According to psycholinguistic theories, processing a compound word (“snowman”) involves its automatic decomposition into its constituents (“snow”, “man”), then connected by an implicit semantic relation (“made of”) to obtain a plausible interpretation (“man made of snow”). However, the appropriate relation is often not univocal and must be selected from a set of competitors. In this study, we investigated whether contextualized word embeddings (cwe) capture human intuitions on compounds’ interpretations. We used BERT-base to obtain cwe of compounds in context (e.g., “We built a [snowman] in our garden”). Then, we systematically replaced compounds with paraphrase variants in which candidate relations were made explicit (e.g., “We built a [man made of snow] in our garden”). We then computed the similarity between the original compound cwe and its multiple variants. We find that these similarities predict participants’ interpretations (i.e., the probability of selecting a given relation) and their degree of conflict. Thus, we show that cwe can be leveraged to generate semantic representations for linguistic units that are not directly observable in text, but which influence compounds’ interpretation and processing.

Ciapparelli, M., Zarbo, C., Marelli, M. (2023). Contextualized word embeddings capture compound words’ implicit relational interpretations. Intervento presentato a: Conference of the European Society for Cognitive Psychology (ESCOP), Porto, Portogallo.

Contextualized word embeddings capture compound words’ implicit relational interpretations

Ciapparelli, M
Primo
;
Marelli, M
Ultimo
2023

Abstract

According to psycholinguistic theories, processing a compound word (“snowman”) involves its automatic decomposition into its constituents (“snow”, “man”), then connected by an implicit semantic relation (“made of”) to obtain a plausible interpretation (“man made of snow”). However, the appropriate relation is often not univocal and must be selected from a set of competitors. In this study, we investigated whether contextualized word embeddings (cwe) capture human intuitions on compounds’ interpretations. We used BERT-base to obtain cwe of compounds in context (e.g., “We built a [snowman] in our garden”). Then, we systematically replaced compounds with paraphrase variants in which candidate relations were made explicit (e.g., “We built a [man made of snow] in our garden”). We then computed the similarity between the original compound cwe and its multiple variants. We find that these similarities predict participants’ interpretations (i.e., the probability of selecting a given relation) and their degree of conflict. Thus, we show that cwe can be leveraged to generate semantic representations for linguistic units that are not directly observable in text, but which influence compounds’ interpretation and processing.
relazione (orale)
computational modelling; compound words; psycholinguistics; large language models
English
Conference of the European Society for Cognitive Psychology (ESCOP)
2023
2023
none
Ciapparelli, M., Zarbo, C., Marelli, M. (2023). Contextualized word embeddings capture compound words’ implicit relational interpretations. Intervento presentato a: Conference of the European Society for Cognitive Psychology (ESCOP), Porto, Portogallo.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/467184
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact