Nizar Habash

Optimizing Tokenization Choice for Machine Translation across Multiple Target Languages

2017 · ˜The œPrague Bulletin of Mathematical Linguistics

Abstract Tokenization is very helpful for Statistical Machine Translation (SMT), especially when translating from morphologically rich languages. Typically, a single tokenization scheme is applied to the entire source-language text and regardless of the target language. …

A Cross-lingual Messenger with Keyword Searchable Phrases for the Travel Domain

2018 · International Conference on Computational Linguistics

We present Qutr (Query Translator), a smart cross-lingual communication application for the travel domain. Qutr is a real-time messaging app that automatically translates conversations while supporting keyword-to-sentence matching. Qutr relies on querying a database that …

The Impact of Preprocessing on Arabic-English Statistical and Neural Machine Translation

2019 · arXiv (Cornell University)

Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While linguistically-motivated tokenization techniques were shown to have significant effects on the performance of statistical MT, it remains unclear if those …

CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

2017

Daniel Zeman, Martin Popel, Milan Straka, Jan Hajič, Joakim Nivre, Filip Ginter, Juhani Luotolahti, Sampo Pyysalo, Slav Petrov, Martin Potthast, Francis Tyers, Elena Badmaeva, Memduh Gokirmak, Anna Nedoluzhko, Silvie Cinková, Jan Hajič jr., Jaroslava Hlaváčová, …

Fine-Grained Arabic Dialect Identification

2018 · International Conference on Computational Linguistics

Previous work on the problem of Arabic Dialect Identification typically targeted coarse-grained five dialect classes plus Standard Arabic (6-way classification). This paper presents the first results on a fine-grained dialect classification task covering 25 specific …

The MADAR Shared Task on Arabic Fine-Grained Dialect Identification

2019

In this paper, we present the results and findings of the MADAR Shared Task on Arabic Fine-Grained Dialect Identification. This shared task was organized as part of The Fourth Arabic Natural Language Processing Workshop, collocated …

The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models

2021 · arXiv (Cornell University)

In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: …