1 |
DoD Enterprise Architecting: Joint Issues Derived From SOF Air Analysis
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
2 |
Using Prosody for Automatic Sentence Segmentation of Multi-Party Meetings
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
3 |
Tactical Digital Information Link-Technical Advice and Lexicon for Enabling Simulation (TADIL-TALES) II: Link 11/11B
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
7 |
Learning to Recognize Features of Valid Textual Entailments
|
|
|
|
In: DTIC (2006)
|
|
Abstract:
This paper advocates a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering and textual entailment have approximated the entailment problem as that of computing the best alignment of the hypothesis to the text, using a locally decomposable matching score. We argue that there are significant weaknesses in this approach, including flawed assumptions of monotonicity and locality. Instead we propose a pipelined approach where alignment is followed by a classification step, in which we extract features representing high-level characteristics of the entailment problem, and pass the resulting feature vector to a statistical classifier trained on development data. We report results on data from the 2005 Pascal RTE Challenge which surpass previously reported results for alignment-based systems. ; Presented at the Human Language Technology-North American chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006, held in New York, NY, on 5-9 Jun 2006; published in proceedings of the same, p41-48, 2006.
|
|
Keyword:
*COMPUTATIONAL LINGUISTICS; Cybernetics; Linguistics; NATURAL LANGUAGE; Operations Research; SYMPOSIA; TEXT PROCESSING; TEXTUAL ENTAILMENT; TEXTUAL INFERENCE SYSTEMS
|
|
URL: http://www.dtic.mil/docs/citations/ADA456759 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA456759
|
|
BASE
|
|
Hide details
|
|
8 |
A Methodology to Predict Specific Communication Themes from Overall Communication Volume for Individuals and Teams
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
9 |
Integrating Ontologies into Multiagent Systems Engineering
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
10 |
Toward an Interagency Language Roundtable Based Assessment of Speech-to-Speech Translation Capabilities
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
11 |
Dealing with Out of Domain Questions in Virtual Characters
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
12 |
Experimental Facility for Measuring the Impact of Environmental Noise and Speaker Variation on Speech-to-Speech Translation Devices
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
13 |
Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
14 |
Edge-Splitting in a Cumulative Multimodal System, for a No-Wait Temporal Threshold on Information Fusion, Combined with an Under-Specified Display
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
15 |
On Speaker-Specific Prosodic Models for Automatic Dialog Act Segmentation of Multi-Party Meetings
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
16 |
Using Linguistic Analysis to Identify High Performing Teams
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
19 |
Text Analysis Using Automated Language Translators
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
20 |
The 2005 AFRL/HEC One-Speaker Detection Systems
|
|
|
|
In: DTIC (2006)
|
|
BASE
|
|
Show details
|
|
|
|