Measuring Thematic Fit with Distributional Feature Overlap

Abstract

In this paper, we introduce a new distributional method for modeling predicateargument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of verb-specific roles: for every verb, we extract the most salient second order contexts for each of its roles (i.e. the most salient dimensions of typical role fillers), and then we compute thematic fit as a weighted overlap between the top features of candidate fillers and role prototypes. Our experiments show that our method consistently outperforms a baseline re-implementing a state-of-theart system, and achieves better or comparable results to those reported in the literature for the other unsupervised systems. Moreover, it provides an explicit representation of the features characterizing verbspecific semantic roles.

Distributional Semantics and Linguistic Theory

“…Their model achieved a Spearman correlation score of 0.33 and 0.47 (p < 0.001) with the human ratings in two different datasets for English involving agent and patient roles. Erk et al's idea of working with argument prototypes has been further refined and developed in subsequent models (Baroni & Lenci 2010;Lenci 2011;Greenberg et al 2015;Santus et al 2017) with improved empirical results and a broader coverage of phenomena.…”

A structured distributional model of sentence meaning and processing

“…However, the differences are clearly minimal, suggesting that the structured knowledge encoded in the C-Phrase embeddings is not a plus for the thematic fit task. Concerning this point, it must be mentioned that most of the current models for thematic fit estimation rely on vectors relying either on syntactic information (Baroni and Lenci 2010; Greenberg et al 2015; Santus et al 2017; Chersoni et al 2017) or semantic roles (Sayeed et al 2015; Tilk et al 2016). On the other hand, our results comply with studies like Lapesa and Evert (2017), who reported comparable performance for bag-of-words and dependency-based models on several semantic modelling tasks, thus questioning whether the injection of linguistic structure in the word vectors is actually worth its processing cost.…”

“…Thematic fit is a psycholinguistic notion similar to selectional preferences, the main difference being that the latter involve the satisfaction of constraints on discrete semantic features of the arguments, while thematic fit is a continuous value expressing the degree of compatibility between an argument and a semantic role (McRae et al 1998). Distributional models for thematic fit estimation have been proposed by several authors (Erk 2007; Baroni and Lenci 2010; Erk et al 2010; Lenci 2011; Sayeed et al 2015; Greenberg et al 2015; Santus et al 2017; Tilk et al 2016; Hong et al 2018). While thematic fit data sets typically include human-elicited typicality scores for argument–filler pairs taken in isolation, DTFit includes tuples of arguments of different length, so that the typicality value of an argument depends on its interaction with the other arguments in the tuple.…”

Distributional Semantics Meets Construction Grammar. towards a Unified Usage-Based Model of Grammar and Meaning

“…In this paper, we assume that at least some aspects of semantic roles can be derived from combining (e.g., with summation) the distributional vectors of their most prototypical fillers, following an approach widely explored in DS (Baroni and Lenci, 2010;Erk et al, 2010;Sayeed et al, 2016;Santus et al, 2017). For instance, the − −− → buyer role in the COMMERCIAL TRANSACTION frame can be taken as a vector encoding the properties of the typical nouns filling this role.…”