Search Results for author: Hanna Suominen

Found 32 papers, 5 papers with code

An Automatic Vowel Space Generator for Language Learner Pronunciation Acquisition and Correction

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.

Pretrained Knowledge Base Embeddings for improved Sentential Relation Extraction

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.

Relation Relation Extraction

Scoping natural language processing in Indonesian and Malay for education applications

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.

Reading Comprehension Sentiment Analysis

Transformer Semantic Parsing

no code implementations ALTA 2020 Gabriela Ferraro, Hanna Suominen

In neural semantic parsing, sentences are mapped to meaning representations using encoder-decoder frameworks.

Decoder Question Answering +1

An Approach to the Frugal Use of Human Annotators to Scale up Auto-coding for Text Classification Tasks

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.

text-classification Text Classification

CILex: An Investigation of Context Information for Lexical Substitution Methods

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.

Sentence Sentence Embeddings +1

Automatic Gloss Dictionary for Sign Language Learners

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.

Orientation-conditioned Facial Texture Mapping for Video-based Facial Remote Photoplethysmography Estimation

no code implementations14 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.

Zero- and Few-Shots Knowledge Graph Triplet Extraction with Large Language Models

no code implementations4 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.

Sentence Triplet

Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Data

no code implementations20 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.

Enhancing Clinical Information Extraction with Transferred Contextual Embeddings

no code implementations15 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.

Transfer Learning

Analyzing the Granularity and Cost of Annotation in Clinical Sequence Labeling

no code implementations23 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.

Learning to Continually Learn Rapidly from Few and Noisy Data

1 code implementation6 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.

Continual Learning Meta-Learning

Highway-Connection Classifier Networks for Plastic yet Stable Continual Learning

no code implementations1 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.

Continual Learning

A Token-wise CNN-based Method for Sentence Compression

no code implementations23 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.

Sentence Sentence Compression

MTL2L: A Context Aware Neural Optimiser

1 code implementation18 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.

Multi-Task Learning

Applications of Natural Language Processing in Bilingual Language Teaching: An Indonesian-English Case Study

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.

speech-recognition Speech Recognition

To compress or not to compress? A Finite-State approach to Nen verbal morphology

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.

Chunking

EINS: Long Short-Term Memory with Extrapolated Input Network Simplification

no code implementations25 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).

Image Generation Imputation +2

PostAc : A Visual Interactive Search, Exploration, and Analysis Platform for PhD Intensive Job Postings

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.

Transfer Learning for Hate Speech Detection in Social Media

no code implementations10 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

DecayNet: A Study on the Cell States of Long Short Term Memories

no code implementations27 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.

The Importance of Recommender and Feedback Features in a Pronunciation Learning Aid

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.

Information Retrieval Recommendation Systems +4

EPUTION at SemEval-2018 Task 2: Emoji Prediction with User Adaption

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.

General Classification Task 2 +4

Cannot find the paper you are looking for? You can Submit a new open access paper.