Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Bowen, Ding, Xiao, Du, Li, Bing, Qin, Liu, Ting
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2208.14509
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909156316807168
author Chen, Bowen
Ding, Xiao
Du, Li
Bing, Qin
Liu, Ting
author_facet Chen, Bowen
Ding, Xiao
Du, Li
Bing, Qin
Liu, Ting
contents Given a task, human learns from easy to hard, whereas the model learns randomly. Undeniably, difficulty insensitive learning leads to great success in NLP, but little attention has been paid to the effect of text difficulty in NLP. In this research, we propose the Human Learning Matching Index (HLM Index) to investigate the effect of text difficulty. Experiment results show: (1) LSTM has more human-like learning behavior than BERT. (2) UID-SuperLinear gives the best evaluation of text difficulty among four text difficulty criteria. (3) Among nine tasks, some tasks' performance is related to text difficulty, whereas some are not. (4) Model trained on easy data performs best in easy and medium data, whereas trains on a hard level only perform well on hard data. (5) Training the model from easy to hard leads to fast convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2208_14509
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Text Difficulty Study: Do machines behave the same as humans regarding text difficulty?
Chen, Bowen
Ding, Xiao
Du, Li
Bing, Qin
Liu, Ting
Computation and Language
Given a task, human learns from easy to hard, whereas the model learns randomly. Undeniably, difficulty insensitive learning leads to great success in NLP, but little attention has been paid to the effect of text difficulty in NLP. In this research, we propose the Human Learning Matching Index (HLM Index) to investigate the effect of text difficulty. Experiment results show: (1) LSTM has more human-like learning behavior than BERT. (2) UID-SuperLinear gives the best evaluation of text difficulty among four text difficulty criteria. (3) Among nine tasks, some tasks' performance is related to text difficulty, whereas some are not. (4) Model trained on easy data performs best in easy and medium data, whereas trains on a hard level only perform well on hard data. (5) Training the model from easy to hard leads to fast convergence.
title Text Difficulty Study: Do machines behave the same as humans regarding text difficulty?
topic Computation and Language
url https://arxiv.org/abs/2208.14509