Share This Author
Building Watson: An Overview of the DeepQA Project
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.
Metaphor Detection with Cross-Lingual Model Transfer
We show 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…
A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering
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.
Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models
- Harsh Jhamtani, Varun Gangal, E. Hovy, Eric Nyberg
- LinguisticsProceedings of the Workshop on Stylistic…
- 1 July 2017
This paper explores automated methods to transform text from modern English to Shakespearean English using an end to end trainable neural model with pointers to enable copy action and pre-train embeddings of words.
An Efficient Interlingua Translation System for Multi-lingual Document Production
KANT is described, a system that reduces this requirement to produce practical, scalable, and accurate KBMT applications and results from a fully implemented prototype are presented.
Semantic Extensions of the Ephyra QA System for TREC 2007
- Nico Schlaefer, Jeongwoo Ko, J. Betteridge, M. Pathak, Eric Nyberg, Guido Sautter
- Computer ScienceTREC
The approach for the ‘other’ questions uses Wikipedia and Google to judge the relevance of answer candidates found in the corpora and a novel answer type classifier combines a statistical model and hand-coded rules to predict the answer type based on syntactic and semantic features of the question.
The Language Application Grid
The transformative aspect of the LAPPS Grid is that it orchestrates access to and deployment of language resources and processing functions available from servers around the globe and enables users to add their own language resources, services, and even service grids to satisfy their particular needs.
Structural Embedding of Syntactic Trees for Machine Comprehension
Experimental results demonstrate that the proposed structural embedding of syntactic trees (SEST) can accurately identify the syntactic boundaries of the sentences and extract answers that are syntactically coherent over the baseline methods.
Controlled Language for Multilingual Document Production: Experience with Caterpillar Technical English 1
To support consistent, high-quality authoring and translation of these documents from English into a variety of target languages, Caterpillar uses Caterpillar Technical English (CTE), a controlled English system developed in conjunction with CarnegieMellon University’s Center forMachine Translation and Carnegie Group Incorporated (CGI).
Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
- Kaixin Ma, Jonathan Francis, Quanyang Lu, Eric Nyberg, A. Oltramari
- Computer ScienceEMNLP
- 30 October 2019
This paper performs a survey of recent commonsense QA methods and provides a systematic analysis of popular knowledge resources and knowledge-integration methods, across benchmarks from multiple commonsense datasets, and shows that attention-based injection seems to be a preferable choice for knowledge integration.