D
David R. Mortensen
Researcher at Carnegie Mellon University
Publications - 72
Citations - 1026
David R. Mortensen is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Phone. The author has an hindex of 12, co-authored 52 publications receiving 725 citations. Previous affiliations of David R. Mortensen include University of California, Berkeley & University of Toronto.
Papers
More filters
Proceedings ArticleDOI
URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors
TL;DR: The URIEL knowledge base for massively multilingual NLP and the lang2vec utility, which provides information-rich vector identifications of languages drawn from typological, geographical, and phylogenetic databases and normalized to have straightforward and consistent formats, naming, and semantics are introduced.
Proceedings Article
Epitran: Precision G2P for Many Languages.
TL;DR: In a particular ASR task, Epitran was shown to improve the word error rate over Babel baselines for acoustic modeling, and its efficacy has been demonstrated in multiple research projects relating to language transfer, polyglot models, and speech.
Proceedings ArticleDOI
Phonologically Aware Neural Model for Named Entity Recognition in Low Resource Transfer Settings
TL;DR: An attentional neural model which only uses language universal phonological character representations with word embeddings to achieve state of the art performance in a monolingual setting using supervision and which can quickly adapt to a new language with minimal or no data is introduced.
Proceedings Article
PanPhon: A Resource for Mapping IPA Segments to Articulatory Feature Vectors
TL;DR: It is shown that phonological features outperform character-based models in PanPhon, a database relating over 5,000 IPA segments to 21 subsegmental articulatory features that boosts performance in various NER-related tasks.
Posted Content
Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning
Yulia Tsvetkov,Sunayana Sitaram,Manaal Faruqui,Guillaume Lample,Patrick Littell,David R. Mortensen,Alan W. Black,Lori Levin,Chris Dyer +8 more
TL;DR: The authors introduced polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to be predicted.