Nina Tahmasebi on Nina Tahmasebi

Material för studiecirkel i digitala metoder för DH

Mon, 30 Sep 2019 00:00:00 +0200

Introduktion till data-intensiv forskningsmetodologi

Digital Text

Språkteknologi

Maskininlärning

DWUG: A large Resource of Diachronic Word Usage Graphs in Four Languages

Thu, 26 Aug 2021 00:00:00 +0200

Computational approaches to semantic change

Sun, 22 Aug 2021 00:00:00 +0200

Survey of computational approaches to lexical semantic change detection

Sun, 22 Aug 2021 00:00:00 +0200

Visualization systems and novel applications

Sun, 22 Aug 2021 00:00:00 +0200

Challenges for computational lexical semantic change

Sat, 21 Aug 2021 00:00:00 +0200

SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection

Wed, 22 Jul 2020 00:00:00 +0200

Post-Evaluation Data for SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection

Wed, 27 May 2020 00:00:00 +0200

Creating an Annotated Corpus for Aspect-Based Sentiment Analysis in Swedish

Mon, 30 Mar 2020 00:00:00 +0200

The Strengths and Pitfalls of Large-Scale Text Mining for Literary Studies

Mon, 30 Mar 2020 00:00:00 +0200

Swedish Test Data for SemEval 2020 Task 1

Wed, 19 Feb 2020 00:00:00 +0100

SemEval 2020 Task 1: Unsupervised Lexical Semantic Change Detection

Wed, 01 Jan 2020 00:00:00 +0100

The past decade has seen a rise in academic work focussing on the computational tackling of lexical semantic change. An overview of the literature until 2018 is available in Tahmasebi et al. (2018) and Kutuzov et al. (2018). Nonetheless, most studies have different evaluation procedures and tackle different languages, corpora, and periods, making systems difficult to compare. This SemEval task aims to introduce a simple evaluation framework for unsupervised lexical semantic change detection. Tasks

There are two tasks: a classification task, and a ranking task. For each language, both tasks are based on the same two corpora, which span different periods. Corpora will be provided in four languages: German, English, Swedish, and Latin. Systems will be evaluated against a ground truth, as annotated (Schlechtweg et al., 2018) by human native speakers (except for Latin, which was annotated by scholars of Latin).

Swedish testdata available here, postevaluation data for all participating languages available here. Our task description paper is available on ArXiV.

The workshop will be held online on December 12-13, 2020.

Project pages

Time for change: Evaluating models of semantic change without evaluation tasks

Sat, 09 Nov 2019 00:00:00 +0100

Digital Literacy

Wed, 09 Oct 2019 10:00:00 +0200

Video comes in two parts: Video part-1 and Video part-2

Literary studies and DH

Wed, 09 Oct 2019 10:00:00 +0200