DE eng

Search in the Catalogues and Directories

Page: 1...4 5 6 7 8 9 10 11 12...15
Hits 141 – 160 of 287

141
Document Image Parsing and Understanding using Neuromorphic Architecture
In: DTIC (2015)
BASE
Show details
142
A Fast Variational Approach for Learning Markov Random Field Language Models
In: DTIC (2015)
BASE
Show details
143
Methods for Evaluating Text Extraction Toolkits: An Exploratory Investigation
In: DTIC (2015)
BASE
Show details
144
Study of Discussion Record Analysis Using Temporal Data Crystallization and Its Application to TV Scene Analysis
In: DTIC (2015)
BASE
Show details
145
Learning to Understand Natural Language with Less Human Effort
In: DTIC (2015)
Abstract: Learning to understand the meaning of natural language is an important problem within language processing that has the potential to revolutionize human interactions with computer systems. Informally, the problem specification is to map natural language text to a formal semantic representation connected to the real world. This problem has applications such as information extraction and understanding robot commands, and also may be helpful for other natural language processing tasks. Human annotation is a significant bottleneck in constructing language understanding systems. These systems have two components that are both constructed using human annotation: a semantic parser and a knowledge base. Semantic parsers are typically trained on individually-annotated sentences. Knowledge bases are typically manually constructed and given to the system. While these annotations can be provided in simple settings -- specifically, when the knowledge base is small -- the annotation burden quickly becomes unbearable as the size of the knowledge base increases. More annotated sentences are required to train the semantic parser and the knowledge base itself requires more annotations. Alternative methods to build language understanding systems that require less human annotation are necessary in order to learn to understand natural language in these more challenging settings. This thesis explores alternative supervision assumptions for building language understanding systems with the goal of reducing the annotation burden described above. I focus on two applications: information extraction and understanding language in physical environments. In the information extraction application, I present algorithms for training semantic parsers using only predicate instances from a knowledge base and an unlabeled text corpus. ; Sponsored in part by AFOSR, grant no. FA9750-09-C-0179.
Keyword: *COMPUTATIONAL LINGUISTICS; *COMPUTER PROGRAMS; *NATURAL LANGUAGE; *STATISTICAL INFERENCE; ALGORITHMS; CLASSIFICATION; Computer Programming and Software; DISTANT SUPERVISION; FEATURE EXTRACTION; GROUNDED LANGUAGE UNDERSTANDING; INFORMATION EXTRACTION SYSTEMS; INFORMATION PROCESSING; KNOWLEDGE BASED SYSTEMS; LEARNING MACHINES; Linguistics; MAPPING; NATURAL LANGUAGE UNDERSTANDING; OPERATING SYSTEMS(COMPUTERS); PARSERS; PROBABILITY; SEMANTIC PARSING; SEMANTICS; Statistics and Probability; STOCHASTIC PROCESSES; TEXT PROCESSING; THESES
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA624638
http://www.dtic.mil/docs/citations/ADA624638
BASE
Hide details
146
BJUT at TREC 2015 Microblog Track: Real Time Filtering Using Knowledge Base
BASE
Show details
147
Documentary Linguistics and Computational Linguistics: A response to Brooks
Bird, Steven; Chiang, David; Frowein, Friedel. - : University of Hawaii Press, 2015
BASE
Show details
148
MarsaTag
Rauzy, Stéphane Mr, CNRS - LPL. - : Laboratoire parole et langage - UMR 7309 (LPL, Aix-en-Provence FR), 2015. : http://lpl-aix.fr, 2015
BASE
Show details
149
MarsaGram
BASE
Show details
150
Some Puzzles of Politeness and Impoliteness within a Formal Semantics of Offensive Language ; Conflict and Multimodal Communication: Social Research and Machine Intelligence
VOGEL, CARL. - : Springer, 2015
BASE
Show details
151
Disfluency in Multiparty Social Talk ; Disfluency in Spontaneous Speech 2015
BASE
Show details
152
Stylochronometry: Timeline Prediction in Stylometric Analysis ; Research and Development in Intelligent Systems XXXII
VOGEL, CARL. - : Springer, 2015
BASE
Show details
153
Temporal Forces and Type Coercion in Strings ; Proceedings of the 12th International Conference on Finite-State Methods and Natural Language Processing 2015 (FSMNLP 2015)
KELLEHER, DEREK; FERNANDO, TIM; VOGEL, CARL. - : Association for Computational Linguistics, 2015
BASE
Show details
154
The discourse value of social signals at topic change moments ; Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015)
BASE
Show details
155
An unsupervised EM method to infer time variation in sense probabilities ; ICON 2015 : 12th International Conference on Natural Language Processing
EMMS, MARTIN. - 2015
BASE
Show details
156
Author verification: basic stacked generalization applied to predictions from a set of heterogeneous learners ; PAN/CLEF Evaluation Lab 2015
VOGEL, CARL. - 2015
BASE
Show details
157
A formal approach to the generation of visual language environments supporting multiple views
Guerra, Esther; Díaz, Paloma; Lara, Juan de. - : Institute of Electrical and Electronics Engineers, 2015
BASE
Show details
158
A Hedging Annotation Scheme Focused on Epistemic Phrases for Informal Language ; Proceedings of the IWCS Workshop on Models for Modality Annotation, MOMA 2015
MAMANI SANCHEZ, LILIANA PAOLA; VOGEL, CARL. - : Association for Computational Linguistics, 2015
BASE
Show details
159
Digital humanities: centres and peripheries
In: Historical Social Research ; 37 ; 3 ; 46-58 ; Kontroversen um die Digitalen Geisteswissenschaften / Controversies around the digital humanities (2015)
BASE
Show details
160
Identifying events using computer-assisted text analysis
In: Social Science Computer Review ; 26 ; 4 ; 483-497 (2015)
BASE
Show details

Page: 1...4 5 6 7 8 9 10 11 12...15

Catalogues
17
3
0
0
1
1
5
Bibliographies
21
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
256
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern