Papers by Miikka Silfverberg
Resisting the Lure of the Skyline: Grounding Practices in Active Learning for Morphological Inflection (2024.acl-short)
Copied to clipboard
| Challenge: | Several approaches to active learning are available, including confidence-based, diversity-based and committee-based. |
| Approach: | They propose to use a baseline and a skyline to measure the accuracy of the unannotated sample pool. |
| Outcome: | The proposed model outperforms a random selection baseline and a skyline approach. |
Linguistically-Motivated Yorùbá-English Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Several phenomena where asymmetry arises have been identified as challenging problems for machine translation. |
| Approach: | They perform a fine-grained analysis of how an SMT system compares with two NMT systems when translating bare nouns into English. |
| Outcome: | The proposed model outperforms the SMT and BiLSTM models for 4 categories and the BiLST outperformed the SLT models for 3 categories. |
Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing (2024.emnlp-main)
Copied to clipboard
| Challenge: | a paper addresses the data scarcity problem in automated glossing for low-resource languages . traditional manual documenting is laborintensive and a lack of data is limiting the accuracy of glossing . |
| Approach: | They propose to integrate token-level and sentence-level translations into models and integrate available dictionary resources into the model. |
| Outcome: | The proposed model improves word-level accuracy by 5% on the lowest-resource language Gitksan . the authors also show that the model improve on a simulated low-resourced language with fewer than 100 glossed sentences . |
Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection (2023.emnlp-main)
Copied to clipboard
| Challenge: | a data augmentation technique that generates synthetic examples by randomly substituting stem characters in existing training examples is still poorly understood. |
| Approach: | They propose a data augmentation strategy that generates synthetic examples by randomly substituting stem characters in existing training examples. |
| Outcome: | The proposed method generates synthetic examples by randomly substituting stem characters in existing training examples. |
PyFoma: a Python finite-state compiler module (2024.acl-demos)
Copied to clipboard
| Challenge: | Finite-state models can be used to constrain output of neural networks to prevent text generation that fails to adhere to a specific format. |
| Approach: | They propose to build finite-state automata from regular expressions, string rewriting rules, right-linear grammars, or low-level state/transition manipulation. |
| Outcome: | The module is designed for teaching finite-state models and finite models. |
A Computational Architecture for the Morphology of Upper Tanana (L18-1)
Copied to clipboard
| Challenge: | a computational model of Upper Tanana is described to model the Dene language . the model uses lexical-inflectional verb classes to predict possible derivations and their morphological behavior. |
| Approach: | They propose a computational model of Upper Tanana, a highly endangered Dene language . the model parses and generates inflected Upper Tanans and uses a lexical-inflectional verb system to predict possible derivations and their morphological behavior. |
| Outcome: | The proposed model parses and generates inflected Upper Tanana verb forms . it also uses the language's verb theme category system to predict possible derivations and their morphological behavior . |
Yet Another Format of Universal Dependencies for Korean (2022.coling-1)
Copied to clipboard
Yige Chen, Eunkyul Leah Jo, Yundong Yao, KyungTae Lim, Miikka Silfverberg, Francis M. Tyers, Jungyeul Park
| Challenge: | Existing dependency parsers for Korean do not perform as well as their English counterparts due to the complexity of Korean's linguistic features. |
| Approach: | They propose a morpheme-based Korean dependency parsing format and propose to adopt it to Universal Dependencies. |
| Outcome: | The proposed format outperforms parsing results for Korean UD treebanks and detailed error analysis. |
BabyFST - Towards a Finite-State Based Computational Model of Ancient Babylonian (2020.lrec-1)
Copied to clipboard
| Challenge: | morphological analyzer for Akkadian is not yet available for the extinct language . we present a general finite-state based model for Babylonian that can achieve a coverage of 97.3% and a recall of 93.7% on token level. |
