Hal Daumé Iii

Hal Daumé Iii

Auto-generated profile, based on publicly available information

Hal Daumé Iii

University of Maryland

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
14 March 2009 in Machine Learning
Verified
Journal Article
Open access
PDF file
HDHal Daumé
Hal Daumé
JLJohn Langford
John Langford
DMDaniel Marcu
Daniel Marcu
We present Searn, an algorithm for integrating search and learning to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision. Searn is a meta-algorithm that transforms these complex problems into simple classification problems to which any binary classifier may be applied. Unlike current algorithms for structured learning that require decomposition of both the loss function and the feature functions over the predicted structure, Searn is able to learn prediction functions for any loss function and any class of features. Moreover, Searn comes with a strong, natural theoretical guarantee: good performance on the derived classification problems implies good performance on the structured prediction problem.

3 November 2021 in Computational Linguistics
Verified
Journal Article
Open access
PDF file
YCYang Trista Cao
Yang Trista Cao
HDHal Daumé
Hal Daumé
Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systematic biases in coreference resolution systems, including biases that can harm binary and non-binary trans and cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and investigate where in the machine learning pipeline such biases can enter a coreference resolution system. We inspect many existing data sets for trans-exclusionary biases, and develop two new data sets for interrogating bias in both crowd annotations and in existing coreference resolution systems. Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we will build systems that fail for: quality of service, stereotyping, and over- or under-representation, especially for binary and non-binary trans users.

29 May 2020 in arXiv
Verified
Preprint
Open access
PDF file
SBSu Lin Blodgett
Su Lin Blodgett
SBSolon Barocas
Solon Barocas
HIHal Daumé Iii
Hal Daumé Iii
HWHanna Wallach
Hanna Wallach
We survey 146 papers analyzing "bias" in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing "bias" is an inherently normative process. We further find that these papers' proposed quantitative techniques for measuring or mitigating "bias" are poorly matched to their motivations and do not engage with the relevant literature outside of NLP. Based on these findings, we describe the beginnings of a path forward by proposing three recommendations that should guide work analyzing "bias" in NLP systems. These recommendations rest on a greater recognition of the relationships between language and social hierarchies, encouraging researchers and practitioners to articulate their conceptualizations of "bias"---i.e., what kinds of system behaviors are harmful, in what ways, to whom, and why, as well as the normative reasoning underlying these statements---and to center work around the lived experiences of members of communities affected by NLP systems, while interrogating and reimagining the power relations between technologists and such communities.

1 January 2023
Verified
Conference Paper
Open access
PDF file
ASArjun Subramonian
Arjun Subramonian
XYXingdi Yuan
Xingdi Yuan
HIHal Daumé Iii
Hal Daumé Iii
SBSu Lin Blodgett
Su Lin Blodgett
Arjun Subramonian, Xingdi Yuan, Hal Daumé III, Su Lin Blodgett. Findings of the Association for Computational Linguistics: ACL 2023. 2023.

1 January 2019
Verified
Conference Paper
Open access
PDF file
SRSudha Rao
Sudha Rao
HIHal Daumé Iii
Hal Daumé Iii
Sudha Rao, Hal Daumé III. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.

1 January 2023
Verified
Conference Paper
Open access
PDF file
NGNavita Goyal
Navita Goyal
EBEleftheria Briakou
Eleftheria Briakou
ALAmanda Liu
Amanda Liu
CBConnor Baumler
Connor Baumler
CBClaire Bonial
Claire Bonial
HIHal Daumé Iii
Hal Daumé Iii
Navita Goyal, Eleftheria Briakou, Amanda Liu, Connor Baumler, Claire Bonial, Jeffrey Micher, Clare Voss, Marine Carpuat, Hal Daumé III. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.