15883

Attention-based NMT Models as Feature Functions in Phrase-based SMT

Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
Faculty of Mathematics and Computer Science, Adam Mickiewicz University in Poznan
arXiv:1605.04809 [cs.CL], (16 May 2016)
@article{junczys-dowmunt2016amuuedin,

   title={The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT},

   author={Junczys-Dowmunt, Marcin and Dwojak, Tomasz and Sennrich, Rico},

   year={2016},

   month={may},

   archivePrefix={"arXiv"},

   primaryClass={cs.CL}

}

Download Download (PDF)   View View   Source Source   

251

views

This paper describes the AMU-UEDIN submissions to the WMT 2016 shared task on news translation. We explore methods of decode-time integration of attention-based neural translation models with phrase-based statistical machine translation. Efficient batch-algorithms for GPU-querying are proposed and implemented. For English-Russian, the phrase-based system cannot surpass state-of-the-art stand-alone neural models. For the Russian-English task, our submission achieves the top BLEU result, outperforming the best pure-neural system by 1.1 BLEU points and our own phrase-based baseline by 1.6 BLEU. In follow-up experiments we improve these results by additional 0.7 BLEU.
VN:F [1.9.22_1171]
Rating: 5.0/5 (2 votes cast)
Attention-based NMT Models as Feature Functions in Phrase-based SMT, 5.0 out of 5 based on 2 ratings

* * *

* * *

TwitterAPIExchange Object
(
    [oauth_access_token:TwitterAPIExchange:private] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
    [oauth_access_token_secret:TwitterAPIExchange:private] => o29ji3VLVmB6jASMqY8G7QZDCrdFmoTvCDNNUlb7s
    [consumer_key:TwitterAPIExchange:private] => TdQb63pho0ak9VevwMWpEgXAE
    [consumer_secret:TwitterAPIExchange:private] => Uq4rWz7nUnH1y6ab6uQ9xMk0KLcDrmckneEMdlq6G5E0jlQCFx
    [postfields:TwitterAPIExchange:private] => 
    [getfield:TwitterAPIExchange:private] => ?cursor=-1&screen_name=hgpu&skip_status=true&include_user_entities=false
    [oauth:protected] => Array
        (
            [oauth_consumer_key] => TdQb63pho0ak9VevwMWpEgXAE
            [oauth_nonce] => 1475335912
            [oauth_signature_method] => HMAC-SHA1
            [oauth_token] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
            [oauth_timestamp] => 1475335912
            [oauth_version] => 1.0
            [cursor] => -1
            [screen_name] => hgpu
            [skip_status] => true
            [include_user_entities] => false
            [oauth_signature] => PJ1llWqo3nNR1HBT82Lv9TBTLKw=
        )

    [url] => https://api.twitter.com/1.1/users/show.json
)
Follow us on Facebook
Follow us on Twitter

HGPU group

2006 peoples are following HGPU @twitter

HGPU group © 2010-2016 hgpu.org

All rights belong to the respective authors

Contact us: