Scalable Understanding of Multilingual Media

Project Information

SUMMA

Grant agreement ID: 688139

DOI 10.3030/688139

Project closed

EC signature date 10 November 2015

Start date 1 February 2016

End date 31 January 2019

Funded under

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Total cost € 7 963 951,25

EU contribution € 6 193 361,25

Coordinated by

THE UNIVERSITY OF EDINBURGH
United Kingdom

Deliverables

Other (9)

Release of storyline-level, frame-semantic and AMR parsing capabilities

This deliverable will consist of code and the associated documentation relating to the storyline-level, frame-semantic and AMR parsing capabilities.

Release of multilingual named entity recognition, linking and coreference capabilities

This deliverable will consist of code and the associated documentation relating the multilingual named entity recognition, linking and coreference capabilities

Release of multilingual relation extraction capabilities

This deliverable will consist of code and the associated documentation relating the multilingual relation extraction capabilities

Release of stream processing tools, version 1

This deliverable will consist of code and the associated documentation relating to the initial version of the stream processing tools developed in the project.

Release of initial platform

This deliverable will consist of the code and documentation of the system platform architecture.

Release of stream processing tools, version 2

This deliverable will consist of code and the associated documentation relating to the final version of the stream processing tools developed in the project.

Release of story highlight generator and event summarization tools, version 2

This deliverable will consist of code and the associated documentation relating to the story highlight generator and event summarization tools, version 2.

Release of system capabilities for extending knowledge bases to new relations and forecasting in temporal knowledge basis

This deliverable will consist of code and the associated documentation relating the system capabilities for extending knowledge bases to new relations and forecasting in temporal knowledge basis.

Release of story highlight generator and event summarization tools, version 1

This deliverable will consist of code and the associated documentation relating to the story highlight generator and event summarization tools, version 1.

Demonstrators, pilots, prototypes (2)

External Media Monitoring Demonstrator beta-version ptrototype

This deliverable will describe and demonstrate the beta version of the external media monitoring use case interface.

Internal and External Demonstrator final version

This deliverable will describe and demonstrate the final version of the external and internal media monitoring use case interfaces.

Documents, reports (24)

Final report on platform and platform documentation

This report will describe the final project architecture and capabilities.

Initial Prototype Report

This report will describe the initial SUMMA prototype's non-functional requirements, web interfaces and capabilities.

Initial progress report on automatic knowledge base creation

This report will consist of the initial scientific advances relating to multilingual named entity extraction and relation extraction. It will also describe the first version of the SUMMA automatic knowledge base creation capabilities.

Data Management Plan

This report will describe the provision of managed data environments for the technical partners to work within, which will be in line with H2020 guidelines.

Initial progress report on natural language understanding

This report will consist of the initial scientific advances relating to natural language understanding. It will also describe the first version of the SUMMA natural language understanding capabilities.

Final Prototype Report

This report will describe the final SUMMA prototype.

Initial Evaluation Report

This report will describe the results of component testing as well as testing of the external use case capabilities.

Platform architecture and API Modelling tools selection

This report will describe the platform architecture, the metadata exchange mechanisms and the common demonstrator interface.

Ethics review and recommendations

This report will describe the procedures that will be implemented to ensure that the ethical standards and guidelines of Horizon2020 will be rigorously applied.

Final report on automatic knowledge base construction

This report will consist of the final scientific advances relating to automatic knowledge base construction. It will also describe the final version of the SUMMA automatic knowledge base creation capabilities.

Final report on shallow stream processing

This report will consist of the final scientific advances made in the project relating to stream processing. It will also describe the final version of the SUMMA stream processing capabilities.

Updated Data Management Plan

This report will describe the managed data environments and the data sets collected and created.

Final progress report on natural language understanding

This report will consist of the final scientific advances relating to natural language understanding. It will also describe the final version of the SUMMA natural language understanding capabilities.

Use Case Description and Requirements

This report describes the external and the internal media monitoring use cases, and the requirements for the use cases.

Updated ethics review and recommendations

This report will describe how the the ethics and the data management plan are being implemented.

Initial Data Provision Report

This report will describe the initial provision of data dumps, data streams, and customized data and it will include the definition of the ontologies.

Dissemination and Exploitation Plan and Initial Report

This report will describe the dissemination and exploitation plan and describe progress so far.

