Open Access. Powered by Scholars. Published by Universities.®
Social and Behavioral Sciences Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Active learning (1)
- Alpnet (1)
- Ambiguity (1)
- Analogical modeling (1)
- Automated Language Processing Systems (ALPS) (1)
-
- Automated ontology generation (1)
- Book of Mormon (1)
- Cognitive robotics (1)
- Exemplar-based approach (1)
- First vision (1)
- Grammar (1)
- Joseph Smith (1)
- Language modeling and machine learning approaches (1)
- Learning (1)
- Linguistic behavior prediction (1)
- Machine learning community (1)
- Machine translation (MT) (1)
- Maximum Entropy Markov Model tagger (1)
- Natural language (1)
- Natural language web pages (1)
- Ontology engineering (1)
- Ontology reuse (1)
- Part-of-speech annotated corpus (1)
- Query by Committee (QBC) (1)
- Query by Uncertainty (QBU) (1)
- Review (1)
- Semantic Web ontologies (1)
- Teaching (1)
- Translation Sciences Institute (TSI) (1)
- Utah Valley (1)
Articles 1 - 7 of 7
Full-Text Articles in Social and Behavioral Sciences
From Alps To Alpnet (And Beyond), Deryle W. Lonsdale
From Alps To Alpnet (And Beyond), Deryle W. Lonsdale
Faculty Publications
Nestled in the Wasatch range of the Rocky Mountains in northern Utah lies scenic Utah Valley. Home to Brigham Young University (BYU) and a host of foreign-speaking residents, the setting also served as a hotbed throughout the 1980's for the machine translation (MT) industry. To fully appreciate this narrative the chronologically prior story of BYU's Translation Sciences Institute (TSI)—which has not yet been written— would need to be consulted. When the Church1 withdrew funding for the project, the TSI team disbanded. Some former participants remained at BYU, others left the university to work for industrial corporations, and the majority remained …
Turning Away, Jacob D. Rawlins
Turning Away, Jacob D. Rawlins
Faculty Publications
From the time of Joseph Smith’s first vision, the concepts of general apostasy and divine restoration have been central to the Latter-day Saint movement. In the Prophet’s account of his vision, he records that after he asked which church he should join, “I was answered that I must join none of them, for they were all wrong; and the Personage who addressed me said that all their creeds were an abomination in his sight; that those professors were all corrupt; that: ‘they draw near to me with their lips, but their hearts are far from me, they teach for doctrines …
Generating Ontologies Via Language Components And Ontology Reuse, Deryle W. Lonsdale, Yihong Ding, David W. Embley, Martin Hepp, Li Xu
Generating Ontologies Via Language Components And Ontology Reuse, Deryle W. Lonsdale, Yihong Ding, David W. Embley, Martin Hepp, Li Xu
Faculty Publications
Realizing the Semantic Web involves creating ontologies, a tedious and costly challenge. Reuse can reduce the cost of ontology engineering. Semantic Web ontologies can provide useful input for ontology reuse. However, the automated reuse of such ontologies remains underexplored. This paper presents a generic architecture for automated ontology reuse. With our implementation of this architecture, we show the practicality of automating ontology generation through ontology reuse. We experimented with a large generic ontology as a basis for automatically generating domain ontologies that fit the scope of sample natural-language web pages. The results were encouraging, resulting in five lessons pertinent to …
Structural Ambiguity Collecting As A Tool For Teaching Grammar, Dallin D. Oaks
Structural Ambiguity Collecting As A Tool For Teaching Grammar, Dallin D. Oaks
Faculty Publications
Structural ambiguities can be a valuable resource for grammar students. Because structural ambiguities present more than one possible grammatical interpretation, authentic examples of such ambiguities lend themselves well to meaningful grammatical discussions. One particularly useful way for involving students in the recognition and analysis of structural ambiguities is to assign them to find designated ambiguity types. This paper will consider some benefits of structural ambiguity study and will provide some ideas and suggestions related to a specific type of assignment that involves students in collecting structural ambiguities.
Active Learning For Part-Of-Speech Tagging: Accelerating Corpus Annotation, Deryle W. Lonsdale, Eric K. Ringger, Peter J. Mcclanahan, Robbie A. Haertel, George Busby, Marc A. Carmen, James Carroll, Kevin Seppi
Active Learning For Part-Of-Speech Tagging: Accelerating Corpus Annotation, Deryle W. Lonsdale, Eric K. Ringger, Peter J. Mcclanahan, Robbie A. Haertel, George Busby, Marc A. Carmen, James Carroll, Kevin Seppi
Faculty Publications
In the construction of a part-of-speech annotated corpus, we are constrained by a fixed budget. A fully annotated corpus is required, but we can afford to label only a subset. We train a Maximum Entropy Markov Model tagger from a labeled subset and automatically tag the remainder. This paper addresses the question of where to focus our manual tagging efforts in order to deliver an annotation of highest quality. In this context, we find that active learning is always helpful. We focus on Query by Uncertainty (QBU) and Query by Committee (QBC) and report on experiments with several baselines and …
Analogical Modeling: An Update, Deryle W. Lonsdale, David Eddington
Analogical Modeling: An Update, Deryle W. Lonsdale, David Eddington
Faculty Publications
Analogical modeling is a supervised exemplar-based approach that has been widely applied to predict linguistic behavior. The paradigm has been well documented in the linguistics and cognition literature, but is less well known to the machine learning community. This paper sets out some of the basics of the approach, including a simplified example of the fundamental algorithm’s operation. It then surveys some of the recent analogical modeling language applications, and sketches how the computational system has been enhanced lately to offer users increased flexibility and processing power. Some comparisons and contrasts are drawn between analogical modeling and other language modeling …
A Cognitive Robotics Approach To Comprehending Human Language And Behaviors, Deryle W. Lonsdale, D. Paul Benjamin, Damian Lyons
A Cognitive Robotics Approach To Comprehending Human Language And Behaviors, Deryle W. Lonsdale, D. Paul Benjamin, Damian Lyons
Faculty Publications
The ADAPT project is a collaboration of researchers in linguistics, robotics and artificial intelligence at three universities. We are building a complete robotic cognitive architecture for a mobile robot designed to interact with humans in a range of environments, and which uses natural language and models human behavior. This paper concentrates on the HRI aspects of ADAPT, and especially on how ADAPT models and interacts with humans.