Sequence Classification with Human Attention

2018-10-01CONLL 2018Code Available0· sign in to hype

Maria Barrett, Joachim Bingel, Nora Hollenstein, Marek Rei, Anders S{\o}gaard

Code Available — Be the first to reproduce this paper.

Code

github.com/coastalcph/Sequence_classification_with_human_attention
OfficialIn papertf★ 0

Abstract

Learning attention functions requires large volumes of data, but many NLP tasks simulate human behavior, and in this paper, we show that human attention really does provide a good inductive bias on many attention functions in NLP. Specifically, we use estimated human attention derived from eye-tracking corpora to regularize attention functions in recurrent neural networks. We show substantial improvements across a range of tasks, including sentiment analysis, grammatical error detection, and detection of abusive language.

Tasks

Abusive Language Classification General Classification Grammatical Error Detection Inductive Bias Sentiment Analysis

Sequence Classification with Human Attention

Code

Abstract

Tasks

Reproductions