Elizabeth Boschee

Elizabeth Boschee

Auto-generated profile, based on publicly available information

Elizabeth Boschee

Information Sciences Institute University of Southern California

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 January 2019
Verified
Conference Paper
Open access
PDF file
XHXiao Huang
Xiao Huang
LDLi Dong
Li Dong
EBElizabeth Boschee
Elizabeth Boschee
NPNanyun Peng
Nanyun Peng
Xiao Huang, Li Dong, Elizabeth Boschee, Nanyun Peng. Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL). 2019.

1 January 2023
Verified
Conference Paper
Open access
PDF file
CJChris Jenkins
Chris Jenkins
SAShantanu Agarwal
Shantanu Agarwal
JBJoel Barry
Joel Barry
SFSteven Fincke
Steven Fincke
EBElizabeth Boschee
Elizabeth Boschee
Chris Jenkins, Shantanu Agarwal, Joel Barry, Steven Fincke, Elizabeth Boschee. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). 2023.

1 January 2023
Verified
Conference Paper
Open access
PDF file
DLDong-Ho Lee
Dong-Ho Lee
RSRavi Kiran Selvam
Ravi Kiran Selvam
SSSheikh Muhammad Sarwar
Sheikh Muhammad Sarwar
BLBill Yuchen Lin
Bill Yuchen Lin
FMFred Morstatter
Fred Morstatter
XRXiang Ren
Xiang Ren
Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, Xiang Ren. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

16 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
DLDong-Ho Lee
Dong-Ho Lee
RKRahul Khanna
Rahul Khanna
BLBill Yuchen Lin
Bill Yuchen Lin
JCJamin Chen
Jamin Chen
SLSeyeon Lee
Seyeon Lee
XRXiang Ren
Xiang Ren
Successfully training a deep neural network demands a huge corpus of labeled data. However, each label only provides limited information to learn from and collecting the requisite number of labels involves massive human effort. In this work, we introduce LEAN-LIFE, a web-based, Label-Efficient AnnotatioN framework for sequence labeling and classification tasks, with an easy-to-use UI that not only allows an annotator to provide the needed labels for a task, but also enables LearnIng From Explanations for each labeling decision. Such explanations enable us to generate useful additional labeled data from unlabeled instances, bolstering the pool of available training data. On three popular NLP tasks (named entity recognition, relation extraction, sentiment analysis), we find that using this enhanced supervision allows our models to surpass competitive baseline F1 scores by more than 5-10 percentage points, while using 2X times fewer labeled instances. Our framework is the first to utilize this enhanced supervision technique and does so for three important tasks -- thus providing improved annotation recommendations to users and an ability to build datasets of (data, label, explanation) triples instead of the regular (data, label) pair.

13 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
QYQinyuan Ye
Qinyuan Ye
XHXiao Huang
Xiao Huang
EBElizabeth Boschee
Elizabeth Boschee
XRXiang Ren
Xiang Ren
Advances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples. In contrast, humans are typically able to generalize with only a few examples, relying on deeper underlying world knowledge, linguistic sophistication, and/or simply superior deductive powers. In this paper, we focus on "teaching" machines reading comprehension, using a small number of semi-structured explanations that explicitly inform machines why answer spans are correct. We extract structured variables and rules from explanations and compose neural module teachers that annotate instances for training downstream MRC models. We use learnable neural modules and soft logic to handle linguistic variation and overcome sparse coverage; the modules are jointly optimized with the MRC model to improve final performance. On the SQuAD dataset, our proposed method achieves 70.14% F1 score with supervision from 26 explanations, comparable to plain supervised learning using 1,100 labeled instances, yielding a 12x speed up.

5 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
SAShantanu Agarwal
Shantanu Agarwal
JBJoel Barry
Joel Barry
EBElizabeth Boschee
Elizabeth Boschee
SMScott Miller
Scott Miller
Machine Translation for English Retrieval of Information in Any Language (MATERIAL) is an IARPA initiative targeted to advance the state of cross-lingual information retrieval (CLIR). This report provides a detailed description of Information Sciences Institute's (ISI's) Summarization and domain-Adaptive Retrieval Across Language's (SARAL's) effort for MATERIAL. Specifically, we outline our team's novel approach to handle CLIR with emphasis in developing an approach amenable to retrieve a query-relevant document \textit{set}, and not just a ranked document-list. In MATERIAL's Phase-3 evaluations, SARAL exceeded the performance of other teams in five out of six evaluation conditions spanning three different languages (Farsi, Kazakh, and Georgian).