Search Results for author: Michele Bevilacqua

Found 8 papers, 4 papers with code

SPRING Goes Online: End-to-End AMR Parsing and Generation

no code implementations EMNLP (ACL) 2021 Rexhina Blloshmi, Michele Bevilacqua, Edoardo Fabiano, Valentina Caruso, Roberto Navigli

In this paper we present SPRING Online Services, a Web interface and RESTful APIs for our state-of-the-art AMR parsing and generation system, SPRING (Symmetric PaRsIng aNd Generation).

AMR Parsing

Integrating Personalized PageRank into Neural Word Sense Disambiguation

1 code implementation EMNLP 2021 Ahmed El Sheikh, Michele Bevilacqua, Roberto Navigli

Neural Word Sense Disambiguation (WSD) has recently been shown to benefit from the incorporation of pre-existing knowledge, such as that coming from the WordNet graph.

Word Sense Disambiguation

Generationary or ``How We Went beyond Word Sense Inventories and Learned to Gloss''

no code implementations EMNLP 2020 Michele Bevilacqua, Marco Maru, Roberto Navigli

Mainstream computational lexical semantics embraces the assumption that word senses can be represented as discrete items of a predefined inventory.

Word Sense Disambiguation

AAA: Fair Evaluation for Abuse Detection Systems Wanted

1 code implementation ACM Web Science 2021 Agostina Calabrese, Michele Bevilacqua, Björn Ross, Rocco Tripodi, Roberto Navigli

In this work, we introduce Adversarial Attacks against Abuse (AAA), a new evaluation strategy and associated metric that better captures a model’s performance on certain classes of hard-to-classify microposts, and for example penalises systems which are biased on low-level lexical features.

Abusive Language Hate Speech Detection +1

One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline

1 code implementation Proceedings of the AAAI Conference on Artificial Intelligence 2021 Michele Bevilacqua, Rexhina Blloshmi, Roberto Navigli

In Text-to-AMR parsing, current state-of-the-art semantic parsers use cumbersome pipelines integrating several different modules or components, and exploit graph recategorization, i. e., a set of content-specific heuristics that are developed on the basis of the training set.

Ranked #2 on AMR Parsing on LDC2020T02 (using extra training data)

AMR Parsing AMR-to-Text Generation +1

Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts

no code implementations ACL 2020 Agostina Calabrese, Michele Bevilacqua, Roberto Navigli

Thanks to the wealth of high-quality annotated images available in popular repositories such as ImageNet, multimodal language-vision research is in full bloom.

Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation

no code implementations RANLP 2019 Michele Bevilacqua, Roberto Navigli

While contextualized embeddings have produced performance breakthroughs in many Natural Language Processing (NLP) tasks, Word Sense Disambiguation (WSD) has not benefited from them yet.

Word Sense Disambiguation

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