activity
20162022
most citedIs Structure Necessary for Modeling Argument Expectations in Distributional Semantics?

4 citations · 8 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL20221 cited

Word Order Matters when you Increase Masking

Karim Lasri, Alessandro Lenci, Thierry Poibeau

Word order, an essential property of natural languages, is injected in Transformer-based neural language models using position encoding. However, recent experiments have shown that…

cs.CL2022

Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT

Karim Lasri, Olga Seminck, Alessandro Lenci +1

Both humans and neural language models are able to perform subject-verb number agreement (SVA). In principle, semantics shouldn't interfere with this task, which only requires synt…

cs.CL2021

Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge

Paolo Pedinotti, Giulia Rambelli, Emmanuele Chersoni +3

Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality r…

cs.CL20193 cited

A Structured Distributional Model of Sentence Meaning and Processing

Emmanuele Chersoni, Enrico Santus, Ludovica Pannitto +3

Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a Structured Distributional Model (SDM) that combines w…

cs.CL20174 cited

Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?

Emmanuele Chersoni, Enrico Santus, Philippe Blache +1

Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations. The…

cs.CL2017

Measuring Thematic Fit with Distributional Feature Overlap

Enrico Santus, Emmanuele Chersoni, Alessandro Lenci +1

In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of…