Initial progress report on shallow stream processing

This report will consist of the initial scientific advances made in the project relating to stream processing. It will also describe the first version of the SUMMA stream processing capabilities.

Final ethics review and recommendations

This report will describe how the project complied with EU ethics guidelines. It will also describe the risks and implications of possible dual use of the capabilities developed in the project.

Final Data Provision Report

This report will describe the final provision of data dumps, data streams, and customized data.

Evaluation Plan

This report will defining the testing and validation methodology of the platform, and it will contain a plan for carrying out these tests.

Final Evaluation Report

This report will describe the final results of component testing as well as testing of the external and internal use case capabilities.

Intermediate report on platform

This report will describe the initial integration of the functionality and interfaces in the SUMMA platform.

Final Dissemination and Exploitation Report

This report will describe all the dissemination activities pursued in the project and it will also cover the future exploitation of SUMMA capabilities.

Open Research Data Pilot (1)

Final Data Management Plan

This report will describe the archiving and the sustainability of the data sets that were collected and created during SUMMA.

Websites, patent fillings, videos etc. (2)

Project web portal

A web site will be created to manage the project's online presence.

Project fact sheet

A project fact sheet will be created as part of the initial dissemination package.

Publications

Conference proceedings (76)

Extrapolation in NLP

Author(s): Jeff Mitchell, Pontus Stenetorp, Pasquale Minervini, Sebastian Riedel
Published in: Proceedings of the Workshop on Generalization in the Age of Deep Learning, 2018, Page(s) 28-33
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/W18-1005

Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness

Author(s): Ivan Sanchez, Jeff Mitchell, Sebastian Riedel
Published in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2018, Page(s) 1975-1985
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/N18-1179

WERD: Using social text spelling variants for evaluating dialectal speech recognition

Author(s): Ahmed Ali, Preslav Nakov, Peter Bell, Steve Renals
Published in: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2017, Page(s) 141-148, ISBN 978-1-5090-4788-8
Publisher: IEEE
DOI: 10.1109/ASRU.2017.8268928

An Extensible Framework for Verification of Numerical Claims

Author(s): James Thorne, Andreas Vlachos
Published in: Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017, Page(s) 37-40
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/e17-3010

Speech recognition challenge in the wild: Arabic MGB-3

Author(s): Ahmed Ali, Stephan Vogel, Steve Renals
Published in: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2017, Page(s) 316-322, ISBN 978-1-5090-4788-8
Publisher: IEEE
DOI: 10.1109/ASRU.2017.8268952

Fake news stance detection using stacked ensemble of classifiers

Author(s): James Thorne, Mingjie Chen, Giorgos Myrianthous, Jiashu Pu, Xiaoxuan Wang, Andreas Vlachos
Published in: Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism, 2017, Page(s) 80-83
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/w17-4214

Deep architectures for Neural Machine Translation

Author(s): Antonio Valerio Miceli Barone, Jindřich Helcl, Rico Sennrich, Barry Haddow, Alexandra Birch
Published in: Proceedings of the Second Conference on Machine Translation, 2017, Page(s) 99-107
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/W17-4710

Word Error Rate Estimation for Speech Recognition: e-WER

Author(s): A Ali and S Renals
Published in: ACL, 2018
Publisher: ACL

Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation

Author(s): Hardy, Hardy and Vlachos, Andreas
Published in: EMNLP, 2018
Publisher: ACL

Factorised Representations for Neural Network Adaptation to Diverse Acoustic Environments

Author(s): Joachim Fainberg, Steve Renals, Peter Bell
Published in: Interspeech 2017, 2017, Page(s) 749-753
Publisher: ISCA
DOI: 10.21437/interspeech.2017-1365

Dynamic Evaluation of Neural Sequence Models

Author(s): Krause, Ben and Kahembwe, Emmanuel and Murray, Iain and Renals, Steve
Published in: ICML, 2018
Publisher: ICML

Evaluating Discourse Phenomena in Neural Machine Translation

Author(s): Rachel Bawden, Rico Sennrich, Alexandra Birch, Barry Haddow
Published in: NAACL, 2018
Publisher: ACL

