458 citations · 979 across the 26 of their papers we have counts for
Showing 2016Show all
3 papers · 1 filter
cs.CL2016
Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data
Tengfei Ma, Tetsuya Nasukawa
Topic models have been successfully applied in lexicon extraction. However, most previous methods are limited to document-aligned data. In this paper, we try to address two challen…
math.NA2016
Accelerated Kaczmarz Algorithms using History Information
Tengfei Ma
The Kaczmarz algorithm is a well known iterative method for solving overdetermined linear systems. Its randomized version yields provably exponential convergence in expectation. In…
cs.CL2016★ 18 cited
Learning Crosslingual Word Embeddings without Bilingual Corpora
Long Duong, Hiroshi Kanayama, Tengfei Ma +2
Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive res…