paper-with-me

Papers

Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach

2018-08-27 · TACL 2019 3 · Pratik Jawanpuria, Arjun Balgovind, Anoop Kunchukuttan, Bamdev Mishra

We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples learning the transformation from the source language to the target language into (a) learning rotations for language-specific embeddings to align them to a common space, and (b) learning a similarity metric in the common space to model similarities between the embeddings. We model the bilingual mapping problem as an optimization problem on smooth Riemannian manifolds. We show that our approach outperforms previous approaches on the bilingual lexicon induction and cross-lingual word similarity tasks. We also generalize our framework to represent multiple languages in a common latent space. In particular, the latent space representations for several languages are learned jointly, given bilingual dictionaries for multiple language pairs. We illustrate the effectiveness of joint learning for multiple languages in zero-shot word translation setting. Our implementation is available at https://github.com/anoopkunchukuttan/geomm .

📄 PDF Abstract BibTeX arXiv:1808.08773

Code (2)

anoopkunchukuttan/geomm 공식 구현 tf
microsoft/recommenders tf

Tasks

Bilingual Lexicon InductionMultilingual Word EmbeddingsRecommendation SystemsTranslationWord EmbeddingsWord SimilarityWord Translation

Similar Papers 제목 키워드 기반

Multilingual Factor Analysis

2019-05-14 · ACL 2019 7 · Francisco Vargas, Kamen Brestnichki, Alex Papadopoulos-Korfiatis, Nils Hammerla

In this work we approach the task of learning multilingual word representations in an offline manner by fitting a generative latent variable model to a multilingual dictionary. We model equivalent words in different lang…

Learning Geometric Word Meta-Embeddings

2020-04-20 · WS 2020 7 · Pratik Jawanpuria, N T V Satya Dev, Anoop Kunchukuttan, Bamdev Mishra

We propose a geometric framework for learning meta-embeddings of words from different embedding sources. Our framework transforms the embeddings into a common latent space, where, for example, simple averaging of differe…

Word Similarity

Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context

2017-06-25 · WS 2017 8 · Shyam Upadhyay, Kai-Wei Chang, Matt Taddy, Adam Kalai 외

Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense o…

Representation LearningWord Embeddings

Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models

2018-09-07 · Takashi Wada, Tomoharu Iwata

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of mul…

Cross-Lingual Word EmbeddingsSentenceWord AlignmentWord Embeddings

Cross-Domain Matching for Bag-of-Words Data via Kernel Embeddings of Latent Distributions

2015-12-01 · NeurIPS 2015 12 · Yuya Yoshikawa, Tomoharu Iwata, Hiroshi Sawada, Takeshi Yamada

We propose a kernel-based method for finding matching between instances across different domains, such as multilingual documents and images with annotations. Each instance is assumed to be represented as a multiset of fe…

Articles