While gazetteers can be used to perform named entity recognition through lookup-based methods, ambiguity and incomplete gazetteers lead to relatively low recall. A sequence model which uses more general features can a...
详细信息
ISBN:
(纸本)9781577354147
While gazetteers can be used to perform named entity recognition through lookup-based methods, ambiguity and incomplete gazetteers lead to relatively low recall. A sequence model which uses more general features can achieve higher recall while maintaining reasonable precision, but typically requires expensive annotated training data. To circumvent the need for such training data, we bootstrap the learning of a sequence model with a gazetteer-driven labeling algorithm which only labels tokens in unlabeled data that it can label confidently. We present an algorithm, called the Partial Perceptron, for discriminatively learning the parameters of a sequence model from such partially labeled data. The algorithm is easy to implement and trains much more quickly than a state-of-the-art algorithm based on Conditional Random Fields with equivalent performance. Experimental results show that the learned model yields a substantial relative improvement in recall (77.3%) with some loss in precision (a 28.7% relative decrease) when compared to the gazetteer-driven method.
The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, was pleased to present the 2009 springsymposium Series, held Monday throug...
详细信息
The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, was pleased to present the 2009 springsymposium Series, held Monday through Wednesday, March 23-25, 2009, at Stanford University. The titles of the nine symposia were Agents That Learn from Human Teachers, Benchmarking of Qualitative Spatial and Temporal Reasoning Systems, Experimental Design for Real- World Systems, Human Behavior Modeling, Intelligent Event Processing, Intelligent Narrative Technologies II, learning by reading and learning to read, Social Semantic Web: Where Web 2.0 Meets Web 3.0, and Technosocial Predictive Analytics. The goal of the Agents That Learn from Human Teachers symposium was to investigate how we can enable software and robotics agents to leam from real-time interaction with an everyday human partner. The aim of the Benchmarking of Qualitative Spatial and Temporal Reasoning Systems symposium was to initiate the development of a problem repository in the field of qualitative spatial and temporal reasoning and identify a graded set of challenges for future midterm and long-term research. The Experimental Design symposium discussed the challenges of evaluating AI systems. The Human Behavior Modeling symposium explored reasoning methods for understanding various aspects of human behavior, especially in the context of designing intelligent systems that interact with humans. The Intelligent Event Processing symposium discussed the need for more Al-based approaches in event pro-cessing and defined a kind of research agenda for the field, coined as intelligent complex event processing (iCEP). The Intelligent Narrative Technologies IIaaaisymposium discussed innovations, progress, and novel techniques in the research domain. The learning by reading and learning to readsymposium explored two aspects of making natural language texts semantically accessible to, and processable by, machines. The Social Semantic
The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, was pleased to present the 2009 springsymposium Series, held Monday throug...
The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, was pleased to present the 2009 springsymposium Series, held Monday through Wednesday, March 23-25, 2009, at Stanford University. The titles of the nine symposia were Agents That Learn from Human Teachers, Benchmarking of Qualitative Spatial and Temporal Reasoning Systems, Experimental Design for Real-World Systems, Human Behavior Modeling, Intelligent Event Processing, Intelligent Narrative Technologies II, learning by reading and learning to read, Social Semantic Web: Where Web 2.0 Meets Web 3.0, and Technosocial Predictive Analytics. The goal of the Agents That Learn from Human Teachers symposium was to investigate how we can enable software and robotics agents to learn from real-time interaction with an everyday human partner. The aim of the Benchmarking of Qualitative Spatial and Temporal Reasoning Systems symposium was to initiate the development of a problem repository in the field of qualitative spatial and temporal reasoning and identify a graded set of challenges for future midterm and long-term research. The Experimental Design symposium discussed the challenges of evaluating AI systems. The Human Behavior Modeling symposium explored reasoning methods for understanding various aspects of human behavior, especially in the context of designing intelligent systems that interact with humans. The Intelligent Event Processing symposium discussed the need for more AI-based approaches in event processing and defined a kind of research agenda for the field, coined as intelligent complex event processing (iCEP). The Intelligent Narrative Technologies II aaaisymposium discussed innovations, progress, and novel techniques in the research domain. The learning by reading and learning to readsymposium explored two aspects of making natural language texts semantically accessible to, and processable by, machines. The Social Semantic
The proceedings contain 14 papers. The topics discussed include: machine reading;inference in text understanding;semantic integration in learningfrom text;reporting on some logic-based machine reading research;readin...
详细信息
ISBN:
(纸本)9781577353157
The proceedings contain 14 papers. The topics discussed include: machine reading;inference in text understanding;semantic integration in learningfrom text;reporting on some logic-based machine reading research;reading to learn: an investigation into language understanding;robust graph alignment methods for textual inference and machine reading;ontology learningfrom text using automatic ontological-semantic text annotation and the Web as the corpus;a prototype system that learns by reading simplified texts;machine reading as a cognitive science research instrument;machine reading through textual and knowledge entailment;using episodic memory in a memory based parser to assist machine reading;building knowledge base for readingfrom encyclopedia;moving from textual relations to ontologized relations;and answering and questioning for machine reading.
Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes learningreader, a prototype system that extends its knowledge base by reading. learning...
详细信息
ISBN:
(纸本)9781577353157
Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes learningreader, a prototype system that extends its knowledge base by reading. learningreader consists of three components. The reader, which converts text into formally represented cases, uses a Direct Memory Access Parser operating over a large knowledge base, derived from ResearchCyc. The Q/A system, which provides a means of quizzing the system on what it has learned, uses focused sets of axioms automatically extracted from the knowledge base for tractability. The Ruminator, which attempts to improve the system's understanding of what it has read by off-line processing, generates questions for itself by several means, including analogies with prior material and automatically constructed generalizations from examples in the KB and its prior reading. We discuss the architecture of the system, how each component works, and some experimental results.
This paper concerns learning information by reading natural language texts. The major aim is to develop representations that are understandable by a reasoning engine and can be used to answer questions. We use abducti...
详细信息
We describe how we are using natural language techniques to develop systems that can automatically encode a range of input materials for cognitive simulations. We start by summarizing this type of problem, and the com...
详细信息
This paper presents our work on textual inference and situates it within the context of the larger goals of machine reading. The textual inference task is to determine if the meaning of one text can be inferred from t...
详细信息
暂无评论