Sabrina J. Mielke

Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.

? Tutorial for this page

Demo Data from VLDB 2026 / reviewers in the wild / expert

dblp:218/5797 · also S. J. Mielke · DBLP profile ↗

← Back

12ranked-venue papers

3as first author

2since 2021 · last 2022

—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 12 · 3 first-author · 2 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author

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 6 papers		Information extraction and text analysis · 26% Trustworthy machine learning · 18% Machine translation · 13%
Databases, data mining, and information retrieval 1 paper		Data mining · 100%

Topics — the 12 heaviest of 14, each with the papers that count most for it

Topic	Weight	Papers	Last	Evidence papers
Data mining › text mining topic modeling	0.4	1	2020	Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too! · EMNLP (1) 2020
Machine learning › Trustworthy machine learning counterfactual data augmentation	0.4	1	2019	Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology · ACL (1) 2019
Machine learning › Deep learning architectures and training data augmentation	0.4	1	2019	Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology · ACL (1) 2019
Machine learning › Trustworthy machine learning fairness	0.4	1	2019	Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology · ACL (1) 2019
Natural language and speech › Information extraction and text analysis › multilingual NLP multilingual language modeling	0.4	1	2019	What Kind of Language Is Hard to Language-Model? · ACL (1) 2019
Natural language and speech › Language models and text generation neural language model	0.4	1	2019	Spell Once, Summon Anywhere: A Two-Level Open-Vocabulary Language Model · AAAI 2019
Computer vision › Vision and language open-vocabulary models	0.4	1	2019	Spell Once, Summon Anywhere: A Two-Level Open-Vocabulary Language Model · AAAI 2019
Natural language and speech › Information extraction and text analysis › computational morphology morphological inflection	0.3	1	2018	A Structured Variational Autoencoder for Contextual Morphological Inflection · ACL (1) 2018
Machine learning › Generative modeling variational autoencoder	0.3	1	2018	A Structured Variational Autoencoder for Contextual Morphological Inflection · ACL (1) 2018
Machine learning › Representation and self-supervised learning › pre-training pretrained word embeddings	0.1	1	2020	Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too! · EMNLP (1) 2020
Natural language and speech › Language models and text generation evaluation of language models	0.1	1	2019	What Kind of Language Is Hard to Language-Model? · ACL (1) 2019
Natural language and speech › Machine translation morphologically rich languages	0.1	1	2019	Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology · ACL (1) 2019

Methods — techniques the papers use, named apart from their topics

word embeddings · 0.9clustering · 0.9PCA · 0.9surprisal-based difficulty estimation · 0.4recurrent neural network · 0.4mixed-effects modeling · 0.4counterfactual data augmentation · 0.4bayesian generative model · 0.4wake-sleep algorithm · 0.3variational inference · 0.3

Year	Publication	Venue	Position
2022	UniMorph 4.0: Universal Morphology abstract The 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	12
2022	Reducing Conversational Agents' Overconfidence through Linguistic Calibration abstract Abstract While improving neural dialogue agents’ factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue, is transparency about ignorance. In this work, we analyze to what extent state-of-the-art chit-chat models are linguistically calibrated in the sense that their verbalized expression of doubt (or confidence) matches the likelihood that the model’s responses are factually incorrect (or correct). We find that these models are poorly calibrated, yet we show that likelihood of correctness can accurately be predicted. By incorporating such metacognitive features into the training of a controllable generation model, we obtain a dialogue agent with greatly improved linguistic calibration. Sabrina J. Mielke, Arthur Szlam, Emily Dinan, Y-Lan Boureau	Trans. Assoc. Comput. Linguistics	1
2020	It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information abstract The performance of neural machine translation systems is commonly evaluated in terms of BLEU. However, due to its reliance on target language properties and generation, the BLEU metric does not allow an assessment of which translation directions are more difficult to model. In this paper, we propose cross-mutual information (XMI): an asymmetric information-theoretic metric of machine translation difficulty that exploits the probabilistic nature of most neural machine translation models. XMI allows us to better evaluate the difficulty of translating text into the target language while controlling for the difficulty of the target-side generation component independent of the translation task. We then present the first systematic and controlled study of cross-lingual translation difficulties using modern neural translation systems. Code for replicating our experiments is available online at https://github.com/e-bug/nmt-difficulty. Emanuele Bugliarello, Sabrina J. Mielke, Antonios Anastasopoulos, Ryan Cotterell, Naoaki Okazaki	ACL	2
2020	Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too! abstract Topic models are a useful analysis tool to uncover the underlying themes within document collections.The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way to obtain topics: clustering pretrained word embeddings while incorporating document information for weighted clustering and reranking top words.We provide benchmarks for the combination of different word embeddings and clustering algorithms, and analyse their performance under dimensionality reduction with PCA.The best performing combination for our approach performs as well as classical topic models, but with lower runtime and computational complexity. Suzanna Sia, Ayush Dalmia, Sabrina J. Mielke	EMNLP (1)	3
2020	UniMorph 3.0: Universal Morphology abstract The 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	8
2020	Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset abstract This paper describes the Dakshina dataset, a new resource consisting of text in both the Latin and native scripts for 12 South Asian languages. The dataset includes, for each language: 1) native script Wikipedia text; 2) a romanization lexicon; and 3) full sentence parallel data in both a native script of the language and the basic Latin alphabet. We document the methods used for preparation and selection of the Wikipedia text in each language; collection of attested romanizations for sampled lexicons; and manual romanization of held-out sentences from the native script collections. We additionally provide baseline results on several tasks made possible by the dataset, including single word transliteration, full sentence transliteration, and language modeling of native script and romanized text. Brian Roark, Lawrence Wolf-Sonkin, Christo Kirov, Sabrina J. Mielke, Cibu Johny, Isin Demirsahin, Keith B. Hall	LREC	4
2019	Spell Once, Summon Anywhere: A Two-Level Open-Vocabulary Language Model abstract We show how the spellings of known words can help us deal with unknown words in open-vocabulary NLP tasks. The method we propose can be used to extend any closedvocabulary generative model, but in this paper we specifically consider the case of neural language modeling. Our Bayesian generative story combines a standard RNN language model (generating the word tokens in each sentence) with an RNNbased spelling model (generating the letters in each word type). These two RNNs respectively capture sentence structure and word structure, and are kept separate as in linguistics. By invoking the second RNN to generate spellings for novel words in context, we obtain an open-vocabulary language model. For known words, embeddings are naturally inferred by combining evidence from type spelling and token context. Comparing to baselines (including a novel strong baseline), we beat previous work and establish state-of-the-art results on multiple datasets. Sabrina J. Mielke, Jason Eisner	AAAI	1
2019	What Kind of Language Is Hard to Language-Model? abstract How language-agnostic are current state-ofthe-art NLP tools?Are there some types of language that are easier to model with current methods?In prior work (Cotterell et al., 2018) we attempted to address this question for language modeling, and observed that recurrent neural network language models do not perform equally well over all the highresource European languages found in the Europarl corpus.We speculated that inflectional morphology may be the primary culprit for the discrepancy.In this paper, we extend these earlier experiments to cover 69 languages from 13 language families using a multilingual Bible corpus.Methodologically, we introduce a new paired-sample multiplicative mixed-effects model to obtain language difficulty coefficients from at-least-pairwise parallel corpora.In other words, the model is aware of inter-sentence variation and can handle missing data.Exploiting this model, we show that "translationese" is not any easier to model than natively written language in a fair comparison.Trying to answer the question of what features difficult languages have in common, we try and fail to reproduce our earlier (Cotterell et al., 2018) observation about morphological complexity and instead reveal far simpler statistics of the data that seem to drive complexity in a much larger sample. Difficulty estimation from sentence surprisal Sabrina J. Mielke, Ryan Cotterell, Kyle Gorman, Brian Roark, Jason Eisner	ACL (1)	1
2019	Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology abstract Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems.Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly employed produce ungrammatical sentences in morphologically rich languages.We present a novel approach for converting between masculine-inflected and feminineinflected sentences in such languages.For Spanish and Hebrew, our approach achieves F 1 scores of 82% and 73% at the level of tags and accuracies of 90% and 87% at the level of forms.By evaluating our approach using four different languages, we show that, on average, it reduces gender stereotyping by a factor of 2.5 without any sacrifice to grammaticality. Ran Zmigrod, Sabrina J. Mielke, Hanna M. Wallach, Ryan Cotterell	ACL (1)	2
2018	A Structured Variational Autoencoder for Contextual Morphological Inflection abstract Statistical morphological inflectors are typically trained on fully supervised, type-level data.One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance?To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation.To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm.We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases. Lawrence Wolf-Sonkin, Jason Naradowsky, Sabrina J. Mielke, Ryan Cotterell	ACL (1)	3
2018	UniMorph 2.0: Universal Morphology Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia 0002, Manaal Faruqui, Sabrina J. Mielke, Arya McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden	LREC	8
2018	Incident-Driven Machine Translation and Name Tagging for Low-resource Languages Ulf Hermjakob, Daniel Marcu, Jonathan May, Sabrina J. Mielke, Nima Pourdamghani, Michael Pust, Kevin Knight, Tomer Levinboim, Kenton Murray, David Chiang 0001, Boliang Zhang, Xiaoman Pan, Di Lu 0003, Heng Ji 0001	Mach. Transl.	5