[PDF][PDF] Sparse bilingual word representations for cross-lingual lexical entailment

Y Vyas, M Carpuat - Proceedings of the 2016 conference of the …, 2016 - aclanthology.org
We introduce the task of cross-lingual lexical entailment, which aims to detect whether the
meaning of a word in one language can be inferred from the meaning of a word in another …

Leveraging orthographic similarity for multilingual neural transliteration

A Kunchukuttan, M Khapra, G Singh… - Transactions of the …, 2018 - direct.mit.edu
We address the task of joint training of transliteration models for multiple language pairs
(multilingual transliteration). This is an instance of multitask learning, where individual tasks …

Encoding prior knowledge with eigenword embeddings

D Osborne, S Narayan, SB Cohen - Transactions of the Association …, 2016 - direct.mit.edu
Canonical correlation analysis (CCA) is a method for reducing the dimension of data
represented using two views. It has been previously used to derive word embeddings …

False-friend detection and entity matching via unsupervised transliteration

Y Chen, S Skiena - ar** abstract scenes to text
N Papasarantopoulos, H Jiang, S Cohen - Proceedings of the AAAI …, 2018 - ojs.aaai.org
We describe a technique for structured prediction, based on canonical correlation analysis.
Our learning algorithm finds two projections for the input and the output spaces that aim at …

[PDF][PDF] Canonical Correlation Inference for Map** Abstract Scenes to Text

H Jiang, N Papasarantopoulos, SB Cohen - CoRR, 2016 - homepages.inf.ed.ac.uk
We describe a technique for structured prediction, based on canonical correlation analysis.
Our learning algorithm finds two projections for the input and the output spaces that aim at …