David Chiang

David Chiang

Auto-generated profile, based on publicly available information

David Chiang

Computer Science and Engineering University of Notre Dame Notre Dame IN USA

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 May 2024 in Transactions of the Association for Computational Linguistics
Verified
Journal Article
Open access
PDF file
LSLena Strobl
Lena Strobl
WMWilliam Merrill
William Merrill
GWGail Weiss
Gail Weiss
DCDavid Chiang
David Chiang
DADana Angluin
Dana Angluin
As transformers have gained prominence in natural language processing, some researchers have investigated theoretically what problems they can and cannot solve, by treating problems as formal languages. Exploring such questions can help clarify the power of transformers relative to other models of computation, their fundamental capabilities and limits, and the impact of architectural choices. Work in this subarea has made considerable progress in recent years. Here, we undertake a comprehensive survey of this work, documenting the diverse assumptions that underlie different results and providing a unified framework for harmonizing seemingly contradictory findings.

1 January 2013
Verified
Conference Paper
Open access
PDF file
AVAshish Vaswani
Ashish Vaswani
YZYinggong Zhao
Yinggong Zhao
VFVictoria Fossum
Victoria Fossum
DCDavid Chiang
David Chiang
Ashish Vaswani, Yinggong Zhao, Victoria Fossum, David Chiang. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. 2013.

1 January 2024
Verified
Conference Paper
Open access
PDF file
FFFahim Faisal
Fahim Faisal
OAOrevaoghene Ahia
Orevaoghene Ahia
ASAarohi Srivastava
Aarohi Srivastava
KAKabir Ahuja
Kabir Ahuja
DCDavid Chiang
David Chiang
AAAntonios Anastasopoulos
Antonios Anastasopoulos
Fahim Faisal, Orevaoghene Ahia, Aarohi Srivastava, Kabir Ahuja, David Chiang, Yulia Tsvetkov, Antonios Anastasopoulos. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

1 June 2006 in Journal of Computational Biology
Verified
Journal Article
Closed access
DCDavid Chiang
David Chiang
AJAravind K. Joshi
Aravind K. Joshi
DSDavid B. Searls
David B. Searls
Since the first application of context-free grammars to RNA secondary structures in 1988, many researchers have used both ad hoc and formal methods from computational linguistics to model RNA and protein structure. We show how nearly all of these methods are based on the same core principles and can be converted into equivalent approaches in the framework of tree-adjoining grammars and related formalisms. We also propose some new approaches that extend these core principles in novel ways.

25 June 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SGSamuel Grieggs
Samuel Grieggs
BSBingyu Shen
Bingyu Shen
GRGreta Rauch
Greta Rauch
PLPei Li
Pei Li
JMJiaqi Ma
Jiaqi Ma
WSWalter J. Scheirer
Walter J. Scheirer
In this paper, we consider how to incorporate psychophysical measurements of human visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can reduce errors. As a case study to assess the viability of this approach, we look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. Here we describe a general enhancement strategy, underpinned by the new loss formulation, which can be applied to the training regime of any deep learning-based document transcription system. Through experimentation, reliable performance improvement is demonstrated for the standard IAM and RIMES datasets for three different network architectures. Further, we go on to show feasibility for our approach on a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall in the the 9th century.

6 April 2023 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
DCDavid Chiang
David Chiang
CMColin McDonald
Colin McDonald
CSChung-Chieh Shan
Chung-Chieh Shan
Recursive calls over recursive data are useful for generating probability distributions, and probabilistic programming allows computations over these distributions to be expressed in a modular and intuitive way. Exact inference is also useful, but unfortunately, existing probabilistic programming languages do not perform exact inference on recursive calls over recursive data, forcing programmers to code many applications manually. We introduce a probabilistic language in which a wide variety of recursion can be expressed naturally, and inference carried out exactly. For instance, probabilistic pushdown automata and their generalizations are easy to express, and polynomial-time parsing algorithms for them are derived automatically. We eliminate recursive data types using program transformations related to defunctionalization and refunctionalization. These transformations are assured correct by a linear type system, and a successful choice of transformations, if there is one, is guaranteed to be found by a greedy algorithm.