Compositionality as an Analogical Process: Introducing ANNE

Giulia Rambelli, Emmanuele Chersoni, Philippe Blache, Alessandro Lenci


Abstract
Usage-based constructionist approaches consider language a structured inventory of constructions, form-meaning pairings of different schematicity and complexity, and claim that the more a linguistic pattern is encountered, the more it becomes accessible to speakers. However, when an expression is unavailable, what processes underlie the interpretation? While traditional answers rely on the principle of compositionality, for which the meaning is built word-by-word and incrementally, usage-based theories argue that novel utterances are created based on previously experienced ones through analogy, mapping an existing structural pattern onto a novel instance. Starting from this theoretical perspective, we propose here a computational implementation of these assumptions. As the principle of compositionality has been used to generate distributional representations of phrases, we propose a neural network simulating the construction of phrasal embedding as an analogical process. Our framework, inspired by word2vec and computer vision techniques, was evaluated on tasks of generalization from existing vectors.
Anthology ID:
2022.cogalex-1.10
Volume:
Proceedings of the Workshop on Cognitive Aspects of the Lexicon
Month:
November
Year:
2022
Address:
Taipei, Taiwan
Venue:
CogALex
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
78–96
Language:
URL:
https://aclanthology.org/2022.cogalex-1.10
DOI:
Bibkey:
Cite (ACL):
Giulia Rambelli, Emmanuele Chersoni, Philippe Blache, and Alessandro Lenci. 2022. Compositionality as an Analogical Process: Introducing ANNE. In Proceedings of the Workshop on Cognitive Aspects of the Lexicon, pages 78–96, Taipei, Taiwan. Association for Computational Linguistics.
Cite (Informal):
Compositionality as an Analogical Process: Introducing ANNE (Rambelli et al., CogALex 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2022.cogalex-1.10.pdf