T
Tim Vieira
Researcher at Johns Hopkins University
Publications - 35
Citations - 624
Tim Vieira is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Computer science & Spanning tree. The author has an hindex of 9, co-authored 29 publications receiving 413 citations.
Papers
More filters
Proceedings ArticleDOI
Universal Decompositional Semantics on Universal Dependencies.
Aaron Steven White,Dee Ann Reisinger,Keisuke Sakaguchi,Tim Vieira,Sheng Zhang,Rachel Rudinger,Kyle Rawlins,Benjamin Van Durme +7 more
TL;DR: A framework for augmenting data sets from the Universal Dependencies project with Universal Decompositional Semantics, and describes results from annotating the English Universal Dependency treebank, dealing with word senses, semantic roles, and event properties.
Journal ArticleDOI
Reasoning about Quantities in Natural Language
Subhro Roy,Tim Vieira,Dan Roth +2 more
TL;DR: A computational approach is developed which is shown to successfully recognize and normalize textual expressions of quantities and is used to further develop algorithms to assist reasoning in the context of the aforementioned tasks.
Posted Content
If beam search is the answer, what was the question?
TL;DR: It is found that beam search enforces uniform information density in text, a property motivated by cognitive science, and suggests a set of decoding objectives that explicitly enforce this property and finds that exact decoding with these objectives alleviates the problems encountered when decoding poorly calibrated language generation models.
Proceedings ArticleDOI
A Joint Model of Orthography and Morphological Segmentation
TL;DR: A model of morphological segmentation that jointly learns to segment and restore orthographic changes, e.g., funniest7! fun-y-est, is presented and an importance sampling algorithm for approximate inference is derived.
Journal Article
Relation Alignment for Textual Entailment Recognition.
Mark Sammons,V. G. Vinod Vydiswaran,Tim Vieira,Nikhil Johri,Ming-Wei Chang,Dan Goldwasser,Vivek Srikumar,Gourab Kundu,Yuancheng Tu,Kevin Small,Joshua Rule,Quang Do,Dan Roth +12 more
TL;DR: An approach to textual entailment recognition is presented, in which inference is based on a shallow semantic representation of relations in the text and hypothesis of the entailment pair, and in which specialized knowledge is encapsulated in modular components with very simple interfaces.