Bootstrapping Translation Detection and Sentence Extraction from Comparable Corpora

Abstract

Most work on extracting parallel text from comparable corpora depends on linguistic resources such as seed parallel documents or translation dictionaries. This paper presents a simple baseline approach for bootstrapping a parallel collection. It starts by observing documents published on similar dates and the cooccurrence of a small number of identical tokens across languages. It then uses fast, online inference for a latent variable model to represent multilingual documents in a shared topic space where it can do efficient nearestneighbor search. Starting from the Gigaword collections in English and Spanish, we train a translation system that outperforms one trained on the WMT'11 parallel training set.

An Empirical Study on Crosslingual Transfer in Probabilistic Topic Models

“…Topic assignments are denoted as z, and w denotes observed tokens. extensively used and adapted in various ways for different crosslingual tasks (Krstovski and Smith 2011;Moens and Vulic 2013;Vulić and Moens 2014;Liu, Duh, and Matsumoto 2015;Krstovski and Smith 2016).…”

“…Models that transfer knowledge on the document level have many variants, including SOFTLINK , comparable bilingual LDA (C-BILDA; Heyman, Vulic, and Moens 2016), the partially connected multilingual topic model (PCMLTM; Liu, Duh, and Matsumoto 2015), and multi-level hyperprior polylingual topic model (MLHPLTM; Krstovski, Smith, and Kurtz 2016). SOFTLINK generalizes DOCLINK by using a dictionary, so that documents can be linked based on overlap in their vocabulary, even if the corpus is not parallel or comparable.…”