Table understanding in structured documents

2 code implementations • 22 Mar 2019 • Martin Holeček, Antonín Hoskovec, Petr Baudiš, Pavel Klinger

We will work on our newly presented dataset of pro forma invoices, invoices and debit note documents using this representation and propose multiple baselines to solve this labeling problem.

Table Detection

Sentence Pair Scoring: Towards Unified Framework for Text Comprehension

1 code implementation • 19 Mar 2016 • Petr Baudiš, Jan Pichl, Tomáš Vyskočil, Jan Šedivý

We review the task of Sentence Pair Scoring, popular in the literature in various forms - viewed as Answer Sentence Selection, Semantic Text Scoring, Next Utterance Ranking, Recognizing Textual Entailment, Paraphrasing or e. g. a component of Memory Networks.

Natural Language Inference Reading Comprehension +1

Evaluating Go Game Records for Prediction of Player Attributes

no code implementations • 30 Dec 2015 • Josef Moudřík, Petr Baudiš, Roman Neruda

We propose a way of extracting and aggregating per-move evaluations from sets of Go game records.

BIG-bench Machine Learning

COCOpf: An Algorithm Portfolio Framework

no code implementations • 14 May 2014 • Petr Baudiš

As a demonstration, we measure the performance of stock SciPy optimization algorithms and the popular CMA algorithm alone and in a portfolio with two simple selection strategies.