Learning to Adapt: A Meta-learning Approach for Speaker Adaptation

Author(s): Ondřej Klejch, Joachim Fainberg, Peter Bell
Published in: Interspeech 2018, 2018, Page(s) 867-871
Publisher: ISCA
DOI: 10.21437/interspeech.2018-1244

STACKED NEURAL NETWORKS WITH PARAMETER SHARING FOR MULTILINGUAL LANGUAGE MODELING

Author(s): Khonglah, Banriskhem K and Madikeri, Srikanth and Rekabsaz, Navid and Pappas, Nikolaos and Motlicek, Petr and Bourlard, Herve
Published in: IEEE ICASSP, 2019
Publisher: IEEE

SUMMA: Scalable Understanding of Multilingual Media

Author(s): Ulrich Germann, Alexandra Birch, Peggy van der Kreeft, Guntis Barzdins, Steve Renals
Published in: KDD, 2018
Publisher: ACM

Jointly Learning to Embed and Predict with Multiple Languages

Author(s): Ferreira, Daniel, Martins, André, and Almeida, Mariana S. C.
Published in: ACL, 2016
Publisher: ACL

The SUMMA platform: A scalable infrastructure for multi-lingual multi-media monitoring

Author(s): Ulrich Germann, Renars Liepins, Guntis Barzdins, Didzis Gosko, Sebastiao Miranda, David Nogueira
Published in: ACL, 2018
Publisher: ACL

Cross-lingual Abstract Meaning Representation Parsing

Author(s): Marco Damonte, Shay B. Cohen
Published in: NAACL, 2018
Publisher: ACL

Regularization Techniques for Fine-tuning in Neural Machine Translation

Author(s): AVM Barone, B Haddow, U Germann, and R Sennrich
Published in: EMNLP, 2017
Publisher: ACL

The University of Edinburgh’s systems submission to the MT task at IWSLT},

Author(s): Junczys-Dowmunt, Marcin and Birch, Alexandra
Published in: IWSLT, 2016
Publisher: IWSLT

The SUMMA Platform: Scalable Understanding of Multilingual Media

Author(s): Ulrich Germann, Peggy van der Kreeft, Guntis Barzdins, Alexandra Birch
Published in: EAMT, 2018
Publisher: EAMT

Marian: Fast Neural Machine Translation in C++

Author(s): Junczys-Dowmunt, Marcin and Grundkiewicz, Roman and Dwojak, Tomasz and Hoang, Hieu and Heafield, Kenneth and Neckermann, Tom and Seide, Frank and Germann, Ulrich and Aji, Alham Fikri and Bogoychev, Nikolay and others
Published in: ACL, 2018
Publisher: ACL

The University of Edinburgh’s Submissions to the WMT18 News Translation Task

Author(s): Haddow, Barry and Bogoychev, Nikolay and Emelin, Denis and Germann, Ulrich and Grundkiewicz, Roman and Heafield, Kenneth and Barone, Antonio Valerio Miceli and Sennrich, Rico
Published in: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, 2018
Publisher: ACL

Fast Language Adaptation Using Phonological Information

Author(s): Sibo Tong, Philip N. Garner, Hervé Bourlard
Published in: Interspeech 2018, 2018, Page(s) 2459-2463
Publisher: ISCA
DOI: 10.21437/interspeech.2018-1990

Hierarchical Recurrent Neural Network for Story Segmentation

Author(s): Emiru Tsunoo, Peter Bell, Steve Renals
Published in: Interspeech 2017, 2017, Page(s) 2919-2923
Publisher: ISCA
DOI: 10.21437/interspeech.2017-392

Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features

Author(s): Emiru Tsunoo, Ondrej Klejch, Peter Bell, Steve Renals
Published in: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2017, Page(s) 525-532, ISBN 978-1-5090-4788-8
Publisher: IEEE
DOI: 10.1109/asru.2017.8268981

Discourse Representation Structure Parsing

Author(s): Liu, Jiangming and Cohen, Shay B and Lapata, Mirella
Published in: ACL, 2018
Publisher: ACL

CONTEXT-AWARE ATTENTION MECHANISM FOR SPEECH EMOTION RECOGNITION

Author(s): G Ramet, PN Garner, M Baeriswyl, A Lazaridis
Published in: IEEE SLT, 2018
Publisher: IEEE

Multilingual Clustering of Streaming News

Author(s): Sebastião Miranda, Artūrs Znotiņš, Shay B. Cohen, Guntis Barzdins
Published in: EMNLP, 2018
Publisher: ACL

