Results 61 to 70 of about 6,836 (144)
Emergent Predication Structure in Hidden State Vectors of Neural Readers
A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets. We present experiments supporting the emergence of "predication structure" in the hidden state vectors of ...
Gimpel, Kevin +3 more
core +1 more source
Aptitude complexes: Expanding our view of language aptitude
Abstract In second language (L2) research, aptitude is typically viewed as a multicomponential, cognitive construct. Yet we know that L2 learning is influenced by multiple learner individual differences (IDs) besides cognitive abilities and that these IDs interact.
Lani Freeborn +2 more
wiley +1 more source
Capital Gains: Effects of Word Class and Sentence Position on Capitalization Use Across Age
ABSTRACT Learning to capitalize in English requires identifying a word's type and sentence position. In two cloze studies (2021–2022), Australian students of all genders (95% White, monolingual) spelled words with one and two capitalization cues (proper nouns, sentence‐initial words) and no‐cue control words.
Emilia Hawkey +2 more
wiley +1 more source
Text Understanding with the Attention Sum Reader Network
Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well suited for deep ...
Bajgar, Ondrej +3 more
core +1 more source
Examining the cognitive costs of counterfactual language comprehension: Evidence from ERPs [PDF]
Recent empirical research suggests that understanding a counterfactual event (e.g. ‘If Josie had revised, she would have passed her exams’) activates mental representations of both the factual and counterfactual versions of events.
Cane, James E., Ferguson, Heather J.
core
Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
Pretrained contextual representation models (Peters et al., 2018; Devlin et al., 2018) have pushed forward the state-of-the-art on many NLP tasks. A new release of BERT (Devlin, 2018) includes a model simultaneously pretrained on 104 languages with ...
Dredze, Mark, Wu, Shijie
core +1 more source
AI is not seen through an unbiased lens. People tend to stereotype AI as competent and link it with socially advantaged groups—such as men, the wealthy, the young, and prestigious occupations—raising concerns that such perceptions may deepen existing social divides rather than bridge them.
Zixi Wang +4 more
wiley +1 more source
Tibetan Few‐Shot Learning Model With Deep Contextualised Two‐Level Word Embeddings
ABSTRACT Few‐shot learning is the task of identifying new text categories from a limited set of training examples. The two key challenges in few‐shot learning are insufficient understanding of new samples and imperfect modelling. The uniqueness of low‐resource languages lies in their limited linguistic resources, which directly leads to the difficulty ...
Ziyue Zhang +11 more
wiley +1 more source
Order Effects in Second Language Learning
Abstract We explore how general principles of learning apply to and combine with usage‐based approaches to language learning and teaching, with a focus on the effects of order of exposure to new information in second language (L2) instruction. Although the effects of input spacing and timing on memory and learning have been previously explored (see ...
Laurence Romain +2 more
wiley +1 more source
Abstract This study tested whether encouraging prediction enhances prediction in second language (L2) speakers. L2 English speakers listened to English sentences like The woman … will read/buy one of the newspapers while viewing the target (a newspaper) and distractor objects (a rose, a bowl, and a mango) on a screen and clicked on the target as ...
Aine Ito
wiley +1 more source

