Search Results for author: Matteo Palmonari

Found 7 papers, 3 papers with code

On the Impact of Temporal Representations on Metaphor Detection

no code implementations5 Nov 2021 Giorgio Ottolina, Matteo Palmonari, Mehwish Alam, Manuel Vimercati

Metaphorical expressions are known to co-evolve with language and literal word meanings, and even drive, to some extent, this evolution.

Word Embeddings

SWEAT: Scoring Polarization of Topics across Different Corpora

1 code implementation EMNLP 2021 Federico Bianchi, Marco Marelli, Paolo Nicoli, Matteo Palmonari

Understanding differences of viewpoints across corpora is a fundamental task for computational social sciences.

Knowledge Graph Embeddings and Explainable AI

no code implementations30 Apr 2020 Federico Bianchi, Gaetano Rossiello, Luca Costabello, Matteo Palmonari, Pasquale Minervini

Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces.

Knowledge Graph Embeddings

Compass-aligned Distributional Embeddings for Studying Semantic Differences across Corpora

1 code implementation13 Apr 2020 Federico Bianchi, Valerio Di Carlo, Paolo Nicoli, Matteo Palmonari

In this paper, we present a general framework to support cross-corpora language studies with word embeddings, where embeddings generated from different corpora can be compared to find correspondences and differences in meaning across the corpora.

Word Embeddings

Training Temporal Word Embeddings with a Compass

1 code implementation5 Jun 2019 Valerio Di Carlo, Federico Bianchi, Matteo Palmonari

Temporal word embeddings have been proposed to support the analysis of word meaning shifts during time and to study the evolution of languages.

Diachronic Word Embeddings Word Embeddings

TWINE: A real-time system for TWeet analysis via INformation Extraction

no code implementations EACL 2017 Debora Nozza, Fausto Ristagno, Matteo Palmonari, Elisabetta Fersini, Manch, Pikakshi a, Enza Messina

In this paper we present TWINE, a real-time system for the big data analysis and exploration of information extracted from Twitter streams.

Named Entity Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.