Chu, Mark BoDesikan, Bhargav SrinivasaNadler, Ethan O.Sardo, Ruggerio L.Darragh-Ford, EliseGuilbeault, Douglas2022-09-262022-09-262022-09-262022-01-0110.18653/v1/2022.acl-long.492https://infoscience.epfl.ch/handle/20.500.14299/191052WOS:000828702307019Natural language processing models learn word representations based on the distributional hypothesis, which asserts that word context (e.g., co-occurrence) correlates with meaning. We propose that n-grams composed of random character sequences, or garble, provide a novel context for studying word meaning both within and beyond extant language. In particular, randomly generated character n-grams lack meaning but contain primitive information based on the distribution of characters they contain. By studying the embeddings of a large corpus of garble, extant language, and pseudowords using CharacterBERT, we identify an axis in the model's high-dimensional embedding space that separates these classes of n-grams. Furthermore, we show that this axis relates to structure within extant language, including word part-of-speech, morphology, and concept concreteness. Thus, in contrast to studies that are mainly limited to extant language, our work reveals that meaning and primitive information are intrinsically linked.Computer Science, Artificial IntelligenceComputer Science, Interdisciplinary ApplicationsLinguisticsComputer Sciencewordstext::conference output::conference proceedings::conference paper