Search Results for author: Piotr Szymański

Found 10 papers, 1 papers with code

Is the Best Better? Bayesian Statistical Model Comparison for Natural Language Processing

no code implementations EMNLP 2020 Piotr Szymański, Kyle Gorman

Recent work raises concerns about the use of standard splits to compare natural language processing models.

A Network Perspective on Stratification of Multi-Label Data

no code implementations27 Apr 2017 Piotr Szymański, Tomasz Kajdanowicz

We present a new approach to stratifying multi-label data for classification purposes based on the iterative stratification approach proposed by Sechidis et.

Community Detection General Classification +1

Is a Data-Driven Approach still Better than Random Choice with Naive Bayes classifiers?

no code implementations13 Feb 2017 Piotr Szymański, Tomasz Kajdanowicz

In case of F1 scores and Subset Accuracy - data driven approaches were more likely to perform better than random approaches than otherwise in the worst case.

General Classification Multi-Label Classification

A scikit-based Python environment for performing multi-label classification

2 code implementations5 Feb 2017 Piotr Szymański, Tomasz Kajdanowicz

It provides native Python implementations of popular multi-label classification methods alongside a novel framework for label space partitioning and division.

General Classification Multi-Label Classification

How is a data-driven approach better than random choice in label space division for multi-label classification?

no code implementations7 Jun 2016 Piotr Szymański, Tomasz Kajdanowicz, Kristian Kersting

We show that fastgreedy and walktrap community detection methods on weighted label co-occurence graphs are 85-92% more likely to yield better F1 scores than random partitioning.

Community Detection General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.