COW :: Seminars ::
METU Ceng On the Web
| print-view
list | browse
id : 766
type : PhD_Thesis
dateandtime : 2017-07-12 09:00:00
duration : 120 min.
Recommended duration for PhD thesis is 90 minutes, for other seminar types, it is 60 minutes. The duration specified here is used to reserve the room.
place : A101
Please check room availability from Room Scheduling page. You must use the same room name as used in the scheduling page if you want to automatically reserve the room.
departmental : yes
title : Connectionist Multi-Sequence Modelling and Applications to Multilingual Neural Machine Translation
author : ORHAN FIRAT
Supervisors field is applicable especially for a Thesis Defense
company : Computer Engineering Dept. Middle East Technical Univ.
country : Turkey
abstract : Deep (recurrent) neural networks has been shown to successfully learn complex mappings between arbitrary length input and output sequences, called sequence to sequence learning, within the effective framework of encoder-decoder networks. This thesis investigates the extensions of sequence to sequence models, to handle multiple sequences at the same time within a single parametric model, and proposes the first large scale connectionist multi-sequence modeling approach. The proposed multi-sequence modeling architecture learns to map a set of input sequences into a set of output sequences thanks to the explicit and shared parametrization of a shared medium, interlingua.

Proposed multi-sequence modeling architecture is applied to machine translation tasks, tackling the problem of multi-lingual neural machine translation (MLNMT). We explore applicability and the benefits of MLNMT, (1) on large scale machine translation tasks, between ten pairs of languages within the same model, (2) low-resource language transfer problems, where the data between any given pair is scarce, and measuring the transfer learning capabilities, (3) multi-source translation tasks where we have multi-way parallel data available, leveraging complementary information between input sequences while mapping them into a single output sequence and finally (4) Zero-resource translation task, where we don't have any available aligned data between a pair of source-target sequences.
biography :
download slides :
[ ]check this to delete slides
slidesFilename :
slidesFilename is the name of downloadable file, and will be automatically filled when you upload a new file. You may change the name also.
links :
notificationSent : final
| top
2017-10-20 09:53:32, 0.042 secs
COW by: Ahmet Sacan