Demo Data from EDBT 2026 / reviewers in the wild / expert
Miikka Silfverberg
dblp:99/671k
· DBLP profile ↗
20ranked-venue papers
4as first author
8since 2021 · last 2024
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 20 · 4 first-author · 8 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
4 papers |
Language models and text generation · 41% Information extraction and text analysis · 29% Deep learning architectures and training · 22% | |
| Databases, data mining, and information retrieval
1 paper |
Information retrieval · 100% |
Topics — the 7 heaviest of 9, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Natural language and speech › Language models and text generation
low-resource languages |
0.8 | 1 | 2024 | Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing · EMNLP 2024 |
Machine learning › Deep learning architectures and training
data augmentation |
0.7 | 1 | 2023 | Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection · EMNLP 2023 |
Natural language and speech › Language models and text generation
low-resource language processing |
0.7 | 1 | 2023 | Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection · EMNLP 2023 |
Natural language and speech › Information extraction and text analysis › computational morphology
morphological inflection |
0.7 | 1 | 2023 | Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection · EMNLP 2023 |
Natural language and speech › Information extraction and text analysis
morphological analysis |
0.3 | 1 | 2018 | An Encoder-Decoder Approach to the Paradigm Cell Filling Problem · EMNLP 2018 |
Machine learning › Deep learning architectures and training
encoder-decoder architecture |
0.1 | 1 | 2018 | An Encoder-Decoder Approach to the Paradigm Cell Filling Problem · EMNLP 2018 |
Machine learning › Probabilistic and Bayesian machine learning › statistical inference › density estimation
kernel density estimation |
0.1 | 1 | 2015 | Kernel Density Estimation for Text-Based Geolocation · AAAI 2015 |
Methods — techniques the papers use, named apart from their topics
large language model · 0.8dictionary resources · 0.8uncertainty sampling · 0.7data selection · 0.7STEM-CORRUPT · 0.7kernel density estimation · 0.4encoder-decoder neural network · 0.3
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2024 | Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource GlossingabstractIn this paper, we address the data scarcity problem in automatic data-driven glossing for low-resource languages by coordinating multiple sources of linguistic expertise.We enhance models by incorporating both tokenlevel and sentence-level translations, utilizing the extensive linguistic capabilities of modern LLMs, and incorporating available dictionary resources.Our enhancements lead to an average absolute improvement of 5%-points in word-level accuracy over the previous state of the art on a typologically diverse dataset spanning six low-resource languages.The improvements are particularly noticeable for the lowest-resourced language Gitksan, where we achieve a 10%-point improvement.Furthermore, in a simulated ultra-low resource setting for the same six languages, training on fewer than 100 glossed sentences, we establish an average 10%-point improvement in word-level accuracy over the previous state-of-the-art system. Changbing Yang, Garrett Nicolai, Miikka Silfverberg |
EMNLP | 3 |
| 2023 | Understanding Compositional Data Augmentation in Typologically Diverse Morphological InflectionabstractData augmentation techniques are widely used in low-resource automatic morphological inflection to overcome data sparsity.However, the full implications of these techniques remain poorly understood.In this study, we aim to shed light on the theoretical aspects of the prominent data augmentation strategy STEM-CORRUPT (Silfverberg et al., 2017;Anastasopoulos and Neubig, 2019), a method that generates synthetic examples by randomly substituting stem characters in gold standard training examples.To begin, we conduct an information-theoretic analysis, arguing that STEMCORRUPT improves compositional generalization by eliminating spurious correlations between morphemes, specifically between the stem and the affixes.Our theoretical analysis further leads us to study the sampleefficiency with which STEMCORRUPT reduces these spurious correlations.Through evaluation across seven typologically distinct languages, we demonstrate that selecting a subset of datapoints with both high diversity and high predictive uncertainty significantly enhances the data-efficiency of STEMCORRUPT.However, we also explore the impact of typological features on the choice of the data selection strategy and find that languages incorporating a high degree of allomorphy and phonological alternations derive less benefit from synthetic examples with high uncertainty.We attribute this effect to phonotactic violations induced by STEMCORRUPT, emphasizing the need for further research to ensure optimal performance across the entire spectrum of natural language morphology. 1 Farhan Samir, Miikka Silfverberg |
EMNLP | 2 |
