215 citations · 1.3k across the 64 of their papers we have counts for
14 papers · 1 filter
Quantification and Analysis of Scientific Language Variation Across Research Fields
Pei Zhou, Muhao Chen, Kai-Wei Chang +1
Quantifying differences in terminologies from various academic domains has been a longstanding problem yet to be solved. We propose a computational approach for analyzing linguisti…
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
Tianlu Wang, Jieyu Zhao, Mark Yatskar +2
In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables --such as gender-- in visual recognition tasks. We show that train…
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
Wasi Uddin Ahmad, Zhisong Zhang, Xuezhe Ma +3
Different languages might have different word orders. In this paper, we investigate cross-lingual transfer and posit that an order-agnostic model will perform better when transferr…
Learning Robust, Transferable Sentence Representations for Text Classification
Wasi Uddin Ahmad, Xueying Bai, Nanyun Peng +1
Despite deep recurrent neural networks (RNNs) demonstrate strong performance in text classification, training RNN models are often expensive and requires an extensive collection of…
Learning Gender-Neutral Word Embeddings
Jieyu Zhao, Yichao Zhou, Zeyu Li +2
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora…
Robust Text Classifier on Test-Time Budgets
Md Rizwan Parvez, Tolga Bolukbasi, Kai-Wei Chang +1
We propose a generic and interpretable learning framework for building robust text classification model that achieves accuracy comparable to full models under test-time budget cons…