no code implementations • ALTA 2020 • Xinyuan Chao, Charbel El-Khaissi, Nicholas Kuo, Priscilla Kan John, Hanna Suominen
Speech visualisations are known to help language learners to acquire correct pronunciation and promote a better study experience.
no code implementations • NAACL (ClinicalNLP) 2022 • Sandaru Seneviratne, Elena Daskalaki, Artem Lenskiy, Hanna Suominen
Acronym disambiguation (AD) is the process of identifying the correct expansion of the acronyms in text.
1 code implementation • ACL 2022 • Andrea Papaluca, Daniel Krefl, Hanna Suominen, Artem Lenskiy
In this work we put forward to combine pretrained knowledge base graph embeddings with transformer based language models to improve performance on the sentential Relation Extraction task in natural language processing.
no code implementations • ACL 2022 • Zara Maxwelll-Smith, Michelle Kohler, Hanna Suominen
Indonesian and Malay are underrepresented in the development of natural language processing (NLP) technologies and available resources are difficult to find.
no code implementations • ALTA 2020 • Gabriela Ferraro, Hanna Suominen
In neural semantic parsing, sentences are mapped to meaning representations using encoder-decoder frameworks.
no code implementations • ALTA 2021 • Li’An Chen, Hanna Suominen
Driven by the Move-Step analytic framework theorized in the applied linguistics field, our study offers a rigorous approach to the frugal use of two human annotators to scale up auto-coding for text classification tasks.
1 code implementation • COLING 2022 • Sandaru Seneviratne, Elena Daskalaki, Artem Lenskiy, Hanna Suominen
Methods based on lexical resources are likely to miss relevant substitutes whereas relying only on contextual word embedding models fails to provide adequate information on the impact of a substitute in the entire context and the overall meaning of the input.
no code implementations • ACL 2022 • Chenchen Xu, Dongxu Li, Hongdong Li, Hanna Suominen, Ben Swift
A multi-language dictionary is a fundamental tool for language learning, allowing the learner to look up unfamiliar words.
no code implementations • 14 Apr 2024 • Sam Cantrill, David Ahmedt-Aristizabal, Lars Petersson, Hanna Suominen, Mohammad Ali Armin
We demonstrate significant performance improvements of up to 29. 6% in all tested motion scenarios in cross-dataset testing on MMPD, even in the presence of dynamic and unconstrained subject motion, emphasizing the benefits of disentangling motion through modeling the 3D facial surface for motion robust facial rPPG estimation.
no code implementations • 4 Dec 2023 • Andrea Papaluca, Daniel Krefl, Sergio Mendez Rodriguez, Artem Lensky, Hanna Suominen
In this work, we tested the Triplet Extraction (TE) capabilities of a variety of Large Language Models (LLMs) of different sizes in the Zero- and Few-Shots settings.
no code implementations • 20 Jun 2023 • Wenbo Ge, Pooia Lalbakhsh, Leigh Isai, Artem Lensky, Hanna Suominen
This study aims to compare multiple deep learning-based forecasters for the task of predicting volatility using multivariate data.
no code implementations • 29 Sep 2021 • Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Gabriela Ferraro, Christian Walder, Hanna Suominen
Neural networks usually excel in learning a single task.
no code implementations • 15 Sep 2021 • Zimin Wan, Chenchen Xu, Hanna Suominen
The Bidirectional Encoder Representations from Transformers (BERT) model has achieved the state-of-the-art performance for many natural language processing (NLP) tasks.
no code implementations • 23 Aug 2021 • Haozhan Sun, Chenchen Xu, Hanna Suominen
Therefore we recommend emphasizing other features, like textual knowledge, for researchers and practitioners as a cost-effective source for increasing the sequence labeling performance.
no code implementations • CVPR 2021 • Dongxu Li, Chenchen Xu, Kaihao Zhang, Xin Yu, Yiran Zhong, Wenqi Ren, Hanna Suominen, Hongdong Li
Video deblurring models exploit consecutive frames to remove blurs from camera shakes and object motions.
1 code implementation • 6 Mar 2021 • Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution.
no code implementations • 1 Jan 2021 • Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen
Catastrophic forgetting occurs when a neural network is trained sequentially on multiple tasks – its weights will be continuously modified and as a result, the network will lose its ability in solving a previous task.
2 code implementations • NeurIPS 2020 • Dongxu Li, Chenchen Xu, Xin Yu, Kaihao Zhang, Ben Swift, Hanna Suominen, Hongdong Li
Sign language translation (SLT) aims to interpret sign video sequences into text-based natural language sentences.
no code implementations • 23 Sep 2020 • Weiwei Hou, Hanna Suominen, Piotr Koniusz, Sabrina Caldwell, Tom Gedeon
Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information.
1 code implementation • 18 Jul 2020 • Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen
Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner.
no code implementations • WS 2020 • Zara Maxwelll-Smith, Sim{\'o}n Gonz{\'a}lez Ochoa, Ben Foley, Hanna Suominen
Multilingual corpora are difficult to compile and a classroom setting adds pedagogy to the mix of factors which make this data so rich and problematic to classify.
no code implementations • ACL 2020 • Saliha Muradoglu, Nicholas Evans, Hanna Suominen
While the {`}Chunking{'} model is under half the size of the full de-composed counterpart, the decomposition displays higher structural order.
no code implementations • 25 Sep 2019 • Nicholas I-Hsien Kuo, Mehrtash T. Harandi, Nicolas Fourrier, Gabriela Ferraro, Christian Walder, Hanna Suominen
This paper contrasts the two canonical recurrent neural networks (RNNs) of long short-term memory (LSTM) and gated recurrent unit (GRU) to propose our novel light-weight RNN of Extrapolated Input for Network Simplification (EINS).
no code implementations • ACL 2019 • Chenchen Xu, Inger Mewburn, Will J Grant, Hanna Suominen
Employers{'} low awareness and interest in attracting PhD graduates means that the term {``}PhD{''} is rarely used as a keyword in job advertisements; 80{\%} of companies looking to employ similar researchers do not specifically ask for a PhD qualification.
no code implementations • 10 Jun 2019 • Marian-Andrei Rizoiu, Tianyu Wang, Gabriela Ferraro, Hanna Suominen
This paper uses a transfer learning technique to leverage two independent datasets jointly and builds a single representation of hate speech.
Social and Information Networks Computers and Society
no code implementations • 27 Sep 2018 • Nicholas I.H. Kuo, Mehrtash T. Harandi, Hanna Suominen, Nicolas Fourrier, Christian Walder, Gabriela Ferraro
It is unclear whether the extensively applied long-short term memory (LSTM) is an optimised architecture for recurrent neural networks.
no code implementations • WS 2018 • Dzikri Fudholi, Hanna Suominen
An artificial intelligence system can take a role in these guided learning approaches as an enabler of an application for pronunciation learning with a recommender system to guide language learners through exercises and feedback system to correct their pronunciation.
no code implementations • 19 Jun 2018 • Leif W. Hanlen, Richard Nock, Hanna Suominen, Neil Bacon
Confidential text corpora exist in many forms, but do not allow arbitrary sharing.
no code implementations • SEMEVAL 2018 • Liyuan Zhou, Qiongkai Xu, Hanna Suominen, Tom Gedeon
This paper describes our approach, called EPUTION, for the open trial of the SemEval- 2018 Task 2, Multilingual Emoji Prediction.