| 2022 | Linguistically-Motivated Yorùbá-English Machine TranslationabstractTranslating between languages where certain features are marked morphologically in one but absent or marked contextually in the other is an important test case for machine translation. When translating into English which marks (in)definiteness morphologically, from Yorùbá which uses bare nouns but marks these features contextually, ambiguities arise. In this work, we perform fine-grained analysis on how an SMT system compares with two NMT systems (BiLSTM and Transformer) when translating bare nouns in Yorùbá into English. We investigate how the systems what extent they identify BNs, correctly translate them, and compare with human translation patterns. We also analyze the type of errors each model makes and provide a linguistic description of these errors. We glean insights for evaluating model performance in low-resource settings. In translating bare nouns, our results show the transformer model outperforms the SMT and BiLSTM models for 4 categories, the BiLSTM outperforms the SMT model for 3 categories while the SMT outperforms the NMT models for 1 category. Ife Adebara, Muhammad Abdul-Mageed, Miikka Silfverberg |
COLING | 3 |
| 2022 | Yet Another Format of Universal Dependencies for KoreanabstractIn this study, we propose a morpheme-based scheme for Korean dependency parsing and adopt the proposed scheme to Universal Dependencies. We present the linguistic rationale that illustrates the motivation and the necessity of adopting the morpheme-based format, and develop scripts that convert between the original format used by Universal Dependencies and the proposed morpheme-based format automatically. The effectiveness of the proposed format for Korean dependency parsing is then testified by both statistical and neural models, including UDPipe and Stanza, with our carefully constructed morpheme-based word embedding for Korean. morphUD outperforms parsing results for all Korean UD treebanks, and we also present detailed error analysis. Eunkyul Leah Jo, Yundong Yao, Miikka Silfverberg, Francis M. Tyers, Jungyeul Park |
COLING | 5 |
| 2022 | Penalizing Divergence: Multi-Parallel Translation for Low-Resource Languages of North AmericaabstractThis paper explores a special case in multilingual machine translation: so called multi-parallel translation, where the target data for all language pairs are identical. While multi-parallelism offers benefits which are not available in a standard translation setting, translation models can easily overfit when training data are limited. We introduce a regularizer, the divergence penalty, which penalizes the translation model when it represents source sentences with identical target translations in divergent ways. Experiments on very low-resourced Indigenous North American languages show that an initially deficient multilingual translator can improve by 4.9 BLEU through mBART pre-training, and 5.5 BLEU points with the strategic addition of monolingual data, and that a divergence penalty leads to further increases of 0.4 BLEU. Further experiments on Germanic languages demonstrate a improvement of 0.5 BLEU when applying the divergence penalty. An investigation of the neural encoder representations learned by our translation models shows that the divergence penalty encourages models to learn a unified neural interlingua. Garrett Nicolai, Changbing Yang, Miikka Silfverberg |
COLING | 3 |
| 2022 | UniMorph 4.0: Universal MorphologyabstractThe Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation, and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements on several fronts that were made in the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 66 new languages, including 24 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g., missing gender and macrons information. We have amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet. Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa, Nizar Habash, Witold Kieras, Gábor Bella, Brian Leonard, Garrett Nicolai, Kyle Gorman, Yustinus Ghanggo Ate, Maria Ryskina, Sabrina J. Mielke, Elena Budianskaya, Charbel El-Khaissi, Tiago Pimentel, Michael Gasser, William Lane 0002, Mohit Raj, Matt Coler, Jaime Rafael Montoya Samame, Delio Siticonatzi Camaiteri, Esaú Zumaeta Rojas, Didier López Francis, Arturo Oncevay, Juan López Bautista, Gema Celeste Silva Villegas, Lucas Torroba Hennigen, Adam Ek, David Guriel, Peter Dirix, Jean-Philippe Bernardy, Andrey Scherbakov, Aziyana Bayyr-ool, Antonios Anastasopoulos, Roberto Zariquiey, Karina Sheifer, Sofya Ganieva, Hilaria Cruz, Ritván Karahóga, Stella Markantonatou, George Pavlidis, Matvey Plugaryov, Elena Klyachko, Ali Salehi, Candy Angulo, Jatayu Baxi, Andrew Krizhanovsky, Natalia Krizhanovskaya, Elizabeth Salesky, Clara Vania, Sardana Ivanova, Jennifer C. White, Rowan Hall Maudslay, Josef Valvoda, Ran Zmigrod, Paula Czarnowska, Irene Nikkarinen, Aelita Salchak, Brijesh Bhatt, Christopher Straughn, Zoey Liu, Jonathan Washington, Yuval Pinter, Duygu Ataman, Marcin Wolinski, Totok Suhardijanto, Anna Yablonskaya, Niklas Stoehr, Hossep Dolatian, Zahroh Nuriah, Shyam Ratan, Francis M. Tyers, Edoardo Maria Ponti, Grant Aiton, Aryaman Arora, Richard J. Hatcher, Ritesh Kumar 0002, Jeremiah Young, Daria Rodionova, Anastasia Yemelina, Taras Andrushko, Igor Marchenko, Polina Mashkovtseva, Alexandra Serova, Emily Tucker Prud'hommeaux, Maria Nepomniashchaya, Fausto Giunchiglia, Eleanor Chodroff, Mans Hulden, Miikka Silfverberg, Arya McCarthy, David Yarowsky, Ryan Cotterell, Reut Tsarfaty, Ekaterina Vylomova |
