Multilingual Reliability and "Semantic" Structure of Continuous Word Spaces
نویسندگان
چکیده
•The Google semantic/syntactic (analogies) →Constructed German counterpart through manual translation by 3 human judges •The paradigmatic semantic relation (analogies) →The dataset was adapted by Lenci & Benotto for English and by Scheible & Schulte im Walde for German. Examples: Antonym-Adj psychological : physical :: maximum : minimum Antonym-NN biblical : secular :: deaf : hearing Antonym-Verb split : join :: sum : subtract Hyperonym-NN groove : dance :: maze : puzzle Synonym-NN skyline : horizon :: rumor : gossip Antonym-Adj faul : eißig :: traurig : heiter Antonym-NN Ausnahmefall : Regelfall :: Deutlichkeit : Undeutlichkeit Antonym-Verb lockern :: festigen : ärgern : freuen Hyperonym-NN Stuhl : Möbel :: Bibel : Buch Synonym-NN P anze : Gewächs :: Zeit : Dauer
منابع مشابه
Psychometric Properties of the Persian Word Pairs Task for Declarative Memory Assessment
Objective: According to the declarative/procedural model, the semantic aspect of language depends on the brain structures responsible for declarative memory. The word pairs task is a common tool for evaluating declarative memory. The current study aimed to design a valid and reliable task for evaluating declarative memory in Persian children at learning and retention stages and to investigate i...
متن کاملMultilingual Word Embeddings using Multigraphs
We present a family of neural-network– inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of embeddings that exhibit higher accuracy on syntactic and semantic compositionality, as well as multilingual semantic similarity, compared to previous models trai...
متن کاملMultilingual Distributional Semantic Models: Toward a Computational Model of the Bilingual Mental Lexicon
In this paper, we propose a novel framework of a multilingual distributional semantic model to provide a psychologically plausible computational model of the bilingual mental lexicon. In the proposed framework, a monolingual semantic space for each target language is first generated from the corresponding monolingual corpus. These monolingual semantic spaces are then converted into ones with co...
متن کاملSemantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
We present ATTRACT-REPEL, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. ATTRACT-REPEL facilitates the use of constraints from monoand crosslingual resources, yielding semantically specialised cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct h...
متن کاملSemantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
We present ATTRACT-REPEL, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. ATTRACT-REPEL facilitates the use of constraints from monoand crosslingual resources, yielding semantically specialized cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct h...
متن کامل