Ranking Sentences for Extractive Summarization with Reinforcement Learning

Author(s): Shashi Narayan, Shay B. Cohen, Mirella Lapata
Published in: NAACL-HLT, 2018
Publisher: ACL

Contextual Pattern Embeddings for One-shot Relation Extraction

Author(s): Obamuyide, Abiola and Vlachos, Andreas
Published in: NIPS Workshop on AKBC, 2017
Publisher: NIPS

Beyond Weight Tying: Learning Joint Input-Output Embeddings for Neural Machine Translation

Author(s): Pappas, Nikolaos and Werlen, Lesly Miculicich and Henderson, James
Published in: WMT, 2018
Publisher: ACL

SUMMA at TAC Knowledge Base Population Task 2016

Author(s): Paikens, Peteris and Barzdins, Guntis and Mendes, Afonso and Ferreira, Daniel C and Broscheit, Samuel and Almeida, Mariana SC and Miranda, Sebasti{\~a}o and Nogueira, David and Balage, Pedro and Martins, Andre FT
Published in: TAC, 2017
Publisher: NIST

Zero-shot Relation Classification as Textual Entailment

Author(s): Obamuyide, Abiola and Vlachos, Andreas
Published in: ACL FEVER Workshop, 2018
Publisher: ACL

The University of Edinburgh's Neural MT Systems for WMT17

Author(s): Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip Williams
Published in: Proceedings of the Second Conference on Machine Translation, 2017, Page(s) 389-399
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/W17-4739

Document-Level Neural Machine Translation with Hierarchical Attention Networks

Author(s): Miculicich, Lesly; Ram, Dhananjay; Pappas, Nikolaos; Henderson, James
Published in: EMNLP, 2018
Publisher: ACL
DOI: 10.5281/zenodo.2276024

Self-Attentive Residual Decoder for Neural Machine Translation

Author(s): Werlen, Lesly Miculicich; Pappas, Nikolaos; Ram, Dhananjay; Popescu-Belis, Andrei
Published in: NAACL-HLT, 2018
Publisher: ACL
DOI: 10.5281/zenodo.2276145

Canonical Correlation Inference for Mapping Abstract Scenes to Text

Author(s): Papasarantopoulos, Nikolaos; Jiang, Helen; Cohen, Shay
Published in: AAAI, Issue 1, 2018
Publisher: AAAI

Local String Transduction as Sequence Labeling

Author(s): Ribeiro, Joana; Narayan, Shashi; Cohen, Shay; Carreras, Xavier
Published in: Ribeiro , J , Narayan , S , Cohen , S & Carreras , X 2018 , Local String Transduction as Sequence Labeling . in 27th International Conference on Computational Linguistics (COLING 2018) . Santa Fe, New-Mexico, USA , pp. 1360-1371 , 27th International Conference on Computational Linguistics , Sante Fe , United States , 20/08/18 ., 2018
Publisher: ACL
DOI: 10.5281/zenodo.2400050

UCL Machine Reading Group: Four Factor Framework For Fact Finding,

Author(s): Takuma Yoneda; Jeff Mitchell; Johannes Welbl; Pontus Stenetorp; Sebastian Riedel
Published in: FEVER Workshop, 2018
Publisher: ACL
DOI: 10.5281/zenodo.2165211

Unsupervised Sentence Simplification Using Deep Semantics

Author(s): Shashi Narayan; Claire Gardent
Published in: Proceedings of The 9th International Natural Language Generation conference, 2016, Page(s) 111-120
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.827390

Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features

Author(s): Ondrej Klejch, Peter Bell, Steve Renals
Published in: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Page(s) 5700-5704, ISBN 978-1-5090-4117-6
Publisher: IEEE
DOI: 10.1109/ICASSP.2017.7953248

Semi-Supervised Learning of Sequence Models with the Method of Moments

Author(s): Zita Marinho; Andre Martins; Cohen, Shay B.; Smith, Noah A.
Published in: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016, Page(s) 287-296
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.827295

Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities

Author(s): Luong, Ngoc Quang; Popescu-Belis, Andrei; Rios, Annette; Tuggener, Don
Published in: 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017, Page(s) 631-636
Publisher: ACL
DOI: 10.5167/uzh-136594

Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing

Author(s): Shashi Narayan; Siva Reddy; Cohen, Shay B.
Published in: Proceedings of The 9th International Natural Language Generation conference, 2016, Page(s) 153-162
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.827303

Unsupervised Adaptation of Recurrent Neural Network Language Models

Author(s): Siva Reddy Gangireddy, Pawel Swietojanski, Peter Bell, Steve Renals
Published in: Interspeech 2016, 2016, Page(s) 2333-2337
Publisher: ISCA
DOI: 10.21437/Interspeech.2016-1342

An Incremental Parser for Abstract Meaning Representation

Author(s): Marco Damonte; Cohen, Shay B.; Giorgio Satta
Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, 2017, Page(s) 536-546
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.827291

Bilingual Document Alignment with Latent Semantic Indexing

Author(s): Ulrich Germann
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 692-696
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/w16-2368

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

Author(s): Junczys-Dowmunt, Marcin; Dwojak, Tomasz; Sennrich, Rico
Published in: Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers, 2016, Page(s) 316-322
Publisher: Association for Computational Linguistics

Nematus: a Toolkit for Neural Machine Translation

Author(s): Sennrich, Rico; Firat, Orhan; Cho, Kyunghyun; Birch-Mayne, Alexandra; Haddow, Barry; Hitschler, Julian; Junczys-Dowmunt, Marcin; Läubli, Samuel; Miceli Barone, Antonio; Mokry, Jozef; Nadejde, Maria
Published in: Proceedings of the EACL 2017 (Software Demonstrations), 2017, Page(s) 65-68
Publisher: Association for Computational Linguistics

An Extensible Framework for Verification of Numerical Claims

Author(s): THORNE, J.; Vlachos, A.
Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (Software Demonstrations), 2017
Publisher: Association for Computational Linguistics

Optimizing Spectral Learning for Parsing

Author(s): Shashi Narayan; Cohen, Shay B.
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016, Page(s) 1546-1556
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.827387

Automatic Dialect Detection in Arabic Broadcast Speech

Author(s): Ahmed Ali, Najim Dehak, Patrick Cardinal, Sameer Khurana, Sree Harsha Yella, James Glass, Peter Bell, Steve Renals
Published in: Interspeech 2016, 2016, Page(s) 2934-2938
Publisher: ISCA
DOI: 10.21437/Interspeech.2016-1297

The SUMMA Platform Prototype

Author(s): Liepins, Renars; Germann, Ulrich; Barzdins, Guntis; Birch, Alexandra; Renals, Steve; Weber, Susanne; van der Kreeft, Peggy; Bourlard, Herve; Prieto, Joao; Klejch, Ondrej; Bell, Peter; Lazaridis, Alexandros; Mendes, Alfonso; Riedel, Sebastian; Mariana S. C. Almeida; Balage, Pedro; Cohen, Shay B.; Dwojak, Tomasz; Garner, Philip N.; Giefer, Andreas; Junczys-Dowmunt, Marcin; Imran, Hina; Nogueira, Dav
Published in: Proceedings of the EACL 2017 (Software Demonstrations), 2017, Page(s) 116-119
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.834347

Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

Author(s): Junczys-Dowmunt, Marcin; Dwojak, Tomasz; Hoang, Hieu
Published in: Proceedings of the International Workshop on Spoken Language Translation 2016, 2016
Publisher: IWSLT

How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs

Author(s): Sennrich, Rico
Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, Issue 14, 2017, Page(s) 376-382
Publisher: Association for Computational Linguistics (ACL)

Punctuated transcription of multi-genre broadcasts using acoustic and lexical approaches

Author(s): Ondrej Klejch, Peter Bell, Steve Renals
Published in: 2016 IEEE Spoken Language Technology Workshop (SLT), 2016, Page(s) 433-440, ISBN 978-1-5090-4903-5
Publisher: IEEE
DOI: 10.1109/SLT.2016.7846300

The MGB-2 challenge: Arabic multi-dialect broadcast media recognition

Author(s): Ahmed Ali, Peter Bell, James Glass, Yacine Messaoui, Hamdy Mubarak, Steve Renals, Yifan Zhang
Published in: 2016 IEEE Spoken Language Technology Workshop (SLT), 2016, Page(s) 279-284, ISBN 978-1-5090-4903-5
Publisher: IEEE
DOI: 10.1109/SLT.2016.7846277

