Predicting Embedding Reliability in Low-Resource Settings

Dunn, J.; Li, H.; & Sastre, D. (2022). “Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures.” In Proceedings of the 13th International Conference on Language Resources and Evaluation. European Language Resources Association. 6461-6470. Abstract This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under … More Predicting Embedding Reliability in Low-Resource Settings

Construction Grammars Converge Given Increased Exposure

Dunn, J. & Tayyar Madabushi, H. (2021). “Learned Construction Grammars Converge Across RegistersGiven Increased Exposure.” Proceedings of the Conference on Computational Natural Language Learning (CoNLL 2021). Association for Computational Linguistics. Abstract. This paper measures the impact of increased exposure on whether learned construction grammars converge onto shared representations when trained on data from different registers. … More Construction Grammars Converge Given Increased Exposure

Global Syntactic Variation in Seven Languages

Dunn, J. (2019). “Global Syntactic Variation in Seven Languages: Towards a Computational Dialectology.” In Frontiers in Artificial Intelligence: Language and Computation. Abstract. The goal of this paper is to provide a complete representation of regional linguistic variation on a global scale. To this end, the paper focuses on removing three constraints that have previously limited … More Global Syntactic Variation in Seven Languages