Papers by Andrea Amelio Ravelli

3 papers
Specifying Genericity through Inclusiveness and Abstractness Continuous Scales (2024.lrec-main)

Copied to clipboard

Challenge: Using a pilot study, we created a small but crucial annotated dataset of 324 sentences, demonstrating the framework’s effectiveness in capturing nuanced aspects of genericity.
Approach: They propose a framework for fine-grained modeling of noun phrases' genericity in natural language using a small but crucial annotated dataset of 324 sentences.
Outcome: The proposed framework can be used to model genericity of noun phrases in natural language and can be easily compared with existing binary annotations.
Coherent or Not? Stressing a Neural Language Model for Discourse Coherence in Multiple Languages (2023.findings-acl)

Copied to clipboard

Challenge: Existing work on coherence assessment using NLMs focuses on properties acquired from stand-alone sentences, but their ability to model discourse and pragmatic phenomena is still unclear.
Approach: They propose to use a Neural Language Model to assess coherence in multiple languages to compare models' performance and to examine their performance in a cross-language scenario.
Outcome: The proposed model can model coherent and incoherent text in multiple languages and in-domain settings.
One event, many representations. Mapping action concepts through visual features. (L18-1)

Copied to clipboard

Challenge: a proposed classification of general verbs is characterized by a high ambiguity and high frequency in the use.
Approach: They propose to use IMAGACT visual component as linkage point between resources . they propose automatic linking with BabelNet and manual linking with Praxicon .
Outcome: The proposed solution exploits the IMAGACT visual component as the linkage point among resources.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations