RESEARCHER PROFILE
Kristina Toutanova
← Back to Sofia University "St. Kliment Ohridski"
K
Sofia University "St. Kliment Ohridski"
Kristina Toutanova works in Topic Modeling, Natural Language Processing Techniques, Syntax, Semantics, Linguistic Variation, Speech Recognition and Synthesis, Speech and dialogue systems. Recorded institutional associations include Google (United States), Google DeepMind (United Kingdom), Sofia University "St. Kliment Ohridski".
150Publications
46,381Citations
44H-index
Inclusion identifies researchers whose recorded research contributions may inform their university’s understanding of its research community. It does not rank individual research quality or establish current employment.
Selected research works
Up to 100 highly cited works; DOI links open the original research. Counts reflect the collected record, not real-time citation totals.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2019 · 31,944 citationsFeature-rich part-of-speech tagging with a cyclic dependency network
2003 · 2,844 citationsNatural Questions: A Benchmark for Question Answering Research
2019 · 2,048 citationsObserved versus latent features for knowledge base and text inference
2015 · 1,025 citationsEnriching the knowledge sources used in a maximum entropy part-of-speech tagger
2000 · 939 citationsRepresenting Text for Joint Embedding of Text and Knowledge Bases
2015 · 750 citationsLatent Retrieval for Weakly Supervised Open Domain Question Answering
2019 · 749 citationsCross-Sentence N -ary Relation Extraction with Graph LSTMs
2017 · 443 citationsWell-Read Students Learn Better: On the Importance of Pre-training Compact Models
2019 · 398 citationsSparse, Dense, and Attentional Representations for Text Retrieval
2021 · 360 citationsBoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
2019 · 312 citationsZero-Shot Entity Linking by Reading Entity Descriptions
2019 · 241 citationsLearning Discriminative Projections for Text Similarity Measures
2011 · 212 citationsBoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
2019 · 205 citationsExtracting Parallel Sentences from Comparable Corpora using Document Level Alignment
2010 · 192 citationsPronunciation modeling for improved spelling correction
2001 · 187 citationsJoint learning improves semantic role labeling
2005 · 177 citationsA Global Joint Model for Semantic Role Labeling
2008 · 142 citationsLinGO Redwoods
2004 · 139 citationsCompositional Learning of Embeddings for Relation Paths in Knowledge Base and Text
2016 · 138 citationsThe LinGO Redwoods treebank motivation and preliminary applications
2002 · 135 citationsUnsupervised morphological segmentation with log-linear models
2009 · 133 citationsCross-Sentence N-ary Relation Extraction with Graph LSTMs
2017 · 127 citationsApplying Morphology Generation Models to Machine Translation
2008 · 121 citationsWell-Read Students Learn Better: The Impact of Student Initialization on Knowledge Distillation
2019 · 118 citations
