Dimitrios Alikaniotis

Dimitrios Alikaniotis, Vipul Raheja

Recent work on Grammatical Error Correction (GEC) has highlighted the importance of language modeling in that it is certainly possible to achieve good performance by comparing the probabilities of the proposed edits. At the same time, advancements in language modeling have managed to generate linguistic output, which is almost indistinguishable from that of human-generated text. In this paper, we up the ante by exploring the potential of more sophisticated language models in GEC and offer some key insights on their strengths and weaknesses. We show that, in line with recent results in other NLP tasks, Transformer architectures achieve consistently high performance and provide a competitive baseline for future machine learning models.

Dimitrios Alikaniotis, John N. Williams

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that the implicit learnability of semantic regularities depends on the degree to which the relevant concept is reflected in language use. In our simulations, we train a Vector-Space model on either an English or a Chinese corpus and then feed the resulting representations to a feed-forward neural network. The task of the neural network was to find a mapping between the word representations and the novel words. Using datasets from four behavioural experiments, which used different semantic manipulations, we were able to obtain learning patterns very similar to those obtained by humans.

Christian Bentz, Dimitrios Alikaniotis

The average uncertainty associated with words is an information-theoretic concept at the heart of quantitative and computational linguistics. The entropy has been established as a measure of this average uncertainty - also called average information content. We here use parallel texts of 21 languages to establish the number of tokens at which word entropies converge to stable values. These convergence points are then used to select texts from a massively parallel corpus, and to estimate word entropies across more than 1000 languages. Our results help to establish quantitative language comparisons, to understand the performance of multilingual translation systems, and to normalize semantic similarity measures.