Advancing NLP with Cognitive Language Processing Signals

Published in

arXiv.org(2019)

External Links:

Generate Graph

TL;DR

This work uses gaze and EEG features to augment models of named entity recognition, relation classification, and sentiment analysis and shows the potential and current limitations of employing human language processing data for NLP.

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.

Authors

N. Langer

2 papers

Nora Hollenstein

2 papers

Maria Barrett

2 papers

References56 items

Thinking theta and alpha: Mechanisms of intuitive and analytical reasoning

Entity Recognition at First Sight: Improving NER with Eye Movement Information

ZuCo, a simultaneous EEG and eye-tracking resource for natural sentence reading

Sequence Classification with Human Attention

Cognitively Inspired Natural Language Processing

Advancing NLP with Cognitive Language Processing Signals

Published in

arXiv.org(2019)

External Links:

Generate Graph

TL;DR

Abstract

Authors

N. Langer

2 papers

Nora Hollenstein

2 papers

Maria Barrett

2 papers

References56 items

Thinking theta and alpha: Mechanisms of intuitive and analytical reasoning

Entity Recognition at First Sight: Improving NER with Eye Movement Information

ZuCo, a simultaneous EEG and eye-tracking resource for natural sentence reading

Sequence Classification with Human Attention

Cognitively Inspired Natural Language Processing

Marius Troendle

1 papers

Francesco Bigiolli

1 papers

The Hitchhiker’s Guide to Testing Statistical Significance in Natural Language Processing

Finding syntax in human encephalography with beam search

Learning to Predict Readability Using Eye-Movement Data From Natives and Learners

ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and Convolutional Neural Networks for Relation Classification and Extraction

Using Gaze Data to Predict Multiword Expressions

Multi-Task Learning for Commercial Brain Computer Interfaces

Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets

Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets

Latent Multi-Task Architecture Learning

Sluice networks: Learning what to share between loosely related tasks

Presenting GECO: An eyetracking corpus of monolingual and bilingual sentence reading

Identifying beneficial task relations for multi-task learning in deep neural networks

Evaluation of temporal stability of eye tracking algorithms using webcams

What to do about non-standard (or non-canonical) language in NLP

Weakly Supervised Part-of-speech Tagging Using Eye-tracking Data

Leveraging Cognitive Features for Sentiment Analysis

Evaluating word embeddings with fMRI and eye-tracking

WebGazer: Scalable Webcam Eye Tracking Using User Interactions

Improving sentence compression by learning to predict gaze

Neural Architectures for Named Entity Recognition

Reading behavior predicts syntactic categories

GloVe: Global Vectors for Word Representation

Predicting term-relevance from brain signals

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

Efficient Estimation of Word Representations in Vector Space

Alpha-band oscillations, attention, and controlled access to stored information

Coregistration of eye movements and EEG in natural reading: analyses and review.

Evaluation of consumer EEG device Emotiv EPOC

Natural Language Processing (Almost) from Scratch

Real-time eye gaze tracking with an unmodified commodity webcam employing a neural network

Emotion classification based on gamma-band EEG

Low-cost gaze interaction: ready to deliver the promises

Data from eye-tracking corpora as evidence for theories of syntactic processing complexity

Synchronizing timelines: Relations between fixation durations and N400 amplitudes during sentence reading

Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text

Effects of word length and frequency on the human event-related potential

Eye movements, word familiarity, and vocabulary acquisition

Investigating the effects of a set of intercorrelated variables on eye fixation durations in reading.

Eye Movements Reveal the On-Line Computation of Lexical Probabilities During Reading

Measuring word recognition in reading: eye movements and event-related potentials

Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition

The contribution of EEG coherence to the investigation of language

Electrophysiology reveals semantic memory use in language comprehension

Multitask Learning

Lexical complexity and fixation times in reading: Effects of word frequency, verb complexity, and lexical ambiguity

Visual attention in reading: Eye movements reflect cognitive processes

From the SelectedWorks of Marcel Adam Just 1980 A theory of reading : From eye fixations to comprehension

Eye movements in reading words and sentences

BNC database and word frequency lists

Doing more with less: Meta-reasoning and metalearning in humans and machines. Current Opinion in Behavioral Sciences

What your eyes do while your mind is reading

Field of Study

Computer Science

Journal Information

Name

ArXiv

Volume

abs/2005.00687

Venue Information

Name

arXiv.org

Type

URL

https://arxiv.org

Alternate Names

ArXiv