Anton Belyy (Belyi)
ru-RU: Антон Белый / zh-CN: 安东·别里 / IPA: [ɐn̪’t̪o̞n̪ ‘bʲeɫɨç]

LinkedIn / Github / Scholar

natural language processing / machine learning / algorithms

Hi, I’m Anton!

I am a Machine Learning Engineer at Apple, where I build scalable ML systems to transform unstructured, noisy Web data into structured, verified factual knowledge.

Prior to Apple, I completed my Masters Degree at the Center for Language and Speech Processing at Johns Hopkins University, and my Bachelors Degree at the Computer Technologies Department at ITMO University. During my Masters, I developed algorithms for automatic and semi-automatic schema induction. I also built human-in-the-loop augmented systems for semantic parsing annotation and story generation. During my Bachelors, I led the development of an exploratory search engine and a plagiarism detection framework. I also worked at Tochka Bank as a Senior Data Scientist, and at VK as a Software Engineer.

Papers

Fleek paper FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge. Farima Fatahi Bayat, Kun Qian, Benjamin Han, Yisi Sang, Anton Belyi, Samira Khorshidi, Fei Wu, Ihab F. Ilyas, Yunyao Li. EMNLP Demo Track 2023. [paper]
[demo]
FTC paper Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI. Suzanna Sia, Anton Belyy, Amjad Almahairi, Madian Khabsa, Luke Zettlemoyer, and Lambert Mathias. AAAI 2023. [paper]
Schema paper Human Schema Curation via Causal Association Rule Mining. Noah Weber, Anton Belyy, Nils Holzenberger, Rachel Rudinger, and Benjamin Van Durme. LREC Linguistic Annotation Workshop 2022. [paper]
[code]
[demo]
[data]
Guided K-best Guided K-best Selection for Semantic Parsing Annotation. Anton Belyy, Chieh-Yang Huang, Jacob Andreas, Emmanouil Antonios Platanios, Sam Thomson, Richard Shin, Subhro Roy, Aleksandr Nisnevich, Charles Chen, and Benjamin Van Durme. ACL Demo Track 2022. [paper]
[poster]
[slides]
[talk]
InFillmore InFillmore: Frame-Guided Language Generation with Bidirectional Context. Jiefu Ou, Nathaniel Weir, Anton Belyy, Felix Yu, and Benjamin Van Durme. STARSEM 2021. [paper]
[poster]
[slides]
[talk]
[demo]
SI as ARM Script Induction As Association Rule Mining. Anton Belyy and Benjamin Van Durme. ACL Workshop on Narrative Understanding, Storylines, and Events 2020. [paper]
[slides]
[talk]
[code]
Normplagdet screenshot Improved Evaluation Framework for Complex Plagiarism Detection. Anton Belyy, Marina Dubova, and Dmitry Nekrasov. ACL 2018. [paper]
[poster]
[slides]
[code]
[blog]
Russian plagiarism detection Framework for Russian Plagiarism Detection Using Sentence Embedding Similarity and Negative Sampling. Anton Belyy and Marina Dubova. Dialogue 2018. [paper]
[slides]
[code]
Hiearchical ARTM improvement Quality Evaluation and Improvement for Hierarchical Topic Modeling. Anton Belyy, Mariia Seleznova, Alexey Sholokhov, and Konstantin Vorontsov. Dialogue 2018. [paper]
[slides]
[demo]

Fun projects

My web-dev projects, written (mostly) on the rare occasions of having spare time, and mostly to play with a fancy new Web framework :)

rysearch screenshot Rysearch (2017 – 2019)
An exploratory search engine, that uses interpretable topic models to organize popular science literature into a hierarchical map and perform document search. Built using Node.js, MongoDB, ZeroMQ, FoamTree, and BigARTM.		 [code] [demo]
esenin screenshot Esenin (2013)
A karaoke music player, featuring songs based on verses of a great 20th-century Russian poet Sergey Esenin. Written overnight using Node.js, Express and CoffeeScript.		 [code] [demo]
lonelord screenshot Lonelord (2013)
A real-time strategy game, where you can build castles, mine resources, wage wars and trade with neighbors… by sending MongoDB database queries! Inspired by mysqlgame.		 [code] [blog]

Page design by Ankit Sultana