Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity
This article explores the distinction between paradigmatic semantic relations, both from a cognitive and a computational linguistic perspective. Focusing on an existing dataset of German synonyms, antonyms and hypernyms across the word classes of nouns, verbs and adjectives, we assess human ratings...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Computer Science, Polish Academy of Sciences
2020-06-01
|
| Series: | Journal of Language Modelling |
| Subjects: | |
| Online Access: | https://jlm.ipipan.waw.pl/index.php/JLM/article/view/199 |
| _version_ | 1818905660699443200 |
|---|---|
| author | Sabine Schulte im Walde |
| author_facet | Sabine Schulte im Walde |
| author_sort | Sabine Schulte im Walde |
| collection | DOAJ |
| description | This article explores the distinction between paradigmatic semantic relations, both from a cognitive and a computational linguistic perspective. Focusing on an existing dataset of German synonyms, antonyms and hypernyms across the word classes of nouns, verbs and adjectives, we assess human ratings and a supervised classification model using window-based and pattern-based distributional vector spaces. Both perspectives suggest differences in relation distinction across word classes, but easy vs. difficult class–relation combinations differ, exhibiting stronger ties between ease and naturalness of classdependent relations for humans than for computational models. In addition, we demonstrate that distributional information is indeed a difficult starting point for distinguishing between paradigmatic relations but that even a simple classification model is able to manage this task. The fact that the most salient vector spaces and their success vary across word classes and paradigmatic relations suggests that combining feature types for relation distinction is better than applying them in isolation. |
| first_indexed | 2024-12-19T21:26:52Z |
| format | Article |
| id | doaj.art-ac659f95c4de44e9b5d214b994418344 |
| institution | Directory Open Access Journal |
| issn | 2299-856X 2299-8470 |
| language | English |
| last_indexed | 2024-12-19T21:26:52Z |
| publishDate | 2020-06-01 |
| publisher | Institute of Computer Science, Polish Academy of Sciences |
| record_format | Article |
| series | Journal of Language Modelling |
| spelling | doaj.art-ac659f95c4de44e9b5d214b9944183442022-12-21T20:05:07ZengInstitute of Computer Science, Polish Academy of SciencesJournal of Language Modelling2299-856X2299-84702020-06-018153–10153–10110.15398/jlm.v8i1.199144Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similaritySabine Schulte im Walde0https://orcid.org/0000-0002-8975-6255Universität Stuttgart, GERMANYThis article explores the distinction between paradigmatic semantic relations, both from a cognitive and a computational linguistic perspective. Focusing on an existing dataset of German synonyms, antonyms and hypernyms across the word classes of nouns, verbs and adjectives, we assess human ratings and a supervised classification model using window-based and pattern-based distributional vector spaces. Both perspectives suggest differences in relation distinction across word classes, but easy vs. difficult class–relation combinations differ, exhibiting stronger ties between ease and naturalness of classdependent relations for humans than for computational models. In addition, we demonstrate that distributional information is indeed a difficult starting point for distinguishing between paradigmatic relations but that even a simple classification model is able to manage this task. The fact that the most salient vector spaces and their success vary across word classes and paradigmatic relations suggests that combining feature types for relation distinction is better than applying them in isolation.https://jlm.ipipan.waw.pl/index.php/JLM/article/view/199semantic relationshuman ratingsdistributional semanticsautomatic classification |
| spellingShingle | Sabine Schulte im Walde Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity Journal of Language Modelling semantic relations human ratings distributional semantics automatic classification |
| title | Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity |
| title_full | Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity |
| title_fullStr | Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity |
| title_full_unstemmed | Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity |
| title_short | Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity |
| title_sort | distinguishing between paradigmatic semantic relations across word classes human ratings and distributional similarity |
| topic | semantic relations human ratings distributional semantics automatic classification |
| url | https://jlm.ipipan.waw.pl/index.php/JLM/article/view/199 |
| work_keys_str_mv | AT sabineschulteimwalde distinguishingbetweenparadigmaticsemanticrelationsacrosswordclasseshumanratingsanddistributionalsimilarity |