Mikko Kurimo


2020

pdf bib
Graph-based Syntactic Word Embeddings
Ragheb Al-Ghezi | Mikko Kurimo
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)

We propose a simple and efficient framework to learn syntactic embeddings based on information derived from constituency parse trees. Using biased random walk methods, our embeddings not only encode syntactic information about words, but they also capture contextual information. We also propose a method to train the embeddings on multiple constituency parse trees to ensure the encoding of global syntactic representation. Quantitative evaluation of the embeddings show a competitive performance on POS tagging task when compared to other types of embeddings, and qualitative evaluation reveals interesting facts about the syntactic typology learned by these embeddings.

pdf bib
Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models
Mittul Singh | Peter Smit | Sami Virpioja | Mikko Kurimo
Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)

Character-based Neural Network Language Models (NNLM) have the advantage of smaller vocabulary and thus faster training times in comparison to NNLMs based on multi-character units. However, in low-resource scenarios, both the character and multi-character NNLMs suffer from data sparsity. In such scenarios, cross-lingual transfer has improved multi-character NNLM performance by allowing information transfer from a source to the target language. In the same vein, we propose to use cross-lingual transfer for character NNLMs applied to low-resource Automatic Speech Recognition (ASR). However, applying cross-lingual transfer to character NNLMs is not as straightforward. We observe that relatedness of the source language plays an important role in cross-lingual pretraining of character NNLMs. We evaluate this aspect on ASR tasks for two target languages: Finnish (with English and Estonian as source) and Swedish (with Danish, Norwegian, and English as source). Prior work has observed no difference between using the related or unrelated language for multi-character NNLMs. We, however, show that for character-based NNLMs, only pretraining with a related language improves the ASR performance, and using an unrelated language may deteriorate it. We also observe that the benefits are larger when there is much lesser target data than source data.

pdf bib
Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning
Stig-Arne Grönroos | Sami Virpioja | Mikko Kurimo
Proceedings of the 12th Language Resources and Evaluation Conference

Data-driven segmentation of words into subword units has been used in various natural language processing applications such as automatic speech recognition and statistical machine translation for almost 20 years. Recently it has became more widely adopted, as models based on deep neural networks often benefit from subword units even for morphologically simpler languages. In this paper, we discuss and compare training algorithms for a unigram subword model, based on the Expectation Maximization algorithm and lexicon pruning. Using English, Finnish, North Sami, and Turkish data sets, we show that this approach is able to find better solutions to the optimization problem defined by the Morfessor Baseline model than its original recursive training algorithm. The improved optimization also leads to higher morphological segmentation accuracy when compared to a linguistic gold standard. We publish implementations of the new algorithms in the widely-used Morfessor software package.

pdf bib
Service registration chatbot: collecting and comparing dialogues from AMT workers and service’s users
Luca Molteni | Mittul Singh | Juho Leinonen | Katri Leino | Mikko Kurimo | Emanuele Della Valle
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)

Crowdsourcing is the go-to solution for data collection and annotation in the context of NLP tasks. Nevertheless, crowdsourced data is noisy by nature; the source is often unknown and additional validation work is performed to guarantee the dataset’s quality. In this article, we compare two crowdsourcing sources on a dialogue paraphrasing task revolving around a chatbot service. We observe that workers hired on crowdsourcing platforms produce lexically poorer and less diverse rewrites than service users engaged voluntarily. Notably enough, on dialogue clarity and optimality, the two paraphrase sources’ human-perceived quality does not differ significantly. Furthermore, for the chatbot service, the combined crowdsourced data is enough to train a transformer-based Natural Language Generation (NLG) system. To enable similar services, we also release tools for collecting data and training the dialogue-act-based transformer-based NLG module.

2019

pdf bib
North Sámi morphological segmentation with low-resource semi-supervised sequence labeling
Stig-Arne Grönroos | Sámi Virpioja | Mikko Kurimo
Proceedings of the Fifth International Workshop on Computational Linguistics for Uralic Languages

pdf bib
A user study to compare two conversational assistants designed for people with hearing impairments
Anja Virkkunen | Juri Lukkarila | Kalle Palomäki | Mikko Kurimo
Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies

Participating in conversations can be difficult for people with hearing loss, especially in acoustically challenging environments. We studied the preferences the hearing impaired have for a personal conversation assistant based on automatic speech recognition (ASR) technology. We created two prototypes which were evaluated by hearing impaired test users. This paper qualitatively compares the two based on the feedback obtained from the tests. The first prototype was a proof-of-concept system running real-time ASR on a laptop. The second prototype was developed for a mobile device with the recognizer running on a separate server. In the mobile device, augmented reality (AR) was used to help the hearing impaired observe gestures and lip movements of the speaker simultaneously with the transcriptions. Several testers found the systems useful enough to use in their daily lives, with majority preferring the mobile AR version. The biggest concern of the testers was the accuracy of the transcriptions and the lack of speaker identification.

