Papers by Alessandro Mazzei
WebNLG-IT: Construction of an aligned RDF-Italian corpus through Machine Translation techniques (2025.findings-acl)
Copied to clipboard
| Challenge: | Using NMT and hand-written rules, we created the first aligned Italian RDF-to-text corpus . |
| Approach: | They propose to use NMT to create an Italian version of the WebNLG corpus and to refine and improve the quality of the produced resource. |
| Outcome: | The proposed system is the best on the original English version and the best in the second step, it improves and refines the quality of the produced resource. |
The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization (D19-63)
Copied to clipboard
| Challenge: | SR is one of the main tasks involved in Natural Language Generation. |
| Approach: | They propose a system which divides the SR task into two independent subtasks, namely word order prediction and morphology inflection prediction. |
| Outcome: | The proposed system is a direct successor to the architecture presented at SR'19. |
PoSTWITA-UD: an Italian Twitter Treebank in Universal Dependencies (L18-1)
Copied to clipboard
Manuela Sanguinetti, Cristina Bosco, Alberto Lavelli, Alessandro Mazzei, Oronzo Antonelli, Fabio Tamburini
| Challenge: | Various approaches and ad hoc resources are needed to provide proper coverage of specific linguistic phenomena. |
| Approach: | They propose to annotate tweets using a well-known dependency-based annotation format . they propose to use the tweets for training NLP systems to improve their performance . |
| Outcome: | The proposed resource can be used for training of NLP systems on social media texts. |
Educational Dialogue Systems for Visually Impaired Students: Introducing a Task-Oriented User-Agent Corpus (2024.lrec-main)
Copied to clipboard
Elisa Di Nuovo, Manuela Sanguinetti, Pier Felice Balestrucci, Luca Anselma, Cristian Bernareggi, Alessandro Mazzei
| Challenge: | a corpus of real-world dialogues between visually impaired users and an agent is described . the corpus is part of a larger research project aimed at developing tools for easier access to educational content for visually impaired people. |
| Approach: | They describe a corpus consisting of real-world dialogues between users and a task-oriented conversational agent . they report the results of a classification experiment on the annotated corpus and an additional experiment to assess the annotation capabilities of three large language models. |
| Outcome: | The proposed corpus is part of a larger research project aimed at improving visual aids for visually impaired users. |
I’m sure you’re a real scholar yourself: Exploring Ironic Content Generation by Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Moreover, irony is highly subjective and can depend on various factors, such as social, cultural, or generational aspects. |
| Approach: | They propose to fine-tune two large language models to generate ironic and non-ironic content and analyze their outputs from a linguistic perspective. |
| Outcome: | The proposed models generate ironic and non-ironic responses to a given social media post and analyze their outputs from a linguistic perspective. |
Can Large Language Models Personalize Dialogues to Generational Styles? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a human evaluation reveals that annotators were able to most accurately identify the generation behind P-MultiWoZ dialogues, based only on a single query-reply pair. |
| Approach: | They create a personalized, generation-specific version of MultiWOZ 2.2 by prompting LLMs to generate personalized dialogue responses. |
| Outcome: | The proposed model is a personalized version of MultiWOZ 2.2 for Generation X, Y, and Z . it is validated by automatic and human evaluations to determine whether it reflects generational linguistic traits. |
Exploring Data Augmentation in Neural DRS-to-Text Generation (2024.eacl-long)
Copied to clipboard
| Challenge: | Neural networks are notoriously data-hungry, resulting in ungrammatical texts . data augmentation requires a specific design for a structurally rich input format . |
| Approach: | They propose to selectively augment a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns. |
| Outcome: | The proposed approach selectively augments a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns. |