Cross-lingual Models of Word Embeddings: An Empirical Comparison
arXiv:1604.00425
Abstract
Despite interest in using cross-lingual knowledge to learn word embeddings for various tasks, a systematic comparison of the possible approaches is lacking in the literature. We perform an extensive evaluation of four popular approaches of inducing cross-lingual embeddings, each requiring a different form of supervision, on four typographically different language pairs. Our evaluation setup spans four different tasks, including intrinsic evaluation on mono-lingual and cross-lingual similarity, and extrinsic evaluation on downstream semantic and syntactic applications. We show that models which require expensive cross-lingual knowledge almost always perform better, but cheaply supervised models often prove competitive on certain tasks.
To appear at ACL 2016
References in corpus (2)
Cited by in corpus (15)
- A Survey Of Cross-lingual Word Embedding Models
- A Survey of Word Embeddings Evaluation Methods
- Multilingual Neural Machine Translation with Task-Specific Attention
- Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
- A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique
- Improving Cross-Lingual Word Embeddings by Meeting in the Middle
- Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context
- Second-Order Word Embeddings from Nearest Neighbor Topological Features
- Embedding Learning Through Multilingual Concept Induction
- Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer
- Neural Machine Translation: A Review and Survey
- Density Matching for Bilingual Word Embedding
- Expanding the Text Classification Toolbox with Cross-Lingual Embeddings
- Characterizing Departures from Linearity in Word Translation
- Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking