A detailed error analysis is a fundamental step in every natural language processing task, as
to be able to diagnose what went wrong will provide cues to decide which research …

Every type of machine translation system (ie neural, statistical, rule-based machine
translation system) is equal important to build a sophistical hybrid machine translation …

Compared to the edited genres that have played a central role in NLP research, microblog
texts use a more informal register with nonstandard lexical items, abbreviations, and free …

This paper describes a method to efficiently leverage Brazilian Portuguese resources as
European Portuguese resources. Brazilian Portuguese and European Portuguese are two …

In this paper, we leverage the existence of dual subtitles as a source of parallel data. Dual
subtitles present viewers with two languages simultaneously, and are generally aligned in …

Phrase-based machine translation models have shown to yield better translations than Word-
based models, since phrase pairs encode the contextual information that is needed for a …

This work describes a process to extract Named Entity (NE) translations from the text
available in web links (anchor texts). It translates a NE by retrieving a list of web documents …

One of the fundamental assumptions in statistical machine translation (SMT) is that the
correspondence between a sentence and its translation can be explained in terms of an …

Lexicalized reordering models play a central role in phrase-based statistical machine
translation systems. Starting from the distance-based reordering model, improvements have …

Bitext alignment is the task of aligning a text in a source language and its translation in the
target language. Aligning amounts to finding the translational correspondences between …