LREC | 90 |
| 2022 | An Inflectional Database for GitksanabstractThis paper presents a new inflectional resource for Gitksan, a low-resource Indigenous language of Canada. We use Gitksan data in interlinear glossed format, stemming from language documentation efforts, to build a database of partial inflection tables. We then enrich this morphological resource by filling in blank slots in the partial inflection tables using neural transformer reinflection models. We extend the training data for our transformer reinflection models using two data augmentation techniques: data hallucination and back-translation. Experimental results demonstrate substantial improvements from data augmentation, with data hallucination delivering particularly impressive gains. We also release reinflection models for Gitksan. Bruce Harold Oliver, Clarissa Forbes, Changbing Yang, Farhan Samir, Edith Coates, Garrett Nicolai, Miikka Silfverberg |
LREC | 7 |
| 2021 | Do RNN States Encode Abstract Phonological Alternations?abstractMiikka Silfverberg, Francis Tyers, Garrett Nicolai, Mans Hulden. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021. Miikka Silfverberg, Francis M. Tyers, Garrett Nicolai, Mans Hulden |
NAACL-HLT | 1 |
| 2020 | Noise Isn't Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection ModelsabstractMorphological inflection, like many sequence-to-sequence tasks, sees great performance from recurrent neural architectures when data is plentiful, but performance falls off sharply in lowerdata settings.We investigate one aspect of neural seq2seq models that we hypothesize contributes to overfitting -teacher forcing.By creating different training and test conditions, exposure bias increases the likelihood that a system too closely models its training data.Experiments show that teacher-forced models struggle to recover when they enter unknown territory.However, a simple modification to the training algorithm to more closely mimic test conditions creates models that are better able to generalize to unseen environments. Garrett Nicolai, Miikka Silfverberg |
COLING | 2 |
| 2020 | UniMorph 3.0: Universal MorphologyabstractThe Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological paradigms for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. We have implemented several improvements to the extraction pipeline which creates most of our data, so that it is both more complete and more correct. We have added 66 new languages, as well as new parts of speech for 12 languages. We have also amended the schema in several ways. Finally, we present three new community tools: two to validate data for resource creators, and one to make morphological data available from the command line. UniMorph is based at the Center for Language and Speech Processing (CLSP) at Johns Hopkins University in Baltimore, Maryland. This paper details advances made to the schema, tooling, and dissemination of project resources since the UniMorph 2.0 release described at LREC 2018. Arya McCarthy, Christo Kirov, Matteo Grella, Amrit Nidhi, Patrick Xia 0002, Kyle Gorman, Ekaterina Vylomova, Sabrina J. Mielke, Garrett Nicolai, Miikka Silfverberg, Timofey Arkhangelskiy, Nataly Krizhanovsky, Andrew Krizhanovsky, Elena Klyachko, Alexey Sorokin, John Mansfield, Valts Ernstreits, Yuval Pinter, Cassandra L. Jacobs, Ryan Cotterell, Mans Hulden, David Yarowsky |
LREC | 10 |
| 2020 | Automated Phonological Transcription of Akkadian Cuneiform TextabstractAkkadian was an East-Semitic language spoken in ancient Mesopotamia. The language is attested on hundreds of thousands of cuneiform clay tablets. Several Akkadian text corpora contain only the transliterated text. In this paper, we investigate automated phonological transcription of the transliterated corpora. The phonological transcription provides a linguistically appealing form to represent Akkadian, because the transcription is normalized according to the grammatical description of a given dialect and explicitly shows the Akkadian renderings for Sumerian logograms. Because cuneiform text does not mark the inflection for logograms, the inflected form needs to be inferred from the sentence context. To the best of our knowledge, this is the first documented attempt to automatically transcribe Akkadian. Using a context-aware neural network model, we are able to automatically transcribe syllabic tokens at near human performance with 96% recall @ 3, while the logogram transcription remains more challenging at 82% recall @ 3. Aleksi Sahala, Miikka Silfverberg, Antti Arppe, Krister Lindén |
LREC | 2 |
