Herrasti, Brandon Stilson, Mark Hopkins
- Computer ScienceConference on Empirical Methods in Natural…
- 1 September 2017
The library is not tied to any particular linguistic representation, but provides a general-purpose API for the interactive exploration of hierarchical linguistic structure, and offers several important features, including expand/collapse functionality, positional and color cues, and explicit visual support for sequential structure.