arXiv subjects

Tengfei Ma

Publications and source records attributed to Tengfei Ma.

111 records · Page 7Linked to original sources

arXiv2017

Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data

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 challenges of applying topic models to lexicon extraction in non-parallel data: 1) hard to model the word relationship and 2) noisy seed dictionary. To solve these two challenges, we propose two new bilingual topic models to better capture the semantic information of each word while discriminating the multiple translations in a noisy seed dictionary. We extend the scope of topic models by inverting the roles of "word" and "document". In addition, to solve the problem of noise in seed dictionary, we incorporate the probability of translation selection in our models. Moreover, we also propose an effective measure to evaluate the similarity of words in different languages and select the optimal translation pairs. Experimental results using real world data demonstrate the utility and efficacy of the proposed models.

cs.CL↗

arXiv2016

Accelerated Kaczmarz Algorithms using History Information

The Kaczmarz algorithm is a well known iterative method for solving overdetermined linear systems. Its randomized version yields provably exponential convergence in expectation. In this paper, we propose two new methods to speed up the randomized Kaczmarz algorithm by utilizing the past estimates in the iterations. The first one utilize the past estimates to get a preconditioner. The second one combines the stochastic average gradient (SAG) method with the randomized Kaczmarz algorithm. It takes advantage of past gradients to improve the convergence speed. Numerical experiments indicate that the new algorithms can dramatically outperform the standard randomized Kaczmarz algorithm.

math.NA↗

arXiv2016

Learning Crosslingual Word Embeddings without Bilingual Corpora

Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual data or were unable to handle polysemy. We address these drawbacks in our method which takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages. Our model achieves state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive results on the monolingual word similarity and cross-lingual document classification task.

cs.CL↗