Francesco Cazzaro

PhD Student in NLP

[INTERACT ERC @interacterc]

🧠 Our paper ZOGRASCOPE: A New Benchmark for Semantic Parsing over Property Graphs by @francescoczz, Justin Kleindienst, Sofia Marquez Gomez and @AriadnaQuattoni is being presented at EMNLP today!
Check it out here 👉 https://t.co/OlkF4CzwAj
Repo 🔗 https://t.co/0GaeGJbLr0

[INTERACT ERC @interacterc]

📢 Excited to share that our paper "SPOT: Zero-Shot Semantic Parsing Over Property Graphs" has been accepted to Findings of #ACL2025!
Joint work with @francescoczz, Justin Kleindienst, Sofia Márquez Gomez and @AriadnaQuattoni
🧑‍💻 Code: https://t.co/SQ0H8yruuE
[1/5]

[EMNLP 2026 @emnlpmeeting]

We're kicking off the awards session at #EMNLP2024 by announcing our (many) **Outstanding Reviewers**!

[Francesco Cazzaro @francescoczz]

📅 This was a joint work w/ @davidelct and @AriadnaQuattoni, to be presented next week at #EACL24. Stay tuned for the paper link!
[7/7]

[Francesco Cazzaro @francescoczz]

📢 Excited to share that our paper "Align and Augment: Generative Data Augmentation for Compositional Generalization" has been accepted for publication in #EACL24 @eaclmeeting
[1/7]

[Francesco Cazzaro @francescoczz]

📚 As a side contributions we introduce AtisAligned: the Atis dataset annotated with word alignments. Find it at https://t.co/SXDnPp2sKM
[6/7]

[INTERACT ERC @interacterc]

📢 Our paper "Entity Disambiguation on a Tight Labeling Budget" has been accepted for publication in Findings of #EMNLP2023 @emnlpmeeting
[1/6]

[Francesco Cazzaro @francescoczz]

👏 We're excited to share our findings and contribute to the ongoing efforts to improve semantic parsing. TPOL was joint work w/ @davidelct @ariadnaquattoni @xavier_nlp @interacterc
[6/6]

[Francesco Cazzaro @francescoczz]

📢 Our paper "Translate First Reorder Later" has been accepted for publication in Findings of #EACL23 @eaclmeeting

📄 Paper: https://t.co/9houBvusW0
🧑‍💻 Code: https://t.co/YrDOd4ecHP
🎥 Video: https://t.co/PITUEqG44K

[1/6]

[Francesco Cazzaro @francescoczz]

📈 Our experiments on two popular semantic parsing datasets have shown that TPOL outperforms both conventional seq2seq models and other approaches that exploit word alignments. TPOL perform well w/ automatic alignments too
[5/6]

[Francesco Cazzaro @francescoczz]

Tomorrow I'm presenting my work "Are Deep Sequence Classifiers Good at Non-Trivial Generalization? " at the Robustness in Sequence Modeling Workshop (poster session) at #NeurIPS2022 ! Find me in room 291! https://t.co/o6ucj1CmKI

[Pranav @nlp_pranav]

#NAACL2022 paper-tweet!

Title: Measuring Alignment Bias in Neural Seq2Seq Semantic Parsers
Author: Davide Locatelli (@davide_lct)
Session: Semeval-11
https://t.co/ko8SMRThu1