Signal in Noise: Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models

Mark Bo Chu, Bhargav Srinivasa Desikan, Ethan O. Nadler, Ruggerio L. Sardo, Elise Darragh-Ford, Douglas Guilbeault

March 15, 2022

Abstract: Natural 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 Character-BERT, 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.

Featured Fellows

Douglas Guilbeault

Haas School of Business, UC Berkeley
Faculty Affiliate