activity
20202023
most citedConstruction Repetition Reduces Information Rate in Dialogue

3 citations · 6 across the 7 of their papers we have counts for

collaborators

8 papers

cs.CL2023

Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue

Aron Molnar, Jaap Jumelet, Mario Giulianelli +1

Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalis…

cs.CL2022

Towards Pragmatic Production Strategies for Natural Language Generation Tasks

Mario Giulianelli

This position paper proposes a conceptual framework for the design of Natural Language Generation (NLG) systems that follow efficient and effective production strategies in order t…

cs.CL20223 cited

Construction Repetition Reduces Information Rate in Dialogue

Mario Giulianelli, Arabella Sinclair, Raquel Fernández

Speakers repeat constructions frequently in dialogue. Due to their peculiar information-theoretic properties, repetitions can be thought of as a strategy for cost-effective communi…

cs.CL20221 cited

Do Not Fire the Linguist: Grammatical Profiles Help Language Models Detect Semantic Change

Mario Giulianelli, Andrey Kutuzov, Lidia Pivovarova

Morphological and syntactic changes in word usage (as captured, e.g., by grammatical profiles) have been shown to be good predictors of a word's meaning change. In this work, we ex…

cs.CL2021

Grammatical Profiling for Semantic Change Detection

Mario Giulianelli, Andrey Kutuzov, Lidia Pivovarova

Semantics, morphology and syntax are strongly interdependent. However, the majority of computational methods for semantic change detection use distributional word representations w…

cs.CL2020

Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts

Ece Takmaz, Mario Giulianelli, Sandro Pezzelle +2

Dialogue participants often refer to entities or situations repeatedly within a conversation, which contributes to its cohesiveness. Subsequent references exploit the common ground…