Advancing NLP with Cognitive Language Processing Signals

Nora Hollenstein, Maria Barrett, Marius Troendle, Francesco Bigiolli, Nicolas Langer +1 more
4/4/2019
cs.CL

Official code: DS3Lab/zuco-nlp (32 stars, last commit 2019-06-24). 1 more implementation below.

Abstract

When we read, our brain processes language and generates cognitive processing data such as gaze patterns and brain activity. These signals can be recorded while reading. Cognitive language processing data such as eye-tracking features have shown improvements on single NLP tasks. We analyze whether using such human features can show consistent improvement across tasks and data sources. We present an extensive investigation of the benefits and limitations of using cognitive processing data for NLP. Specifically, we use gaze and EEG features to augment models of named entity recognition, relation classification, and sentiment analysis. These methods significantly outperform the baselines and show the potential and current limitations of employing human language processing data for NLP.

View on arXivView PDF

Code Implementations(2)

DS3Lab/zuco-nlpOfficial100%

All NLP experiments described in ArXiv paper 1904.02682

3211Perl, PythonMar 12, 20197 years ago
DS3Lab/ner-at-first-sightOfficial100%

This repository contains the data used for the paper "Entity Recognition at First Sight: Improving NER with Eye Movement Information" by Nora Hollenstein & Ce Zhang (accepted at NAACL 2019)

123Feb 26, 20196 years ago

Similar Papers

Integrating Cognitive Processing Signals into Language Models: A Review of Advances, Applications and Future Directions

88% match2025

Integrating LLM, EEG, and Eye-Tracking Biomarker Analysis for Word-Level Neural State Classification in Semantic Inference Reading Comprehension

87% match2023

Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs

87% match2026

Synthesizing Human Gaze Feedback for Improved NLP Performance

86% match2023

Assessing Cognitive Effort in L2 Idiomatic Processing: An Eye-Tracking Dataset

86% match2026

WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset

86% match1 repo82023

Cite this paper

@article{hollenstein2019advancing,
  title  = {Advancing NLP with Cognitive Language Processing Signals},
  author = {Nora Hollenstein and Maria Barrett and Marius Troendle and Francesco Bigiolli and Nicolas Langer and Ce Zhang},
  year   = {2019},
  eprint = {1904.02682},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.02682}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.02682.svg)](https://codeofpaper.com/paper/1904.02682)

Discussion