---
title: "Iterative Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora"
authors:
  - "Meiping Dong"
  - "Yang Liu"
  - "Huan-Bo Luan"
  - "Maosong Sun"
  - "Tatsuya Izuha"
  - "Dakun Zhang"
doi: ""
url: "https://ijcai.org/proceedings/2015/180"
pdf: "https://ijcai.org/proceedings/2015/0180.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "1250-1255"
track: "Main Track"
keywords:
---

# Iterative Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

Meiping Dong, Yang Liu, Huan-Bo Luan, Maosong Sun, Tatsuya Izuha, Dakun Zhang

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 1250-1255.

## Abstract

While parallel corpora are an indispensable resource for data-driven multilingual natural language processing tasks such as machine translation, they are limited in quantity, quality and coverage. As a result, learning translation models from non-parallel corpora has become increasingly important nowadays, especially for low-resource languages. In this work, we propose a joint model for iteratively learning parallel lexicons and phrases from nonparallel corpora. The model is trained using a Viterbi EM algorithm that alternates between constructing parallel phrases using lexicons and updating lexicons based on the constructed parallel phrases. Experiments on Chinese-English datasets show that our approach learns better parallel lexicons and phrases and improves translation performance significantly.