Pawel Nowak
Pawel Nowak has 2 papers in our library, in 2020–2022, most of them on Language models & pretraining, Semantic parsing & meaning representation; often with Francesco Piccinno, Jonathan Herzig, Julian Eisenschlos.
OpenAlex · h-index 5 · 9 works · 936 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 358 citations in our library · ⭐ Paper Star rank #2342
Affiliations
Concepts, shelves and topics
📚 Shelves 5 Arts and Humanities · 2 works Computer Science · 2 works Artificial Intelligence · 2 works Language and Linguistics · 2 works Computer Vision and Pattern Recognition · 1 work
🧭 Topics 2 Language models & pretraining · 1 work Semantic parsing & meaning representation · 1 work
Works by year
2020s
Papers
- TaPas: Weakly Supervised Table Parsing via Pre-training (2020 · 845 citations)
Answering questions over tables is usually treated as semantic parsing: the question is converted into an executable logical form. - Improving Compositional Generalization with Latent Structure and Data Augmentation (2022 · 76 citations)
Pre-trained sequence-to-sequence models such as T5 cope well with natural language variation. However, they often fail when test inputs combine familiar elements in unseen ways. Specialized models with discrete latent structure handle such compositions better, but their gains have mostly been limited to synthetic…
Co-authors here
- Francesco Piccinno
- Jonathan Herzig
- Julian Eisenschlos
- Kristina Toutanova
- Linlu Qiu
- Panupong Pasupat
- Peter Shaw
- Tal Linzen
- Thomas Müller
Venues
- Annual Meeting of the Association for Computational…: 2020
- Conference of the North American Chapter of the Association…: 2022
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/pawel-nowak/