RIGOTRIO at SemEval-2017 Task 9: Combining Machine Learning and Grammar Engineering for AMR Parsing and Generation

Author(s): Gruzitis, Normunds; Gosko, Didzis; Barzdins, Guntis
Published in: ACL SemEval, 2017
Publisher: ACL
DOI: 10.5281/zenodo.827306

Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project

Author(s): Barzdins, Guntis; Renals, Steve; Gosko, Didzis
Published in: LREC, 2016
Publisher: ELRA

Latent-Variable PCFGs: Background and Applications

Author(s): Shay Cohen
Published in: Proceedings of the 15th Meeting on the Mathematics of Language, 2017
Publisher: ACL
DOI: 10.5281/zenodo.827287

Sense-Aware Statistical Machine Translation using Adaptive Context-Dependent Clustering

Author(s): Pu, Xiao; Pappas, Nikolaos; Popescu-Belis, Andrei
Published in: Proceedings of Second Conference on Machine Translation (WMT17), 2017
Publisher: ACL
DOI: 10.5281/zenodo.834305

SUMMA at TAC Knowledge Base Population Task 2016

Author(s): Peteris Paikens; Guntis Barzdins; Afonso Mendes; Daniel Ferreira; Samuel Broscheit; Mariana S. C. Almeida; Sebastiao Miranda; David Nogueira; Pedro Balage; Martins, Andre F. T.
Published in: Proceedings of the Text Analysis Conference (TAC), 2017
Publisher: NIST
DOI: 10.5281/zenodo.827317

Split and Rephrase

Author(s): Shashi Narayan; Claire Gardent; Cohen, Shay B.; Anastasia Shimorina
Published in: EMNLP, 2017
Publisher: ACL
DOI: 10.5281/zenodo.833478

Creating Training Corpora for Micro-Planners

Author(s): Claire Gardent; Anastasia Shimorina; Shashi Narayan; Laura Perez-Beltrachini
Published in: Proc ACL, 2017
Publisher: ACL
DOI: 10.5281/zenodo.827393

Human versus Machine Attention in Document Classification: A Dataset with Crowdsourced Annotations

Author(s): Pappas, Nikolaos; Popescu-Belis, Andrei
Published in: EMNLP, 2016
Publisher: ACL
DOI: 10.5281/zenodo.834299

An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation

Author(s): Tong, Sibo; Garner, Philip N.; Bourlard, Hervé
Published in: Interspeech, 2017
Publisher: ISCA

Multilingual Hierarchical Attention Networks for Document Classification

Author(s): Pappas, Nikolaos; Popescu-Belis, Andrei
Published in: 8th International Joint Conference on Natural Language Processing (IJCNLP), 2017
Publisher: ACLCLP
DOI: 10.5281/zenodo.834306

Investigating Cross-lingual Multi-level Adaptive Networks: The Importance of the Correlation of Source and Target Languages

Author(s): Lazaridis, Alexandros; Himawan, Ivan; Motlicek, Petr; Mporas, Iosif; Garner, Philip N.
Published in: IWSLT 2016, 2016
Publisher: IWSLT

RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy

Author(s): Barzdins, Guntis; Gosko, Didzis
Published in: ACL SemEval 2016, 2016
Publisher: ACL

Improving Pronoun Translation by Modeling Coreference Uncertainty

Author(s): Luong, Ngoc-Quang; Popescu-Belis, Andrei
Published in: Proceedings of the First Conference on Machine Translation (WMT16), 2016
Publisher: ACL

Predicting Target Language CCG Supertags Improves Neural Machine Translation

Author(s): Nadejde, Maria; Reddy, Siva; Sennrich, Rico; Dwojak, Tomasz; Junczys-Dowmunt, Marcin; Koehn, Philipp; Birch, Alexandra
Published in: Second Conference on Machine Translation (WMT17), 2017
Publisher: ACL

Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues

Author(s): Pu, Xiao; Mascarell, Laura; Popescu-Belis, Andrei
Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2017
Publisher: ACL

Timeline extraction using distant supervision and joint inference

Author(s): Savelie Cornegruta, Andreas Vlachos
Published in: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016, Page(s) 1936-1942
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/d16-1200

