Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper explores the relationship between Polish word forms (phonology and morphology, specifically consonant clusters) and their meanings using distributional semantics. They find that semantic embeddings of Polish words encode information about phonotactic complexity, morphotactic transparency, and morphosyntactic categories. Furthermore, they show that these embeddings can be used in a discriminative lexicon model to predict word comprehension and production with high accuracy.
Polish word embeddings surprisingly capture fine-grained phonological and morphological information, enabling accurate prediction of morphosyntactic features and even word processing.
This study investigates the relationship between the phonological and morphological structure of Polish words and their meanings using Distributional Semantics. In the present analysis, we ask whether there is a relationship between the form properties of words containing consonant clusters and their meanings. Is the phonological and morphonological structure of complex words mirrored in semantic space? We address these questions for Polish, a language characterized by non-trivial morphology and an impressive inventory of morphologically-motivated consonant clusters. We use statistical and computational techniques, such as t-SNE, Linear Discriminant Analysis and Linear Discriminative Learning, and demonstrate that -- apart from encoding rich morphosyntactic information (e.g. tense, number, case) -- semantic vectors capture information on sub-lexical linguistic units such as phoneme strings. First, phonotactic complexity, morphotactic transparency, and a wide range of morphosyntactic categories available in Polish (case, gender, aspect, tense, number) can be predicted from embeddings without requiring any information about the forms of words. Second, we argue that computational modelling with the discriminative lexicon model using embeddings can provide highly accurate predictions for comprehension and production, exactly because of the existence of extensive information in semantic space that is to a considerable extent isomorphic with structure in the form space.