Daniel Beck

Accelerated query processing via similarity score prediction

M Petri, A Moffat, J Mackenzie, J Shane Culpepper, D Beck

Conference Proceedings  |  2019  |  Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

Publication rights licensed to ACM. Processing top-k bag-of-words queries is critical to many information retrieval applications, ..

A Unified Neural Architecture for Instrumental Audio Tasks

S Spratley, D Beck, T Cohn

Conference Proceedings  |  2019  |  ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

© 2019 IEEE. Within Music Information Retrieval (MIR), prominent tasks - including pitch-tracking, source-separation, super-resolu..

Neural Speech Translation using Lattice Transformations and Graph Networks

Daniel Beck, Trevor Cohn, Gholamreza Haffari

Conference Proceedings  |  2019  |  Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)

Speech translation systems usually follow a pipeline approach, using word lattices as an intermediate representation. However, pre..

Modelling Uncertainty in Collaborative Document Quality Assessment

Aili Shen, Daniel Beck, Bahar Salehi, Jianzhong Qi, Timothy Baldwin

Conference Proceedings  |  2019  |  Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)

In the context of document quality assessment, previous work has mainly focused on predicting the quality of a document relative t..

Graph-to-Sequence Learning using Gated Graph Neural Networks

Trevor Cohn, Gholamreza Haffari, Daniel Beck

Conference Proceedings  |  2018  |  ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

Gaussian processes for text regression

D Beck

Thesis / Dissertation  |  2018

Modelling Representation Noise in Emotion Analysis using Gaussian Processes

Daniel Beck

Conference Proceedings  |  2017  |  Proceedings of IJCNLP

Emotion Analysis is the task of modelling la-tent emotions present in natural language. La-belled datasets for this task are scarc..

Learning Kernels over Strings using Gaussian Processes

Daniel Beck, Trevor Cohn

Conference Proceedings  |  2017  |  Proceedings of IJCNLP

Non-contiguous word sequences are widely known to be important in mod-elling natural language. However they are not explicitly enc..

Speed-constrained tuning for statistical machine translation using Bayesian optimization

D Beck, A De Gispert, G Iglesias, A Waite, B Byrne

Conference Proceedings  |  2016  |  2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

SHEF-MIME: Word-level Quality Estimation Using Imitation Learning

Daniel Beck, Andreas Vlachos, Gustavo H Paetzold, Lucia Specia

Conference Proceedings  |  2016  |  Proceedings of WMT16

Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization

Daniel Beck, Adrià de Gispert, Gonzalo Iglesias, Aurelien Waite, Bill Byrne

Conference Proceedings  |  2016  |  Proceedings of NAACL

We address the problem of automatically finding the parameters of a statistical machine translation system that maximize BLEU scor..

Exploring Prediction Uncertainty in Machine Translation Quality Estimation

Daniel Beck, Lucia Specia, Trevor Cohn

Conference Proceedings  |  2016  |  CoNLL 2016 - 20th SIGNLL Conference on Computational Natural Language Learning, Proceedings

Word embeddings and discourse information for Machine Translation Quality Estimation

Carolina Scarton, Daniel Beck, Kashif Shah, Karin Sim Smith, Lucia Specia

Conference Proceedings  |  2016  |  Proceedings of WMT16

USFD at SemEval-2016 task 1: Putting different state-of-the-arts into a box

A Aker, F Blain, A Duque, M Fomicheva, J Seva, K Shah, D Beck

Conference Proceedings  |  2016  |  Proceedings of SemEval

In this paper we describe our participa-tion in the STS Core subtask which is the determination of the monolingual seman-tic simil..

Learning Structural Kernels for Natural Language Processing

Daniel Beck, Trevor Cohn, Christian Hardmeier, Lucia Specia

Journal article  |  2015  |  Transactions of the Association for Computational Linguistics

SHEF-NN : Translation Quality Estimation with Neural Networks

Kashif Shah, Varvara Logacheva, Gustavo Henrique Paetzold, Frederic Blain, Daniel Beck, Fethi Bougares, Lucia Specia

Conference Proceedings  |  2015  |  Proceedings of WMT

SHEF-Lite 2.0 : Sparse Multi-task Gaussian Processes for Translation Quality Estimation

Daniel Beck, Kashif Shah, Lucia Specia

Conference Proceedings  |  2014  |  Proceedings of WMT14

Joint Emotion Analysis via Multi-task Gaussian Processes

Daniel Beck, Trevor Cohn, Lucia Specia

Conference Proceedings  |  2014  |  EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Bayesian Kernel Methods for Natural Language Processing

Daniel Beck

Conference Proceedings  |  2014  |  Proceedings of ACL Student Research Workshop

Kernel methods are heavily used in Natural Language Processing (NLP). Frequentist approaches like Support Vector Machines are the ..

Tree-based Statistical Machine Translation: Experiments with the English and Brazilian Portuguese Pair

Daniel Beck, Helena Caseli

Journal article  |  2013  |  Learning and Nonlinear Models

SHEF-Lite : When Less is More for Translation Quality Estimation

Daniel Beck, Kashif Shah, Trevor Cohn, Lucia Specia

Conference Proceedings  |  2013  |  Proceedings of the Eighth Workshop on Statistical Machine Translation

Reducing Annotation Effort for Quality Estimation via Active Learning

Daniel Beck, Lucia Specia, Trevor Cohn

Conference Proceedings  |  2013  |  Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics

Bayesian induction of syntactic language models for Brazilian Portuguese

DE Beck, H De Medeiros Caseli

Conference Proceedings  |  2012  |  Proceedings of PROPOR

Portuguese-English Statistical Machine Translation using Tree Transducers

Daniel Beck, Helena Caseli

Conference Proceedings  |  2012  |  Proceedings of ENIA

Tradução Automática Estatística baseada em Sintaxe e Linguagens de Árvores

D Beck

Thesis / Dissertation  |  2012

Syntax-based Statistical Machine Translation using Tree Automata and Tree Transducers

DE Beck

Conference Proceedings  |  2011  |  Proceedings of ACL Student Session