Building a state-of-the-art approach to Grammatical Error Correction
Talk presentation
In this talk, we will look at the current state (post-BERT era) of GEC and share our experience of building the state-of-the-art system to perform this task. We will talk about the pros and cons of different architectures and compare inference times.
Kostiantyn Omelianchuk
Grammarly
- Applied Research Scientist at Grammarly
- Project lead and NLP expert with 4+ years of experience in the industry
- 3rd-place winner of Home Depot Product Search Relevance competition on Kaggle (2016)
- Currently working as Applied Research Scientist with the main focus on ensuring Grammarly leads the industry in Grammatical Error Correction
Oleksandr Skurzhanskyi
Grammarly
- Applied Research Scientist at Grammarly
- Works with the tasks of improving various aspects of communication that are beyond the scope of GEC
- Interested in non-autoregressive sequence generation, self-supervised representation learning, and model compression techniques
- Extensive experience in various NLP tasks like text simplification, machine translation, and geo-location extraction/recognition