DeepAI AI Chat
Log In Sign Up

"Wikily" Neural Machine Translation Tailored to Cross-Lingual Tasks

by   Mohammad Sadegh Rasooli, et al.

We present a simple but effective approach for leveraging Wikipedia for neural machine translation as well as cross-lingual tasks of image captioning and dependency parsing without using any direct supervision from external parallel data or supervised models in the target language. We show that first sentences and titles of linked Wikipedia pages, as well as cross-lingual image captions, are strong signals for a seed parallel data to extract bilingual dictionaries and cross-lingual word embeddings for mining parallel text from Wikipedia. Our final model achieves high BLEU scores that are close to or sometimes higher than strong supervised baselines in low-resource languages; e.g. supervised BLEU of 4.0 versus 12.1 from our model in English-to-Kazakh. Moreover, we tailor our wikily translation models to unsupervised image captioning and cross-lingual dependency parser transfer. In image captioning, we train a multi-tasking machine translation and image captioning pipeline for Arabic and English from which the Arabic training data is a wikily translation of the English captioning data. Our captioning results in Arabic are slightly better than that of its supervised model. In dependency parsing, we translate a large amount of monolingual text, and use it as an artificial training data in an annotation projection framework. We show that our model outperforms recent work on cross-lingual transfer of dependency parsers.


page 2

page 12


Fluency-Guided Cross-Lingual Image Captioning

Image captioning has so far been explored mostly in English, as most ava...

Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning

Cross-lingual transfer learning without labeled target language data or ...

Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards

Generating image descriptions in different languages is essential to sat...

Unsupervised Cross-lingual Image Captioning

Most recent image captioning works are conducted in English as the major...

Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment

Unpaired cross-lingual image captioning has long suffered from irrelevan...

The Cross-Lingual Arabic Information REtrieval (CLAIRE) System

Despite advances in neural machine translation, cross-lingual retrieval ...

Cross-Language Question Re-Ranking

We study how to find relevant questions in community forums when the lan...

Code Repositories


"Wikily" Neural Machine Translation Tailored to Cross-Lingual Tasks.

view repo