Search Results for author:
Found 51 papers, 12 papers with code
Boosting Neural Machine Translation from Finnish to Northern Sámi with Rule-Based Backtranslation
Evaluating the results on an in-domain test set and a small out-of-domain set, we find that the RBMT backtranslation outperforms NMT backtranslation clearly for the out-of-domain test set, but also slightly for the in-domain data, for which the NMT backtranslation model provided clearly better BLEU scores than the RBMT.
The Helsinki submission to the AmericasNLP shared task
The University of Helsinki participated in the AmericasNLP shared task for all ten language pairs.
The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT
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 tools for creating state-of-the-art translation models from that collection.
The OPUS Resource Repository: An Open Package for Creating Parallel Corpora and Machine Translation Services
This paper presents a flexible and powerful system for creating parallel corpora and for running neural machine translation services.
Helsinki-NLP at SemEval-2022 Task 2: A Feature-Based Approach to Multilingual Idiomaticity Detection
This paper describes the University of Helsinki submission to the SemEval 2022 task on multilingual idiomaticity detection.
A Closer Look at Parameter Contributions When Training Neural Language and Translation Models
We analyze the learning dynamics of neural language and translation models using Loss Change Allocation (LCA), an indicator that enables a fine-grained analysis of parameter updates when optimizing for the loss function.
An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation
In this paper, we investigate the benefits of an explicit alignment to language labels in Transformer-based MNMT models in the zero-shot context, by jointly training one cross attention head with word alignment supervision to stress the focus on the target language label.
Creating an Aligned Russian Text Simplification Dataset from Language Learner Data
Parallel language corpora where regular texts are aligned with their simplified versions can be used in both natural language processing and theoretical linguistic studies.
LSDC - A comprehensive dataset for Low Saxon Dialect Classification
We present a new comprehensive dataset for the unstandardised West-Germanic language Low Saxon covering the last two centuries, the majority of modern dialects and various genres, which will be made openly available in connection with the final version of this paper.
Latest Development in the FoTran Project – Scaling Up Language Coverage in Neural Machine Translation Using Distributed Training with Language-Specific Components
We describe the enhancement of a multilingual NMT toolkit developed as part of the FoTran project.
MT for subtitling: User evaluation of post-editing productivity
This paper presents a user evaluation of machine translation and post-editing for TV subtitles.
Modeling Noise in Paraphrase Detection
Noisy labels in training data present a challenging issue in classification tasks, misleading a model towards incorrect decisions during training.
The MUCOW word sense disambiguation test suite at WMT 2020
This paper reports on our participation with the MUCOW test suite at the WMT 2020 news translation task.
Controlling the Imprint of Passivization and Negation in Contextualized Representations
Contextualized word representations encode rich information about syntax and semantics, alongside specificities of each context of use.
OPUS-MT – Building open translation services for the World
This paper presents OPUS-MT a project that focuses on the development of free resources and tools for machine translation.
Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning?
We furthermore provide evidence through similarity measures and investigation of parameters that this lack of positive influence is due to output separability -- which we argue is of use for machine translation but detrimental elsewhere.
A New Massive Multilingual Dataset for High-Performance Language Technologies
We present the HPLT (High Performance Language Technologies) language resources, a new massive multilingual dataset including both monolingual and bilingual corpora extracted from CommonCrawl and previously unused web crawls from the Internet Archive.
MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki
NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled.
SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
This paper presents the results of the SHROOM, a shared task focused on detecting hallucinations: outputs from natural language generation (NLG) systems that are fluent, yet inaccurate.
MaLA-500: Massive Language Adaptation of Large Language Models
Large language models (LLMs) have advanced the state of the art in natural language processing.
Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health
In the mental health domain, domain-specific language models are pretrained and released, which facilitates the early detection of mental health conditions.
Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging
This paper introduces Bayesian uncertainty modeling using Stochastic Weight Averaging-Gaussian (SWAG) in Natural Language Understanding (NLU) tasks.
Democratizing Neural Machine Translation with OPUS-MT
This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows.
When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
Our results show that the model is capable of correctly detecting whether an utterance is humorous 78% of the time and how long the audience's laughter reaction should last with a mean absolute error of 600 milliseconds.
How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets
A central question in natural language understanding (NLU) research is whether high performance demonstrates the models' strong reasoning capabilities.
Analyzing the Use of Character-Level Translation with Sparse and Noisy Datasets
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 subtitles.
NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance
We propose a new diagnostics test suite which allows to assess whether a dataset constitutes a good testbed for evaluating the models' meaning understanding capabilities.
XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection
We introduce XED, a multilingual fine-grained emotion dataset.
The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MT
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 tools for creating state-of-the-art translation models from that collection.
LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?
This paper presents the different models submitted by the LT@Helsinki team for the SemEval 2020 Shared Task 12.
Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation
Transformer-based models have brought a radical change to neural machine translation.
Multimodal Machine Translation through Visuals and Speech
Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data.
Ranked #4 on
Multimodal Machine Translation
on Multi30K
Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction
We describe the design, the evaluation setup, and the results of the 2016 WMT shared task on cross-lingual pronoun prediction.
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
In this paper we introduce a new natural language processing dataset and benchmark for predicting prosodic prominence from written text.
Ranked #1 on
Prosody Prediction
on Helsinki Prosody Corpus
The University of Helsinki submissions to the WMT19 news translation task
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 Finnish-English.
What do Language Representations Really Represent?
If the corpus is multilingual, the same model can be used to learn distributed representations of languages, such that similar languages end up with similar representations.
Multilingual NMT with a language-independent attention bridge
In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages.
The MeMAD Submission to the IWSLT 2018 Speech Translation Task
In this paper, we also describe the experiments leading up to our final systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
The MeMAD Submission to the WMT18 Multimodal Translation Task
Our experiments show that the effect of the visual features in our system is small.
Sentence Embeddings in NLI with Iterative Refinement Encoders
We can show that the sentence embeddings learned in this way can be utilized in a wide variety of transfer learning tasks, outperforming InferSent on 7 out of 10 and SkipThought on 8 out of 9 SentEval sentence embedding evaluation tasks.
Ranked #5 on
Natural Language Inference
on SciTail
Measuring Semantic Abstraction of Multilingual NMT with Paraphrase Recognition and Generation Tasks
In this paper, we investigate whether multilingual neural translation models learn stronger semantic abstractions of sentences than bilingual ones.
Emerging Language Spaces Learned From Massively Multilingual Corpora
Translations capture important information about languages that can be used as implicit supervision in learning linguistic properties and semantic representations.
The Helsinki Neural Machine Translation System
We also discuss our submissions for English--Latvian, English--Chinese and Chinese--English.
Neural Machine Translation with Extended Context
We investigate the use of extended context in attention-based neural machine translation.
Cross-Lingual Dependency Parsing for Closely Related Languages - Helsinki's Submission to VarDial 2017
This paper describes the submission from the University of Helsinki to the shared task on cross-lingual dependency parsing at VarDial 2017.
Neural machine translation for low-resource languages
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 training data to produce sensible output.
Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
We present a character-based model for joint segmentation and POS tagging for Chinese.
Continuous multilinguality with language vectors
Most existing models for multilingual natural language processing (NLP) treat language as a discrete category, and make predictions for either one language or the other.
