TU Darmstadt / ULB / TUbiblio

On the linearity of semantic change: Investigating Meaning Variation via Dynamic Graph Models

Eger, Steffen and Mehler, Alexander (2016):
On the linearity of semantic change: Investigating Meaning Variation via Dynamic Graph Models.
In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), Association for Computational Linguistics, Berlin, Germany, August 2016, [Online-Edition: http://www.aclweb.org/anthology/P16-2009],
[Conference or Workshop Item]

Abstract

We consider two graph models of semantic change. The first is a time-series model that relates embedding vectors from one time period to embedding vectors of previous time periods. In the second, we construct one graph for each word: nodes in this graph correspond to time points and edge weights to the similarity of the word's meaning across two time points. We apply our two models to corpora across three different languages. We find that semantic change is linear in two senses. Firstly, today's embedding vectors (= meaning) of words can be derived as linear combinations of embedding vectors of their neighbors in previous time periods. Secondly, self-similarity of words decays linearly in time. We consider both findings as new laws/hypotheses of semantic change.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Eger, Steffen and Mehler, Alexander
Title: On the linearity of semantic change: Investigating Meaning Variation via Dynamic Graph Models
Language: English
Abstract:

We consider two graph models of semantic change. The first is a time-series model that relates embedding vectors from one time period to embedding vectors of previous time periods. In the second, we construct one graph for each word: nodes in this graph correspond to time points and edge weights to the similarity of the word's meaning across two time points. We apply our two models to corpora across three different languages. We find that semantic change is linear in two senses. Firstly, today's embedding vectors (= meaning) of words can be derived as linear combinations of embedding vectors of their neighbors in previous time periods. Secondly, self-similarity of words decays linearly in time. We consider both findings as new laws/hypotheses of semantic change.

Title of Book: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016)
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: UKP_a_DLinNLP;Semantic Change, Word Embeddings
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Berlin, Germany
Event Dates: August 2016
Date Deposited: 31 Dec 2016 14:29
Official URL: http://www.aclweb.org/anthology/P16-2009
Identification Number: TUD-CS-2016-0172
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item