| Approach: | They propose a general finite-state based morphological model for Babylonian that can achieve a coverage of 97.3% and recall up to 93.7% on lemmatization and POS-tagging tasks. |
| Outcome: | The proposed model can achieve coverage and recall of 97.3% on lemmatization and POS-tagging tasks on token level from a transcribed input. |
Penalizing Divergence: Multi-Parallel Translation for Low-Resource Languages of North America (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies show that multi-parallel translation models can overfit when training data are limited. |
| Approach: | They introduce a regularizer which penalizes translation models when they represent source sentences with identical target translations in divergent ways. |
| Outcome: | The proposed model improves when the target data for all language pairs are identical. |
An Investigation of Noise in Morphological Inflection (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural morphological inflection systems can be used for languages with very little supervised data, but are often less likely to have clean, goldstandard data. |
| Approach: | They propose an error taxonomy and annotation pipeline for inflection training data and propose a character-level masked language modeling (CMLM) pretraining objective. |
| Outcome: | The proposed pipeline is based on error taxonomy and annotation pipelines for unsupervised morphological paradigm completion. |
A Computational Model for the Linguistic Notion of Morphological Paradigm (C18-1)
Copied to clipboard
| Challenge: | In supervised learning of morphological patterns, the strategy of generalizing inflectional tables into more abstract paradigms has been proposed as an efficient method to deduce the inflection of unseen word forms. |
| Approach: | They propose to generalize inflectional tables into more abstract paradigms by aligning the longest common subsequence found in an inflection table with the longest lexeme. |
| Outcome: | The proposed method matches linguist intuitions about what an inflectional paradigm is and can reconstruct missing inflections and generalize and group the witnessed patterns into a model of more abstract paradigmatic behavior of lexemes. |
Noise Isn’t Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models (2020.coling-main)
Copied to clipboard
| Challenge: | Morphological inflection is a sequence-to-sequence task that sees great performance when data is plentiful, but performance falls off sharply in lower-data settings. |
| Approach: | They hypothesize that teacher forcing increases the likelihood that a model too closely models its training data. |
| Outcome: | Experiments show that teacher forcing can overfit models when they enter unknown territory. |
Do RNN States Encode Abstract Phonological Alternations? (2021.naacl-main)
Copied to clipboard
| Challenge: | Sequence-to-sequence models have been successful in word formation tasks, but the opacity of the models makes it difficult to determine whether complex generalizations are learned or whether there is some level of generalization across related sound changes. |
| Approach: | They propose to train character-based sequence-to-sequence models for inflection of Finnish nouns into the genitive case, an inflation type which is encoded in the hidden states of an LSTM encoderdecoder trained to perform word infference. |
| Outcome: | The proposed models encode 17 different consonant gradation processes in a handful of dimensions in the RNN. |
Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Under-Documented Languages (2022.findings-acl)
Copied to clipboard
Clarissa Forbes, Farhan Samir, Bruce Oliver, Changbing Yang, Edith Coates, Garrett Nicolai, Miikka Silfverberg
| Challenge: | Recent progress in NLP is driven by pretrained models leveraging massive datasets. |
| Approach: | They argue that IGT data can be leveraged provided target language expertise is available and that it can be used to create effective models. |
| Outcome: | The proposed model can be leveraged provided that target language expertise is available. |
An Inflectional Database for Gitksan (2022.lrec-1)
Copied to clipboard
Bruce Oliver, Clarissa Forbes, Changbing Yang, Farhan Samir, Edith Coates, Garrett Nicolai, Miikka Silfverberg
| Challenge: | In this paper, we build a database of partial inflection tables for Gitksan, a low-resource Indigenous language of Canada. |
| Approach: | They use Gitksan data in interlinear glossed format to build a database of partial inflection tables and enrich it with neural transformer reinflection models. |
