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

Mark Chu, Bhargav Srinivasa Desikan, Ethan Nadler, Donald Ruggiero Lo Sardo, Elise Darragh-Ford, Douglas Guilbeault


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 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.
Anthology ID:
2022.acl-long.492
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7120–7134
Language:
URL:
https://aclanthology.org/2022.acl-long.492
DOI:
10.18653/v1/2022.acl-long.492
Bibkey:
Cite (ACL):
Mark Chu, Bhargav Srinivasa Desikan, Ethan Nadler, Donald Ruggiero Lo Sardo, Elise Darragh-Ford, and Douglas Guilbeault. 2022. Signal in Noise: Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7120–7134, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Signal in Noise: Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models (Chu et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2022.acl-long.492.pdf
Software:
 2022.acl-long.492.software.zip
Code
 comp-syn/garble