| 2020 | BabyFST - Towards a Finite-State Based Computational Model of Ancient BabylonianabstractAkkadian is a fairly well resourced extinct language that does not yet have a comprehensive morphological analyzer available. In this paper we describe a general finite-state based morphological model for Babylonian, a southern dialect of the Akkadian language, that can achieve a coverage up to 97.3% and recall up to 93.7% on lemmatization and POS-tagging task on token level from a transcribed input. Since Akkadian word forms exhibit a high degree of morphological ambiguity, in that only 20.1% of running word tokens receive a single unambiguous analysis, we attempt a first pass at weighting our finite-state transducer, using existing extensive Akkadian corpora which have been partially validated for their lemmas and parts-of-speech but not the entire morphological analyses. The resultant weighted finite-state transducer yields a moderate improvement so that for 57.4% of the word tokens the highest ranked analysis is the correct one. We conclude with a short discussion on how morphological ambiguity in the analysis of Akkadian could be further reduced with improvements in the training data used in weighting the finite-state transducer as well as through other, context-based techniques. Aleksi Sahala, Miikka Silfverberg, Antti Arppe, Krister Lindén |
LREC | 2 |
| 2019 | Weird Inflects but OK: Making Sense of Morphological Generation ErrorsabstractWe conduct a manual error analysis of the CoNLL-SIGMORPHON 2017 Shared Task on Morphological Reinflection.In this task, systems are given a word in citation form (e.g., hug) and asked to produce the corresponding inflected form (e.g., the simple past hugged).This design lets us analyze errors much like we might analyze children's production errors.We propose an error taxonomy and use it to annotate errors made by the top two systems across twelve languages.Many of the observed errors are related to inflectional patterns sensitive to inherent linguistic properties such as animacy or affect; many others are failures to predict truly unpredictable inflectional behaviors.We also find nearly one quarter of the residual "errors" reflect errors in the gold data. Kyle Gorman, Arya McCarthy, Ryan Cotterell, Ekaterina Vylomova, Miikka Silfverberg, Magdalena Markowska |
CoNLL | 5 |
| 2018 | A Computational Model for the Linguistic Notion of Morphological ParadigmabstractIn supervised learning of morphological patterns, the strategy of generalizing inflectional tables into more abstract paradigms through alignment of the longest common subsequence found in an inflection table has been proposed as an efficient method to deduce the inflectional behavior of unseen word forms. In this paper, we extend this notion of morphological ‘paradigm’ from earlier work and provide a formalization that more accurately matches linguist intuitions about what an inflectional paradigm is. Additionally, we propose and evaluate a mechanism for learning full human-readable paradigm specifications from incomplete data—a scenario when we only have access to a few inflected forms for each lexeme, and want to reconstruct the missing inflections as well as generalize and group the witnessed patterns into a model of more abstract paradigmatic behavior of lexemes. Miikka Silfverberg, Mans Hulden |
COLING | 1 |
| 2018 | An Encoder-Decoder Approach to the Paradigm Cell Filling ProblemabstractThe Paradigm Cell Filling Problem in morphology asks to complete word inflection tables from partial ones.We implement novel neural models for this task, evaluating them on 18 data sets in 8 languages, showing performance that is comparable with previous work with far less training data.We also publish a new dataset for this task and code implementing the system described in this paper.1 Miikka Silfverberg, Mans Hulden |
EMNLP | 1 |
| 2018 | A Computational Architecture for the Morphology of Upper Tanana
Olga Lovick, Christopher Cox, Miikka Silfverberg, Antti Arppe, Mans Hulden |
LREC | 3 |
| 2015 | Kernel Density Estimation for Text-Based GeolocationabstractText-based geolocation classifiers often operate with a grid-based view of the world. Predicting document location of origin based on text content on a geodesic grid is computationally attractive since many standard methods for supervised document classification carry over unchanged to geolocation in the form of predicting a most probable grid cell for a document. However, the grid-based approach suffers from sparse data problems if one wants to improve classification accuracy by moving to smaller cell sizes. In this paper we investigate an enhancement of common methods for determining the geographic point of origin of a text document by kernel density estimation. For geolocation of tweets we obtain a improvements upon non-kernel methods on datasets of U.S. and global Twitter content. Mans Hulden, Miikka Silfverberg, Jerid Francom |
AAAI | 2 |
| 2014 | Accelerated Estimation of Conditional Random Fields using a Pseudo-Likelihood-inspired Perceptron VariantabstractTeemu 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. 2014. Teemu Ruokolainen, Miikka Silfverberg, Mikko Kurimo, Krister Lindén |
EACL | 2 |
| 2014 | Heuristic Hyper-minimization of Finite State Lexicons
Senka Drobac, Krister Lindén, Flammie A. Pirinen, Miikka Silfverberg |
LREC | 4 |
| 2012 | Predictive Text Entry for Agglutinative Languages Using Unsupervised Morphological Segmentation
Miikka Silfverberg, Krister Lindén, Mirka Hyvärinen |
CICLing (2) | 1 |