Human and computer estimations of Predictability of words in written language
Explore this paper's citation graph
Summary
This study shows that using different word embeddings techniques and N-gram-based language models the authors were able to estimate how humans predict words (cloze-task Predictability) and how to better understand eye movements in long Spanish texts to potentially improve NLP algorithms.
- Type
- article
- Published
- 2020-03-10
- Cited by
- 16
- References
- 50
- Access
- Open access
- OpenAlex
- https://openalex.org/W1489614140
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:13825435
Keywords
Predictability, Computer science, Natural language processing, Artificial intelligence, Variety (cybernetics)
References
- Akaike information criterion statistics
- Eye movements during reading proverbs and regular sentences: the incoming word predictability effect
- Lexical complexity and fixation times in reading: Effects of word frequency, verb complexity, and lexical ambiguity
- A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.
- Parafoveal word processing during eye fixations in reading: Effects of word frequency
- Toward a Perceptual-Span Theory of Distributed Processing in Reading: A Reply to Rayner, Pollatsek, Drieghe, Slattery, and Reichle (2007).
- Contextual effects on word perception and eye movements during reading
- Parallel processing and sentence comprehension difficulty
- Eye movements in reading and information processing: 20 years of research.
- Tracking the mind during reading via eye movements: comments on Kliegl, Nuthmann, and Engbert (2006).
- On-line contextual influences during reading normal text: a multiple-regression analysis.
- Tracking the mind during reading: the influence of past, present, and future words on fixation durations.
- Two stages of word processing during eye fixations in the reading of prose
- Frequency and predictability effects in the Dundee Corpus: An eye movement analysis
- Effects of contextual predictability and transitional probability on eye movements during reading.
- An Empirical Study of Smoothing Techniques for Language Modeling
- Eye tracking: a comprehensive guide to methods and measures
- Parsing costs as predictors of reading difficulty: An evaluation using the Potsdam Sentence Corpus
- The effect of word predictability on reading time is logarithmic
- A bit of progress in language modeling
Cited by
- Estimadores computacionales de la predicción humana durante la lectura
- Machine Learning And Neural Network Methodologies of Analyzing Social Media
- Spintronic Sensors Based on Magnetic Tunnel Junctions for Wireless Eye Movement Gesture Control
- Language Models Explain Word Reading Times Better Than Empirical Predictability
- An Implementation of Natural Language Processing and Text Mining in Stroke Research
- Neural bases of predictions during natural reading of known statements: An EEG and eye movements co-registration study.
- Synthetic predictabilities from large language models explain reading eye movements
- A discriminative information-theoretical analysis of the regularity gradient in inflectional morphology
- DERCo: A Dataset for Human Behaviour in Reading Comprehension Using EEG
- Modelando procesos cognitivos de la lectura natural con GPT-2
- Exploring the Integration of Eye Movement Data on Word Embeddings
- Quantifying word informativeness and its impact on eye-movement reading behavior: Cross-linguistic variability and individual differences
- Modeling cognitive processes of natural reading with transformer-based Language Models
- All together now: Random Forests analysis reveals the joint impact of multiple statistical regularities on eye-movements during reading
- Cuentos: A Large-Scale Eye-Tracking Reading Corpus on Spanish Narrative Texts
- Human writing and machine patterns: analyzing a decade of convergence
- The Effect of Word Informativeness on Eye-Movement Reading Behavior: Cross-Linguistic Variability and Individual Differences
- The Grain of Prediction: Character-Level Language Models Better Approximate Human Predictability in Chinese Reading
Related papers
- Is stock return predictability time-varying?
- Word2vec Word Similarities on IBM's TrueNorth Neurosynaptic System
- Deconstructing Word Embedding Algorithms
- Exploration on Grounded Word Embedding: Matching Words and Images with Image-Enhanced Skip-Gram Model
- AWE-CM Vectors: Augmenting Word Embeddings with a Clinical Metathesaurus
- A Method for Visual Interpretation of Word2Vec Static Vector Space
- Evaluating Modeling Units and Sub-word Features in Language Models for Turkish ASR