Multilingual Reliability and “Semantic” Structure of Continuous Word Spaces

By Maximilian Köper, Christian Scheible, Sabine Schulte im Walde. 2015

57 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Word Vectors for 157 Languages (2018, methodology): “In our evaluation, we use the dataset of Svoboda and Brychcin (2016) for Czech, that of K¨oper et al. (2015) for German, that of Cardellino (2016) for Spanish, that of Venekoski and Vankka (2017) for Finnish, that of Berardi et al. (2015) for Italian, the European variant of the dataset proposed by…”
Enriching Word Vectors with Subword Information (2016, methodology): “We use the datasets introduced by Mikolov et al. (2013a) for English, by Svoboda and Brychcin (2016) for Czech, by Köper et al. (2015) for German and by Berardi et al. (2015) for Italian.”
The (too Many) Problems of Analogical Reasoning with Word Vectors (2017, background): “It appears that not all relations can be identified in this way, with lexical semantic relations such as synonymy and antonymy being particularly difficult (Köper et al., 2015; Vylomova et al., 2016).”
Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling (2015, methodology): “Although WS353 was translated to German and then scored with the German JL (Köper et al., 2015), we translated and scored the dataset again in order to keep the same translation and scoring decisions across our datasets.”
Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen (2016, background): “It was later shown to not work as well for a wider range of relations (Köper et al., 2015; Gladkova et al., 2016).”
Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn’t. (2016, methodology): “The low accuracy on the lexicographic part of BATS is consistent with the findings of Köper et al. (2015). It is not clear why lexicographic relations are so difficult to detect with the vector offset method, despite numerous successful word similarity tests on much the same relations, and the fact ”