D
David Chiang
Researcher at University of Notre Dame
Publications - 173
Citations - 7893
David Chiang is an academic researcher from University of Notre Dame. The author has contributed to research in topics: Machine translation & Internal medicine. The author has an hindex of 33, co-authored 132 publications receiving 7482 citations. Previous affiliations of David Chiang include University of Pennsylvania & University of Southern California.
Papers
More filters
Posted Content
An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages
TL;DR: This work presents a model that combines Dyer et al.'s reparameterization of IBM Model 2 (fast-align) and k-means clustering using Dynamic Time Warping as a distance metric and performs significantly better than both a neural model and a strong baseline.
Posted Content
Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource
Antonios Anastasopoulos,Marika Lekakou,Josep Quer,Eleni Zimianiti,Justin DeBenedetto,David Chiang +5 more
TL;DR: This work evaluates POS tagging techniques on an actual endangered language, Griko, and shows that the combination of a semi-supervised method with cross-lingual transfer is more appropriate for this extremely challenging setting, with the best tagger achieving an accuracy of 72.9%.
Proceedings Article
Rule Markov Models for Fast Tree-to-String Translation
TL;DR: Large-scale experiments on a state-of-the-art tree-to-string translation system show that this approach leads to a slimmer model, a faster decoder, yet the same translation quality as composed rules.
Proceedings ArticleDOI
Growing Graphs from Hyperedge Replacement Graph Grammars
TL;DR: In this paper, a graph's clique tree can be used to extract a hyperedge replacement grammar, which can be stored in an ordering from the extraction process, and the extracted graph grammar is guaranteed to generate an isomorphic copy of the original graph.
Posted Content
Auto-Sizing Neural Networks: With Applications to n-gram Language Models
Kenton Murray,David Chiang +1 more
TL;DR: This paper introduced a method for automatically adjusting network size by pruning out hidden units through the regularization of hidden unit weights and showed that these smaller neural models maintain the significant improvements of their unpruned versions.