| Outcome: | The proposed model improves the performance of the experimental data hallucination and back-translation techniques. |
Automated Phonological Transcription of Akkadian Cuneiform Text (2020.lrec-1)
Copied to clipboard
| Challenge: | Akkadian was an east-semitic language spoken in ancient Mesopotamia . cuneiform text does not mark the inflection for logograms, so the inflected form needs to be inferred from the sentence context. |
| Approach: | They propose to automate phonological transcription of the transliterated Akkadian corpora . transcription is normalized according to the grammatical description of a given dialect . they find that cuneiform text does not mark the inflection for logograms . |
| Outcome: | The proposed transcriptions show the Akkadian renderings for Sumerian logograms, while the logogram transcription is more challenging. |
Morphological Processing of Low-Resource Languages: Where We Are and What’s Next (2022.findings-acl)
Copied to clipboard
Adam Wiemerslage, Miikka Silfverberg, Changbing Yang, Arya McCarthy, Garrett Nicolai, Eliana Colunga, Katharina Kann
| Challenge: | Existing models for morphological processing are not suitable for low-resource languages, but they are still lacking in the field of computational morphology. |
| Approach: | They propose to bridge two unsupervised models to understand a language’s morphology from raw text alone and propose to use them to improve their models. |
| Outcome: | The proposed models perform reasonably, but there is room for improvement. |
UniMorph 4.0: Universal Morphology (2022.lrec-1)
Copied to clipboard
Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa, Nizar Habash, Witold Kieraś, Gábor Bella, Brian Leonard, Garrett Nicolai, Kyle Gorman, Yustinus Ghanggo Ate, Maria Ryskina, Sabrina Mielke, Elena Budianskaya, Charbel El-Khaissi, Tiago Pimentel, Michael Gasser, William Abbott Lane, 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 Karahóǧa, 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 White, Rowan Hall Maudslay, Josef Valvoda, Ran Zmigrod, Paula Czarnowska, Irene Nikkarinen, Aelita Salchak, Brijesh Bhatt, Christopher Straughn, Zoey Liu, Jonathan North Washington, Yuval Pinter, Duygu Ataman, Marcin Wolinski, Totok Suhardijanto, Anna Yablonskaya, Niklas Stoehr, Hossep Dolatian, Zahroh Nuriah, Shyam Ratan, Francis M. Tyers, Edoardo M. Ponti, Grant Aiton, Aryaman Arora, Richard J. Hatcher, Ritesh Kumar, Jeremiah Young, Daria Rodionova, Anastasia Yemelina, Taras Andrushko, Igor Marchenko, Polina Mashkovtseva, Alexandra Serova, Emily Prud’hommeaux, Maria Nepomniashchaya, Fausto Giunchiglia, Eleanor Chodroff, Mans Hulden, Miikka Silfverberg, Arya D. McCarthy, David Yarowsky, Ryan Cotterell, Reut Tsarfaty, Ekaterina Vylomova
| Challenge: | The Universal Morphology project provides broad-coverage instantiated morphological inflection tables for hundreds of diverse languages. |
| Approach: | They propose a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. |
| Outcome: | The proposed schema has added 66 new languages, including 24 endangered languages. |
UniMorph 3.0: Universal Morphology (2020.lrec-1)
Copied to clipboard
Arya D. McCarthy, Christo Kirov, Matteo Grella, Amrit Nidhi, Patrick Xia, Kyle Gorman, Ekaterina Vylomova, Sabrina J. Mielke, Garrett Nicolai, Miikka Silfverberg, Timofey Arkhangelskiy, Nataly Krizhanovsky, Andrew Krizhanovsky, Elena Klyachko, Alexey Sorokin, John Mansfield, Valts Ernštreits, Yuval Pinter, Cassandra L. Jacobs, Ryan Cotterell, Mans Hulden, David Yarowsky
| Challenge: | Explicit modeling of morphology has demonstrable benefits for language modeling, speech recognition, word embedding and keyword search. |
| Approach: | They propose a language-independent feature schema for rich morphological annotation and a type-level resource for annotated data in diverse languages. |
| Outcome: | The proposed schema has been improved to make it more complete and correct, and adds 66 new languages and parts of speech for 12 languages. |
An Encoder-Decoder Approach to the Paradigm Cell Filling Problem (D18-1)
Copied to clipboard
| Challenge: | a Paradigm cell filling problem is a problem that asks how speakers of a language can reliably produce inflectional forms without ever witnessing them before. |
| Approach: | They implement novel neural models for the Paradigm Cell Filling Problem in morphology . they evaluate models on 18 data sets in 8 languages and implement them in a new dataset . |
| Outcome: | The proposed model performs comparable to previous work with less training data. |