*2017: For the second time, I was active participant in LIUM team which were ranked first in Task 1: Multimodal Machine Translation of WMT 2017 Multimodal Machine Translation Shared Task. Official results are published:here and it will be presented in the SECOND CONFERENCE ON MACHINE TRANSLATION (WMT17), September 7-8, 2017 Copenhagen, Denmark

*2016: I was active participant in LIUM team which were ranked first in both tasks of WMT 2016 Multimodal Machine Translation Shared Task. Official results are published in : A Shared Task on Multimodal Machine Translation and Crosslingual Image Description in the first conference of MT, 11-12 August 2016 Berlin, Germany

*2016: Our paper entitled From Arabic User-Generated Content to Machine Translation: Integrating Automatic Error Correction won the best presentation award at CICLING 2016: 17th International Conference on Intelligent Text Processing and Computational Linguistics

List of my publications

Accepted in the second MTC2017: Ozan Caglayan, Walid Aransa, Yaxsng Wang, Marc Masana, Mercedes Garcia-Martinez, Fethi Bougares and Loic Barrault, LIUM Machine Translation Systems for WMT17 News Translation Task (WMT17), Second Conference on Machine Translation (WMT17), September 7-8, 2017, Copenhagen, Denmark. (Download)

Accepted in the second MTC2017: Ozan Caglayan, Walid Aransa, Yaxsng Wang, Marc Masana, Mercedes Garcia-Martinez, Fethi Bougares, Loic Barrault, Marc Masana, Luis Herranz and Joost van de Weijer, LIUM-CVC Submissions for WMT17 Multimodal Translation Task, Second Conference on Machine Translation (WMT17), September 7-8, 2017, Copenhagen, Denmark. (Download)

Ozan Caglayan, Walid Aransa, Yaxsng Wang, Marc Masana, Mercedes Garcia-Martinez, Fethi Bougares, Loic Barrault and Joost van de Weijer, Does Multimodality Help Human and Machine for Translation and Image Captioning?, First Conference on Machine Translation (WMT16), 11-12 August 2016, Berlin, Germany. (Download)

Haithem Afli, Walid Aransa, Pintu Lohar and Andy Way, From Arabic User-Generated Content to Machine Translation: Integrating Automatic Error Correction, CICLING 2016, April 3–9, 2016, Konya, Turkey.

Walid Aransa, Holger Schwenk, Loïc Barrault, LIUM, University of Le Mans. Improving CSLM using auxiliary features, IWSLT 2015, 3-4 December 2015, Da Nang, Vietnam. (Download)

Rico Sennrich, Holger Schwenk, and Walid Aransa. A multi-domain translation model framework for statistical machine translation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 832-840,Sofia, Bulgaria, August 2013. Association for Computational Linguistics. (Download)

Walid Aransa, Semi-supervised transliteration mining from parallel Corpora. journe des doctorants de l ecole doctorale STIM (JDOC13), Nantes, France. (Website)

Walid Aransa, Holger Schwenk, Loïc Barrault, LIUM, University of Le Mans. Semi-supervised transliteration mining from parallel and comparable corpora, Proceedings IWSLT'12, 2012. (Download)

Walid Aransa, Mohamed Kouta, Mohammed Sakre, College of Computing & Information Technology, Arab Academy for Science and Technology & Maritime Transport, Injected linguistic tags to improve phrase based SMT, Computer and Automation Engineering (ICCAE), Singapore, 26-28 Feb, 2010. (Download)

Islam Youssef, Walid Aransa, Ibrahim F. Imam. College of Computing & Information Technology, Arab Academy for Science and Technology & Maritime Transport. An English-To-Arabic Web Translation Agent, In Proceedings of ICENCO'4, 2004. (Download - Website)

Projects

My Software/Tools

My Patents

Data/Number Entities detector
This is a free small rule based tool to detect several entities in parallel or mono text (Download)
Another Free script
Another Free script(Download)
Another Free script
Another Free script (Download)

1. Automatically detecting layout of bidirectional (BIDI) text (US Patent US9158742)

2. Automatically detecting layout of bidirectional (BIDI) text (US Patent US8271873)

3. Automatically detecting layout of bidirectional (BIDI) text (US Patent US20110107202)

4. Automatically detecting layout of bidirectional (BIDI) text (US Patent US20120266065)