E
Eric Nyberg
Researcher at Carnegie Mellon University
Publications - 183
Citations - 6045
Eric Nyberg is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Question answering & Machine translation. The author has an hindex of 35, co-authored 182 publications receiving 5629 citations. Previous affiliations of Eric Nyberg include Caterpillar Inc. & Microsoft.
Papers
More filters
Journal ArticleDOI
Building Watson: An Overview of the DeepQA Project
David A. Ferrucci,Eric W. Brown,Jennifer Chu-Carroll,James Fan,David C. Gondek,Aditya Kalyanpur,Adam Lally,J. William Murdock,Eric Nyberg,John M. Prager,Nico Schlaefer,Chris Welty +11 more
TL;DR: The results strongly suggest that DeepQA is an effective and extensible architecture that may be used as a foundation for combining, deploying, evaluating and advancing a wide range of algorithmic techniques to rapidly advance the field of QA.
Proceedings ArticleDOI
A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering
Di Wang,Eric Nyberg +1 more
TL;DR: The proposed method uses a stacked bidirectional Long-Short Term Memory network to sequentially read words from question and answer sentences, and then outputs their relevance scores, which outperforms previous work which requires syntactic features and external knowledge resources.
Patent
Integrated authoring and translation system
Peggy M Anderson,Kathryn L Baker,Michael M Bauer,Nicholas D Brownlow,Roy F. Busdiecker,Jaime G. Carbonell,Alexander Franz,Sharlene L Gallup,Timothy J Harris,Philip J. Hayes,James W Higdon,Dennis A Hill,Susan E Holm,David C Hudson,Huettner Alison Kay,John Robert Russell Leavitt,Deryle Lonsdale,Bruce M. McLaren,Teruko Mitamura,David Nasjleti,Irene Nirenburg,Eric Nyberg,Mervin L Rennich,Eric H. Riebling,Linda M Schmandt,John F Sweet +25 more
TL;DR: In this paper, an interactive text editor enforces lexical and grammatical constraints on a natural language subset used by the authors to create their text, which they help disambiguate to ensure translatability, and the resulting translatable source language text undergoes machine translation into any one of a set of target languages, without the translated text requiring any postediting.
Proceedings ArticleDOI
Metaphor Detection with Cross-Lingual Model Transfer
TL;DR: It is shown that it is possible to reliably discriminate whether a syntactic construction is meant literally or metaphorically using lexical semantic features of the words that participate in the construction.
Patent
Natural language processing system and method for parsing a plurality of input symbol sequences into syntactically or pragmatically correct word messages
Bruce R. Baker,Eric Nyberg +1 more
TL;DR: In this paper, a natural language processing system utilizes a symbol parsing layer in combination with an intelligent word parsing layer to produce a syntactically or pragmatic correct output sentence or other word message.