Search Results for author: Rebecca Hwa

Found 21 papers, 4 papers with code

Contrapositive Local Class Inference

1 code implementation WNUT (ACL) 2021 Omid Kashefi, Rebecca Hwa

Certain types of classification problems may be performed at multiple levels of granularity; for example, we might want to know the sentiment polarity of a document or a sentence, or a phrase.

Quantifying the Evaluation of Heuristic Methods for Textual Data Augmentation

no code implementations EMNLP (WNUT) 2020 Omid Kashefi, Rebecca Hwa

Data augmentation has been shown to be effective in providing more training data for machine learning and resulting in more robust classifiers.

Data Augmentation

Tribe or Not? Critical Inspection of Group Differences Using TribalGram

no code implementations16 Mar 2023 Yongsu Ahn, Muheng Yan, Yu-Ru Lin, Wen-Ting Chung, Rebecca Hwa

With the rise of AI and data mining techniques, group profiling and group-level analysis have been increasingly used in many domains including policy making and direct marketing.

Interpretable Machine Learning Marketing

ArgRewrite V.2: an Annotated Argumentative Revisions Corpus

no code implementations3 Jun 2022 Omid Kashefi, Tazin Afrin, Meghan Dale, Christopher Olshefski, Amanda Godley, Diane Litman, Rebecca Hwa

The variety of revision unit scope and purpose granularity levels in ArgRewrite, along with the inclusion of new types of meta-data, can make it a useful resource for research and applications that involve revision analysis.

Self-Driving Cars

Domain-robust VQA with diverse datasets and methods but no target labels

no code implementations CVPR 2021 Mingda Zhang, Tristan Maidment, Ahmad Diab, Adriana Kovashka, Rebecca Hwa

The observation that computer vision methods overfit to dataset specifics has inspired diverse attempts to make object recognition models robust to domain shifts.

Object Recognition Question Answering +3

Heuristically Informed Unsupervised Idiom Usage Recognition

no code implementations EMNLP 2018 Changsheng Liu, Rebecca Hwa

This information then serves as a form of distant supervision to guide the unsupervised training process for the probabilistic models.

Machine Translation Sentiment Analysis

An Interactive Tool for Natural Language Processing on Clinical Text

no code implementations6 Jul 2017 Gaurav Trivedi, Phuong Pham, Wendy Chapman, Rebecca Hwa, Janyce Wiebe, Harry Hochheiser

Natural Language Processing (NLP) systems often make use of machine learning techniques that are unfamiliar to end-users who are interested in analyzing clinical records.

BIG-bench Machine Learning

A Comparison of MT Errors and ESL Errors

no code implementations LREC 2014 Homa B. Hashemi, Rebecca Hwa

We describe a method for the automatic classification of MT errors according to English as a Second Language (ESL) error categories and conduct a large comparison experiment that includes both high-performing and low-performing translate-to-English MT systems for several source languages.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.