Edinburgh Research Explorer

Character-level neural translation for multilingual media monitoring in the SUMMA project

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://www.lrec-conf.org/proceedings/lrec2016/pdf/4_Paper.pdf
Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016
PublisherEuropean Language Resources Association (ELRA)
Pages1789-1793
Number of pages5
ISBN (Electronic)9782951740891
Publication statusPublished - 2016
Event10th International Conference on Language Resources and Evaluation, LREC 2016 - Portoroz, Slovenia
Duration: 23 May 201628 May 2016

Conference

Conference10th International Conference on Language Resources and Evaluation, LREC 2016
CountrySlovenia
CityPortoroz
Period23/05/1628/05/16

Abstract

The paper steps outside the comfort-zone of the traditional NLP tasks like automatic speech recognition (ASR) and machine translation (MT) to addresses two novel problems arising in the automated multilingual news monitoring: segmentation of the TV and radio program ASR transcripts into individual stories, and clustering of the individual stories coming from various sources and languages into storylines. Storyline clustering of stories covering the same events is an essential task for inquisitorial media monitoring. We address the setwo problems jointly by engaging the low-dimensional semantic representation capabilities of the sequence to sequence neural translation models. To enable joint multi-task learning for multilingual neural translation of morphologically rich languages we replace the attention mechanism with the sliding-window mechanism and operate the sequence to sequence neural translation model on the character-level rather than on the word-level. The story segmentation and storyline clustering problem is tackled by examining the low-dimensional vectors produced as a side-product of the neural translation process. The results of this paper describe a novel approach to the automatic story segmentation and storyline clustering problem.

    Research areas

  • Clustering, Multilingual, Translation

Event

10th International Conference on Language Resources and Evaluation, LREC 2016

23/05/1628/05/16

Portoroz, Slovenia

Event: Conference

ID: 51288417