69 citations · 219 across the 23 of their papers we have counts for
26 papers
Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health
Shaoxiong Ji, Tianlin Zhang, Kailai Yang +3
Pretrained language models have been used in various natural language processing applications. In the mental health domain, domain-specific language models are pretrained and relea…
Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging
Aarne Talman, Hande Celikkanat, Sami Virpioja +2
This paper introduces Bayesian uncertainty modeling using Stochastic Weight Averaging-Gaussian (SWAG) in Natural Language Understanding (NLU) tasks. We apply the approach to standa…
When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
Khalid Alnajjar, Mika Hämäläinen, Jörg Tiedemann +2
Prerecorded laughter accompanying dialog in comedy TV shows encourages the audience to laugh by clearly marking humorous moments in the show. We present an approach for automatical…
How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets
Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis +1
A central question in natural language understanding (NLU) research is whether high performance demonstrates the models' strong reasoning capabilities. We present an extensive seri…
Analyzing the Use of Character-Level Translation with Sparse and Noisy Datasets
Jörg Tiedemann, Preslav Nakov
This paper provides an analysis of character-level machine translation models used in pivot-based translation when applied to sparse and noisy datasets, such as crowdsourced movie…
NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance
Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis +1
Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences rema…
XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection
Emily Öhman, Marc Pàmies, Kaisla Kajava +1
We introduce XED, a multilingual fine-grained emotion dataset. The dataset consists of human-annotated Finnish (25k) and English sentences (30k), as well as projected annotations f…
The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MT
Jörg Tiedemann
This paper describes the development of a new benchmark for machine translation that provides training and test data for thousands of language pairs covering over 500 languages and…
LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?
Marc Pàmies, Emily Öhman, Kaisla Kajava +1
This paper presents the different models submitted by the LT@Helsinki team for the SemEval 2020 Shared Task 12. Our team participated in sub-tasks A and C; titled offensive languag…
Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation
Alessandro Raganato, Yves Scherrer, Jörg Tiedemann
Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism,…
Multimodal Machine Translation through Visuals and Speech
Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos +4
Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative view…
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
Aarne Talman, Antti Suni, Hande Celikkanat +3
In this paper we introduce a new natural language processing dataset and benchmark for predicting prosodic prominence from written text. To our knowledge this will be the largest p…
The University of Helsinki submissions to the WMT19 news translation task
Aarne Talman, Umut Sulubacak, Raúl Vázquez +5
In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation in three language pairs: English-German, English-Finnish and Finnis…
What do Language Representations Really Represent?
Johannes Bjerva, Robert Östling, Maria Han Veiga +2
A neural language model trained on a text corpus can be used to induce distributed representations of words, such that similar words end up with similar representations. If the cor…
Multilingual NMT with a language-independent attention bridge
Raúl Vázquez, Alessandro Raganato, Jörg Tiedemann +1
In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em atte…
The MeMAD Submission to the IWSLT 2018 Speech Translation Task
Umut Sulubacak, Jörg Tiedemann, Aku Rouhe +2
This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end…
The MeMAD Submission to the WMT18 Multimodal Translation Task
Stig-Arne Grönroos, Benoit Huet, Mikko Kurimo +8
This paper describes the MeMAD project entry to the WMT Multimodal Machine Translation Shared Task. We propose adapting the Transformer neural machine translation (NMT) architectur…
Sentence Embeddings in NLI with Iterative Refinement Encoders
Aarne Talman, Anssi Yli-Jyrä, Jörg Tiedemann
Sentence-level representations are necessary for various NLP tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be tr…
Weak invariants, temporally-local equilibria, and isoenergetic processes described by the Lindblad equation
Congjie Ou, Sumiyoshi Abe
The concept of weak invariants is examined in the thermodynamic context. Discussions are made about the temporally-local equilibrium states, corrections to them, and isoenergetic p…
Emerging Language Spaces Learned From Massively Multilingual Corpora
Jörg Tiedemann
Translations capture important information about languages that can be used as implicit supervision in learning linguistic properties and semantic representations. In an informatio…
Neural Machine Translation with Extended Context
Jörg Tiedemann, Yves Scherrer
We investigate the use of extended context in attention-based neural machine translation. We base our experiments on translated movie subtitles and discuss the effect of increasing…
The Helsinki Neural Machine Translation System
Robert Östling, Yves Scherrer, Jörg Tiedemann +2
We introduce the Helsinki Neural Machine Translation system (HNMT) and how it is applied in the news translation task at WMT 2017, where it ranked first in both the human and autom…
Neural machine translation for low-resource languages
Robert Östling, Jörg Tiedemann
Neural machine translation (NMT) approaches have improved the state of the art in many machine translation settings over the last couple of years, but they require large amounts of…
Cross-Lingual Dependency Parsing for Closely Related Languages - Helsinki's Submission to VarDial 2017
Jörg Tiedemann
This paper describes the submission from the University of Helsinki to the shared task on cross-lingual dependency parsing at VarDial 2017. We present work on annotation projection…