Papers by Leonardo Rigutini
Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles (2024.lrec-main)
Copied to clipboard
| Challenge: | Educational crosswords are characterized by less cryptic and more factual clues than traditional puzzles. |
| Approach: | They propose to use a dataset to generate educational clues for Large Language Models (LLMs) they use Wikipedia to gather information associated with relevant keywords and use it to generate clues. |
| Outcome: | The proposed approach generates educational clues from a dataset containing 44,075 examples with text-keyword pairs associated with three distinct crossword clues. |
Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources (L18-1)
Copied to clipboard
| Challenge: | Existing supervised models for Word Sense Disambiguation (WSD) are limited to knowledge-based approaches. |
| Approach: | They propose to use WordNet and WordNet Domains to enhance supervised WSD models by introducing semantic features into the classifiers and using the SLR structure to augment training data. |
| Outcome: | The proposed model improves the state-of-the-art in Word Sense Disambiguation (WSD) The proposed approach is compared with the state of the art in the most popular benchmarks. |
Fast Vocabulary Transfer for Language Model Compression (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods to reduce model size and size are expensive and inefficient for some applications. |
| Approach: | They propose a method that relies on vocabulary transfer to reduce model size and inference time while compromising on performance. |
| Outcome: | The proposed method reduces model size and inference time while compromising on performance. |
PharmaQA.IT: an Italian dataset for Q&A in the pharmaceutical domain (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing medical QA datasets are mostly English and centred on scientific articles or clinical notes. |
| Approach: | They propose an extractive QA dataset built from Riassunti delle Caratteristiche del Prodotto . the final dataset contains 861 high-quality question–answer pairs . |
| Outcome: | The proposed dataset contains 861 high-quality question–answer pairs on indications, contraindications, dosage, warnings, interactions, and pharmacological properties. |
BUSTER: a “BUSiness Transaction Entity Recognition” dataset (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Natural Language Processing has seen major breakthroughs in the last few years, but transferring these advances into industry applications can be difficult. |
| Approach: | They propose to use a BUSiness Transaction Entity Recognition dataset to support industry-oriented research by exploiting both general-purpose and domain-specific language models. |
| Outcome: | The proposed model is the best performing model and an additional silver corpus to BUSTER. |
Multi-word Tokenization for Sequence Compression (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models have proven successful at modelling tasks, but they are expensive and slow to scale. |
| Approach: | They propose a Multi-Word Tokenizer that represents frequent multi-word expressions as single tokens. |
| Outcome: | The proposed tokenizer is more robust across shorter sequence lengths, allowing for major speedups via early sequence truncation. |