Skip to main content

Projects and Resources

Software and Projects7 items

2026

DiCCAS. Resource page and persistent record for the DiCCAS project.

2026

Guidelines for Spoken Language UD Treebanks. Draft guidelines for annotating spoken-language treebanks in Universal Dependencies, produced by the UniDive WG1 T1.5 group. I co-coordinate the project.

2026

NPN Dataset. Dataset for the study of the Italian NPN construction, with inter-annotator agreement.

2026

Corpus Annotation Tools. Tools for corpus annotation developed within a separate project.

2025

Sample Dataset. Small library for generating balanced, constraint-driven samples from tabular data.

2023

Catenae. Code accompanying my PhD work on constructionist approaches to language models.

2020

Thematic Fit Estimation. Repository associated with our LREC 2020 work on thematic fit estimation with word embeddings.

Datasets3 items

2026

KIParla Forest. Universal Dependencies treebank of spoken Italian built on the KIParla corpus, released in UD v2.19 (November 2026).

2020

Recurrent Babbling Dataset. Dataset and supporting material for the CoNLL 2020 paper on grammar acquisition from limited input data.

2019

KIParla. Corpus of spoken Italian developed by the universities of Bologna and Turin; the GitHub organisation collects its data and tools.

Outreach and Dissemination3 items

2021

Teaching NLP Workshop Materials. Supplementary material for the Teaching NLP workshop paper on interactive outreach for Italian students.

2021

AILC Workshop for Schools. Interactive workshop materials developed with AILC for outreach activities in schools and festivals.

2020

Bright-Night Outreach Materials. Materials for the Bright-Night presentation on computational linguistics outreach.

Back to top