On the semantics of noun compounds
- R. Girju, D. Moldovan, M. Tatu, D. Antohe
- Linguistics, Computer ScienceComputer Speech and Language
- 1 October 2005
Performance Issues and Error Analysis in an Open-Domain Question Answering System
- D. Moldovan, Marius Pasca, S. Harabagiu, M. Surdeanu
- Computer ScienceAnnual Meeting of the Association for…
- 6 July 2002
The overall performance of a state-of-the-art Question Answering system depends on the depth of natural language processing resources and the tools used for answer finding.
Underspecification Presents Challenges for Credibility in Modern Machine Learning
- A. D'Amour, K. Heller, D. Sculley
- Computer ScienceArXiv
- 6 November 2020
This work shows the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain, and shows that this problem appears in a wide variety of practical ML pipelines.
Models for the Semantic Classification of Noun Phrases
- D. Moldovan, A. Badulescu, M. Tatu, D. Antohe, R. Girju
- Linguistics, Computer ScienceHLT-NAACL
- 6 May 2004
An approach for detecting semantic relations in noun phrases using a learning algorithm to automatically label complex nominals, genitives and adjectival noun phrases with the corresponding semantic relation.
Automatic Discovery of Part-Whole Relations
- R. Girju, A. Badulescu, D. Moldovan
- Computer Science, LinguisticsInternational Conference on Computational Logic
- 1 March 2006
This paper presents a supervised, semantically intensive, domain independent approach for the automatic detection of part-whole relations in text and demonstrates the importance of word sense disambiguation for this task.
Partitioning and Mapping Algorithms into Fixed Size Systolic Arrays
- D. Moldovan, J. Fortes
- Computer ScienceIEEE transactions on computers
- 1986
A technique for partitioning and mapping algorithms into VLSI systolic arrays is presented and an approach to algorithm partitioning which is also based on algorithm transformations is presented.
FALCON: Boosting Knowledge for Answer Engines
- S. Harabagiu, D. Moldovan, Paul Morarescu
- Computer ScienceText Retrieval Conference
- 1 November 2000
FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance is discussed.
LCC Tools for Question Answering
- D. Moldovan, S. Harabagiu, Orest Bolohan
- PhilosophyText Retrieval Conference
- 2002
¢¡¤£`¥T¦ §© ̈/¥ a"«¬g® ̄©°M±2¬ ́3/μ¬ ́¶°M·] ̧!1^o»¬M1⁄4®»1⁄2a3⁄4j·/¿W1⁄22«¬ a"À|ÁàÄÅÇÆ0Ȭ ́μ21⁄22®»·] ̄©μ"±~¬ ́Æ0È©®É±2¬ ́μn3/¶©Ê 3/ ̄©°M¬ ́¶ 1⁄2¬M1⁄4L1⁄2c1^±2· Ë °M¬ ́μ~μ2®É ̄ÌD1⁄2·…
COGEX: A Logic Prover for Question Answering
- D. Moldovan, Christine Clark, S. Harabagiu, Steven J. Maiorano
- Computer ScienceNorth American Chapter of the Association for…
- 27 May 2003
The idea of automated reasoning applied to question answering is introduced and the feasibility of integrating a logic prover into a Question Answering system is shown.
Learning Semantic Constraints for the Automatic Discovery of Part-Whole Relations
- R. Girju, A. Badulescu, D. Moldovan
- Computer ScienceNorth American Chapter of the Association for…
- 27 May 2003
This paper presents a method and its results for learning semantic constraints to detect part-whole relations and the targeted part-Whole relations were detected with an accuracy of 83%.
...
...