Using Coreference Links to Improve Spanish-to-English Machine Translation

Author(s): Miculicich Werlen, Lesly Sadiht; Popescu-Belis, Andrei
Published in: Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), 2017
Publisher: ACL

Validation of an Automatic Metric for the Accuracy of Pronoun Translation (APT)

Author(s): Miculicich Werlen, Lesly Sadiht; Popescu-Belis, Andrei
Published in: Proceedings of the Third Workshop on Discourse in Machine Translation (DiscoMT), 2017
Publisher: ACL

Peer reviewed articles (9)

Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation

Author(s): Pu, Xiao; Pappas, Nikolaos; Henderson, James; Popescu-Belis, Andrei
Published in: Transactions of the Association for Computational Linguistics, Issue 6, 2018, ISSN 2307-387X
Publisher: E-ISSN: 2307-387X
DOI: 10.5281/zenodo.2275709

Cross-lingual adaptation of a CTC-based multilingual acoustic model

Author(s): Sibo Tong, Philip N. Garner, Hervé Bourlard
Published in: Speech Communication, Issue 104, 2018, Page(s) 39-46, ISSN 0167-6393
Publisher: Elsevier BV
DOI: 10.1016/j.specom.2018.09.001

Small-Footprint Highway Deep Neural Networks for Speech Recognition

Author(s): Liang Lu, Steve Renals
Published in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Issue 25/7, 2017, Page(s) 1502-1511, ISSN 2329-9290
Publisher: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2017.2698723

GILE: A Generalized Input-Label Embedding for Text Classification

Author(s): Pappas, Nikolaos and Henderson, James
Published in: TACL, 2019, ISSN 2307-387X
Publisher: ACL

Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

Author(s): Pawel Swietojanski, Jinyu Li, Steve Renals
Published in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Issue 24/8, 2016, Page(s) 1450-1463, ISSN 2329-9290
Publisher: IEEE Advancing Technology for Humanity
DOI: 10.1109/TASLP.2016.2560534

Differentiable Pooling for Unsupervised Acoustic Model Adaptation

Author(s): Pawel Swietojanski, Steve Renals
Published in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Issue 24/10, 2016, Page(s) 1773-1784, ISSN 2329-9290
Publisher: IEEE Advancing Technology for Humanity
DOI: 10.1109/TASLP.2016.2584700

Multitask Learning of Context-Dependent Targets in Deep Neural Network Acoustic Models

Author(s): Peter Bell, Pawel Swietojanski, Steve Renals
Published in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Issue 25/2, 2017, Page(s) 238-247, ISSN 2329-9290
Publisher: IEEE Advancing Technology for Humanity
DOI: 10.1109/TASLP.2016.2630305

Encoding Prior Knowledge with Eigenword Embeddings

Author(s): Dominique Osborne; Shashi Narayan; Cohen, Shay B.
Published in: Transactions of the Association for Computational Linguistics, Issue 4, 2016, Page(s) 417-430, ISSN 2307-387X
Publisher: ACL
DOI: 10.5281/zenodo.827299

Explicit Document Modeling through Weighted Multiple-Instance Learning

Author(s): Pappas, Nikolaos; Popescu-Belis, Andrei
Published in: Journal of AI Research, Issue 58, 2017, Page(s) 591-626, ISSN 1076-9757
Publisher: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.5240

Other (4)

The Role of CNL and AMR in Scalable Abstractive Summarization for Multilingual Media Monitoring

Author(s): Normunds Gruzitis, Guntis Barzdins
Published in: 2016
Publisher: arXiv

Reduce, Reuse, Recycle: New uses for old QA resources

Author(s): Jeff Mitchell, Sebastian Riedel
Published in: 2018
Publisher: arXiv

FEVER: a large-scale dataset for Fact Extraction and VERification

Author(s): Thorne, James; Vlachos, Andreas; Christodoulopoulos, Christos; Mittal, Arpit
Published in: arXiv.org e-Print Archive, Issue 9, 2018
Publisher: arXiv

Convolutional 2D Knowledge Graph Embeddings

Author(s): Dettmers, Tim; Minervini, Pasquale; Stenetorp, Pontus; Riedel, Sebastian
Published in: arXiv:1707.01476, 2017
Publisher: Arxiv
DOI: 10.5281/zenodo.833287