Home - ufal/NPFL095 GitHub Wiki

Modern Methods in Computational Linguistics NPFL095

See Requirements for getting credits. Let me know if you are interested in this course.

Autumn&Winter 2025/2026

Monday, 17:20-18:50, S6

date speaker paper
Sep 29 startup meeting
Oct 6 Martin Popel Sravana Reddy, Kevin Knight: What We Know About The Voynich Manuscript, ACL 2011.
Oct 13 Martin Popel Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean: Efficient Estimation of Word Representations in Vector Space, ICLR 2013. Questions
Oct 20 Jan Pavelka Ashish Vaswani et al.: Attention Is All You Need (The Transformer paper) (blog), NIPS 2017. Questions Video
Oct 27 -- Turing Game (online)
Nov 3 Hanseo Yoo Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, 2018. Questions
Nov 10 Diana Pavlenok Schick et al.: Toolformer: Language Models Can Teach Themselves to Use Tools, 2023. Questions
Nov 17 no seminar Struggle for Freedom and Democracy Day
Nov 24 Roman Tomchik Sebastien Bubeck et al.: Sparks of Artificial General Intelligence: Early experiments with GPT-4, 2023. Chapters: 8, 9.3(Bias),10 Questions
Dec 1 Alina Haitota Elena Voita, Rico Sennrich, Ivan Titov: The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives, 2019. Questions. See also a blog.
Dec 8 Rob Chiocchio Sennrich, Haddow, Birch: Neural Machine Translation of Rare Words with Subword Units, 2015 Questions
Dec 15 Benjamin Reeves Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu: BLEU: a Method for Automatic Evaluation of Machine Translation, ACL 2002. Questions
Jan 5 Kornelia Skorupinska Thibault Sellam, Dipanjan Das, Ankur Parikh: BLEURT: Learning Robust Metrics for Text Generation, 2020

Papers suggestions

Papers suggested by students

Add your suggestions here

NN

Dependency parsing and Universal Dependencies

LLM

See also papers covered in Past semesters, especially those on structured prediction (M. Collins et al., A.McCallum et al., J. Lafferty et al.). Unless otherwise stated, teaching materials for this course (all content on this wiki) are available under CC BY-SA 4.0.