Cross-lingual word analogies using linear transformations between semantic spaces

Abstract

We generalize the word analogy task across languages, to provide a new intrinsic evaluation method for cross-lingual semantic spaces. We experiment with six languages within different language families, including English, German, Spanish, Italian, Czech, and Croatian. State-of-the-art monolingual semantic spaces are transformed into a shared space using dictionaries of word translations. We compare several linear transformations and rank them for experiments with monolingual (no transformation), bilingual (one semantic space is transformed to another), and multilingual (all semantic spaces are transformed onto English space) versions of semantic spaces. We show that tested linear transformations preserve relationships between words (word analogies) and lead to impressive results. We achieve average accuracy of 51.1%, 43.1%, and 38.2% for monolingual, bilingual, and multilingual semantic spaces, respectively. this does not make sense because w a 1 and w a 2 are in a different language. Thus we discard only w b 3 from the search.

CompareWords: Measuring semantic change in word usage in different corpora

“…Our software allows using of two methods of transformations. The transformation can be done by a modification of the orthogonal transformation [2] or by Canonical Correlation Analysis (CCA) using the implementation from [3]. The goal of the transformation is shown in Fig.…”

EVALITA 2020: Overview of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian

“…We train a separate semantic space for each corpus, and subsequently, we map these two spaces into one common cross-lingual space. We use methods for cross-lingual mapping (Brychcín et al, 2019;Artetxe et al, 2016;Artetxe et al, 2018a;Artetxe et al, 2018b) and thanks to the large similarity between L 1 and L 2 the quality of transformation should be high. We compute cosine similarity of the transformed word vectors to classify whether the target words changed their sense.…”

UWB at SemEval-2020 Task 1: Lexical Semantic Change Detection

“…We perform a cross-lingual mapping of the two vector spaces, getting two matrices Xs and Xt projected into a shared space. We select two methods for the crosslingual mapping Canonical Correlation Analysis (CCA) using the implementation from (Brychcín et al, 2019) and a modification of the Orthogonal Transformation from VecMap (Artetxe et al, 2018b). Both of these methods are linear transformations.…”

“…We train separate semantic space for each corpus and subsequently, we map these two spaces into one common cross-lingual space. We use methods for cross-lingual mapping (Brychcín et al, 2019;Artetxe et al, 2016;Artetxe et al, 2017;Artetxe et al, 2018a;Artetxe et al, 2018b) and thanks to the large similarity between L 1 and L 2 the quality of transformation should be high. We compute cosine similarity to classify and rank the target words, see Section 3 for details.…”