2018

pdf bib
New Baseline in Automatic Speech Recognition for Northern Sámi
Juho Leinonen | Peter Smit | Sámi Virpioja | Mikko Kurimo
Proceedings of the Fourth International Workshop on Computational Linguistics of Uralic Languages

pdf bib
Cognate-aware morphological segmentation for multilingual neural translation
Stig-Arne Grönroos | Sami Virpioja | Mikko Kurimo
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

This article describes the Aalto University entry to the WMT18 News Translation Shared Task. We participate in the multilingual subtrack with a system trained under the constrained condition to translate from English to both Finnish and Estonian. The system is based on the Transformer model. We focus on improving the consistency of morphological segmentation for words that are similar orthographically, semantically, and distributionally; such words include etymological cognates, loan words, and proper names. For this, we introduce Cognate Morfessor, a multilingual variant of the Morfessor method. We show that our approach improves the translation quality particularly for Estonian, which has less resources for training the translation model.

pdf bib
The MeMAD Submission to the WMT18 Multimodal Translation Task
Stig-Arne Grönroos | Benoit Huet | Mikko Kurimo | Jorma Laaksonen | Bernard Merialdo | Phu Pham | Mats Sjöberg | Umut Sulubacak | Jörg Tiedemann | Raphael Troncy | Raúl Vázquez
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

This paper describes the MeMAD project entry to the WMT Multimodal Machine Translation Shared Task. We propose adapting the Transformer neural machine translation (NMT) architecture to a multi-modal setting. In this paper, we also describe the preliminary experiments with text-only translation systems leading us up to this choice. We have the top scoring system for both English-to-German and English-to-French, according to the automatic metrics for flickr18. Our experiments show that the effect of the visual features in our system is small. Our largest gains come from the quality of the underlying text-only NMT system. We find that appropriate use of additional data is effective.

2017

pdf bib
Acoustic Model Compression with MAP adaptation
Katri Leino | Mikko Kurimo
Proceedings of the 21st Nordic Conference on Computational Linguistics

pdf bib
Extending hybrid word-character neural machine translation with multi-task learning of morphological analysis
Stig-Arne Grönroos | Sami Virpioja | Mikko Kurimo
Proceedings of the Second Conference on Machine Translation

2016

pdf bib
Hybrid Morphological Segmentation for Phrase-Based Machine Translation
Stig-Arne Grönroos | Sami Virpioja | Mikko Kurimo
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf bib
A Comparative Study of Minimally Supervised Morphological Segmentation
Teemu Ruokolainen | Oskar Kohonen | Kairit Sirts | Stig-Arne Grönroos | Mikko Kurimo | Sami Virpioja
Computational Linguistics, Volume 42, Issue 1 - March 2016

2015

pdf bib
Towards Reliable Automatic Multimodal Content Analysis
Olli-Philippe Lautenbacher | Liisa Tiittula | Maija Hirvonen | Jorma Laaksonen | Mikko Kurimo
Proceedings of the Fourth Workshop on Vision and Language

pdf bib
Tuning Phrase-Based Segmented Translation for a Morphologically Complex Target Language
Stig-Arne Grönroos | Sami Virpioja | Mikko Kurimo
Proceedings of the Tenth Workshop on Statistical Machine Translation

