Paper accepted at LWDA 2020

We are happy to announce that our paper "Sense Tree: Discovery of New Word Senses with Graph-based Scoring" has been accepted at the LWDA 2020 conference in Bonn. The conference will be fully virtual this year and we are looking forward to present our work there. This publication is the result of our Masterproject "Geneology of Language" in the winter semester 2019/2020.

Authors: Jan Ehmüller, Lasse Kohlmeyer, Holly McKee, Daniel Paeschke, Tim Repke, Ralf Krestel and Felix Naumann

Abstract:
Language is dynamic and constantly evolving: both the us-age context and the meaning of words change over time. Identifying words that acquired new meanings and the point in time at which new word senses emerged is elementary for word sense disambiguation and entity linking in historical texts. For example, cloud once stood mostly for the weather phenomenon and only recently gained the new sense of cloud computing. We propose a clustering-based approach that computes sense trees, showing how meanings of words change over time. The produced results are easy to interpret and explain using a drill-down mechanism. We evaluate our approach qualitatively on the Corpus of Historic American English (COHA), which spans two hundred years.

IEEE
J. Ehmüller et al., “Sense Tree: Discovery of New Word Senses with Graph-based Scoring,” in Proceedings of the Conference on “Lernen, Wissen, Daten, Analysen” (LWDA), 2020, pp. 1--12.

BibTeX
@inproceedings{ehmuller2020sense,
abstract = {Language is dynamic and constantly evolving: both the us-age context and the meaning of words change over time. Identifying words that acquired new meanings and the point in time at which new word senses emerged is elementary for word sense disambiguation and entity linking in historical texts. For example, cloud once stood mostly for the weather phenomenon and only recently gained the new sense of cloud computing. We propose a clustering-based approach that computes sense trees, showing how meanings of words change over time. The produced results are easy to interpret and explain using a drill-down mechanism. We evaluate our approach qualitatively on the Corpus of Historic American English (COHA), which spans two hundred years.},
author = {Ehmüller, Jan and Kohlmeyer, Lasse and McKee, Holly and Paeschke, Daniel and Repke, Tim and Krestel, Ralf and Naumann, Felix},
booktitle = {Proceedings of the Conference on "Lernen, Wissen, Daten, Analysen" (LWDA)},
pages = {1--12},
title = {Sense Tree: Discovery of New Word Senses with Graph-based Scoring},
year = 2020
}