Abelardo Carlos Martínez Lorenzo

Hi!

I’m Abelardo Carlos, a postdoctoral researcher in the Sapienza Natural Language Processing group, under the guidance of Roberto Navigli. I pursued my Ph.D. in Natural Language Processing, holding a position as an Early Stage Researcher under the prestigious Marie Skłodowska-Curie grant in the Knograph project - European Union’s Horizon 2020 research and innovation programme.

My main research focuses on Cross-lingual semantics and Information Extraction, specifically on Semantic Parsing and Language Models.

I am graduated in Software Engineering by Universidad de Málaga in Spain and I pursued the Erasmus Mundus Joint Master Degree Programme in Big Data Management and Analytics (BDMA), a jointly degree delivered by Université Libre de Bruxelles (ULB) in Belgium, Universitat Politècnica de Catalunya (UPC) in Spain and Technische Universität Berlin (TU-Berlin) in Germany.

selected publications

ACL

Mitigating Data Scarcity in Cross-lingual Semantic Parsing: the Multilingual Semantic Layer and its Dataset

Martı́nez Lorenzo, Abelardo Carlos, Huguet Cabot, Pere Lluı́s, Ghonim, Karim, Xu, Lu, Choi, Hee-Soo, Fernandez Castro, Alberte, and Navigli, Roberto

In Aug 2024

Abs PDF
NAACL

MOSAICo: A Multilingual Open-text Semantically Annotated Interlinked Corpus

In 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics Jun 2024

Abs PDF
LREC-COLING

Efficient AMR Parsing with CLAP: Compact Linearization with an Adaptable Parser

Martinez Lorenzo, Abelardo Carlos, and Navigli, Roberto

In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) May 2024

Abs PDF

Sequence-to-sequence models have become the de facto standard for Abstract Meaning Representation (AMR) parsing due to their high-quality performance. However, these systems face efficiency challenges because of their large model size and computational time, which limit their accessibility within the research community. This paper aims to break down these barriers by introducing a novel linearization and system that significantly enhances the efficiency and accessibility of previous AMR parsers. First, we propose our novel Compact linearization that simplifies encoding, thereby reducing the number of tokens by between 40% and 50%. Second, we present CLAP, an innovative modular system that maintains the model’s high performance while achieving remarkable 80% reduction in training and inference times. Furthermore, CLAP is compatible with multiple autoregressive Language Models (LM) and tokenizers, such as BART, T5, and others. These advancements underscore the importance of optimizing sequence-to-sequence models in AMR parsing, thus democratizing access to high-quality semantic analysis. Our code is publicly available at https://github.com/SapienzaNLP/clap/.
ACL

AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing

Martı́nez Lorenzo, Abelardo Carlos, Huguet Cabot, Pere Lluı́s, and Navigli, Roberto

In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) Jul 2023

Abs PDF

In this paper, we examine the current state-of-the-art in AMR parsing, which relies on ensemble strategies by merging multiple graph predictions. Our analysis reveals that the present models often violate AMR structural constraints. To address this issue, we develop a validation method, and show how ensemble models can exploit SMATCH metric weaknesses to obtain higher scores, but sometimes result in corrupted graphs. Additionally, we highlight the demanding need to compute the SMATCH score among all possible predictions. To overcome these challenges, we propose two novel ensemble strategies based on Transformer models, improving robustness to structural constraints, while also reducing the computational time. Our methods provide new insights for enhancing AMR parsers and metrics. Our code is available at [\urlhttps://www.github.com/babelscape/AMRs-Assemble](\urlhttps://www.github.com/babelscape/AMRs-Assemble).
ACL

Incorporating Graph Information in Transformer-based AMR Parsing

Vasylenko, Pavlo, Huguet Cabot, Pere Lluı́s, Martı́nez Lorenzo, Abelardo Carlos, and Navigli, Roberto

In Findings of the Association for Computational Linguistics: ACL 2023 Jul 2023

Abs PDF

Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5, fine-tuned through Teacher Forcing to obtain a linearized version of the AMR graph from a sentence. In this paper, we present LeakDistill, a model and method that explores a modification to the Transformer architecture, using structural adapters to explicitly incorporate graph information into the learned representations and improve AMR parsing performance. Our experiments show how, by employing word-to-node alignment to embed graph structural information into the encoder at training time, we can obtain state-of-the-art AMR parsing through self-knowledge distillation, even without the use of additional data. We release the code at [\urlhttp://www.github.com/sapienzanlp/LeakDistill](\urlhttp://www.github.com/sapienzanlp/LeakDistill).
ACL

Cross-lingual AMR Aligner: Paying Attention to Cross-Attention

Martı́nez Lorenzo, Abelardo Carlos, Huguet Cabot, Pere Lluı́s, and Navigli, Roberto

In Findings of the Association for Computational Linguistics: ACL 2023 Jul 2023

Abs PDF

This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern Transformer-based parsers, which inherently encode alignment information in their cross-attention weights, allowing us to extract this information during parsing. This eliminates the need for English-specific rules or the Expectation Maximization (EM) algorithm that have been used in previous approaches. In addition, we propose a guided supervised method using alignment to further enhance the performance of our aligner. We achieve state-of-the-art results in the benchmarks for AMR alignment and demonstrate our aligner’s ability to obtain them across multiple languages. Our code will be available at [\urlhttps://www.github.com/babelscape/AMR-alignment](\urlhttps://www.github.com/babelscape/AMR-alignment).
ACL

Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation

Martı́nez Lorenzo, Abelardo Carlos, Maru, Marco, and Navigli, Roberto

In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) May 2022

Abs PDF

A language-independent representation of meaning is one of the most coveted dreams in Natural Language Understanding. With this goal in mind, several formalisms have been proposed as frameworks for meaning representation in Semantic Parsing. And yet, the dependencies these formalisms share with respect to language-specific repositories of knowledge make the objective of closing the gap between high- and low-resourced languages hard to accomplish. In this paper, we present the BabelNet Meaning Representation (BMR), an interlingual formalism that abstracts away from language-specific constraints by taking advantage of the multilingual semantic resources of BabelNet and VerbAtlas. We describe the rationale behind the creation of BMR and put forward BMR 1.0, a dataset labeled entirely according to the new formalism. Moreover, we show how BMR is able to outperform previous formalisms thanks to its fully-semantic framing, which enables top-notch multilingual parsing and generation. We release the code at https://github.com/SapienzaNLP/bmr.
AAAI

BabelNet Meaning Representation: A Fully Semantic Formalism to Overcome Language Barriers

Navigli, Roberto, Blloshmi, Rexhina, and Martínez Lorenzo, Abelardo Carlos

Proceedings of the AAAI Conference on Artificial Intelligence Jun 2022

PDF