2014

pdf bib
Part-of-Speech Tagging using Conditional Random Fields: Exploiting Sub-Label Dependencies for Improved Accuracy
Miikka Silfverberg | Teemu Ruokolainen | Krister Lindén | Mikko Kurimo
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf bib
Morfessor 2.0: Toolkit for statistical morphological segmentation
Peter Smit | Sami Virpioja | Stig-Arne Grönroos | Mikko Kurimo
Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics

pdf bib
Accelerated Estimation of Conditional Random Fields using a Pseudo-Likelihood-inspired Perceptron Variant
Teemu Ruokolainen | Miikka Silfverberg | Mikko Kurimo | Krister Linden
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers

pdf bib
Painless Semi-Supervised Morphological Segmentation using Conditional Random Fields
Teemu Ruokolainen | Oskar Kohonen | Sami Virpioja | Mikko Kurimo
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers

pdf bib
Morfessor FlatCat: An HMM-Based Method for Unsupervised and Semi-Supervised Learning of Morphology
Stig-Arne Grönroos | Sami Virpioja | Peter Smit | Mikko Kurimo
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
A Toolkit for Efficient Learning of Lexical Units for Speech Recognition
Matti Varjokallio | Mikko Kurimo
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

String segmentation is an important and recurring problem in natural language processing and other domains. For morphologically rich languages, the amount of different word forms caused by morphological processes like agglutination, compounding and inflection, may be huge and causes problems for traditional word-based language modeling approach. Segmenting text into better modelable units is thus an important part of the modeling task. This work presents methods and a toolkit for learning segmentation models from text. The methods may be applied to lexical unit selection for speech recognition and also other segmentation tasks.

2013

pdf bib
Supervised Morphological Segmentation in a Low-Resource Learning Setting using Conditional Random Fields
Teemu Ruokolainen | Oskar Kohonen | Sami Virpioja | Mikko Kurimo
Proceedings of the Seventeenth Conference on Computational Natural Language Learning

2012

pdf bib
Unsupervised Vocabulary Adaptation for Morph-based Language Models
André Mansikkaniemi | Mikko Kurimo
Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT

2010

pdf bib
Applying Morphological Decompositions to Statistical Machine Translation
Sami Virpioja | Jaakko Väyrynen | André Mansikkaniemi | Mikko Kurimo
Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

pdf bib
Morpho Challenge 2005-2010: Evaluations and Results
Mikko Kurimo | Sami Virpioja | Ville Turunen | Krista Lagus
Proceedings of the 11th Meeting of the ACL Special Interest Group on Computational Morphology and Phonology

pdf bib
Domain Adaptation of Maximum Entropy Language Models
Tanel Alumäe | Mikko Kurimo
Proceedings of the ACL 2010 Conference Short Papers

pdf bib
Personalising Speech-To-Speech Translation in the EMIME Project
Mikko Kurimo | William Byrne | John Dines | Philip N. Garner | Matthew Gibson | Yong Guan | Teemu Hirsimäki | Reima Karhila | Simon King | Hui Liang | Keiichiro Oura | Lakshmi Saheer | Matt Shannon | Sayaki Shiota | Jilei Tian
Proceedings of the ACL 2010 System Demonstrations

2009

pdf bib
Minimum Bayes Risk Combination of Translation Hypotheses from Alternative Morphological Decompositions
Adrià de Gispert | Sami Virpioja | Mikko Kurimo | William Byrne
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers

pdf bib
Analysing Recognition Errors in Unlimited-Vocabulary Speech Recognition
Teemu Hirsimäki | Mikko Kurimo
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers

pdf bib
Morpho Challenge - Evaluation of algorithms for unsupervised learning of morphology in various tasks and languages
Mikko Kurimo | Sami Virpioja | Ville Turunen | Teemu Hirsimäki
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Demonstration Session

2008

pdf bib
Speech to speech machine translation: Biblical chatter from Finnish to English
David Ellis | Mathias Creutz | Timo Honkela | Mikko Kurimo
Proceedings of the IJCNLP-08 Workshop on NLP for Less Privileged Languages

2007

pdf bib
Analysis of Morph-Based Speech Recognition and the Modeling of Out-of-Vocabulary Words Across Languages
Mathias Creutz | Teemu Hirsimäki | Mikko Kurimo | Antti Puurula | Janne Pylkkönen | Vesa Siivola | Matti Varjokallio | Ebru Arisoy | Murat Saraçlar | Andreas Stolcke
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference

pdf bib
Vocabulary Decomposition for Estonian Open Vocabulary Speech Recognition
Antti Puurula | Mikko Kurimo
Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics

2006

pdf bib
Unlimited vocabulary speech recognition for agglutinative languages
Mikko Kurimo | Antti Puurula | Ebru Arisoy | Vesa Siivola | Teemu Hirsimäki | Janne Pylkkönen | Tanel Alumäe | Murat Saraclar
Proceedings of the Human Language Technology Conference of the NAACL, Main Conference