Eger, Steffen ; Mehler, Alexander (2016)
On the linearity of semantic change: Investigating Meaning Variation via Dynamic Graph Models.
Berlin, Germany (August 2016)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2016 |
| Autor(en): | Eger, Steffen ; Mehler, Alexander |
| Art des Eintrags: | Bibliographie |
| Titel: | On the linearity of semantic change: Investigating Meaning Variation via Dynamic Graph Models |
| Sprache: | Englisch |
| Publikationsjahr: | August 2016 |
| Verlag: | Association for Computational Linguistics |
| Buchtitel: | Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016) |
| Veranstaltungsort: | Berlin, Germany |
| Veranstaltungsdatum: | August 2016 |
| URL / URN: | http://www.aclweb.org/anthology/P16-2009 |
| Kurzbeschreibung (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. |
| Freie Schlagworte: | UKP_a_DLinNLP;Semantic Change, Word Embeddings |
| ID-Nummer: | TUD-CS-2016-0172 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 31 Dez 2016 14:29 |
| Letzte Änderung: | 31 Aug 2018 09:28 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum