Results 1 - 10 of 1,310

An Algorithm that Learns What's in a Name

by Daniel M. Bikel, Richard Schwartz, Ralph M. Weischedel , 1999
"... In this paper, we present IdentiFinder^TM, a hidden Markov model that learns to recognize and classify names, dates, times, and numerical quantities. We have evaluated the model in English (based on data from the Sixth and Seventh Message Understanding Conferences [MUC-6, MUC-7] and broadcast news) ..."
Abstract - Cited by 372 (7 self) - Add to MetaCart
) and in Spanish (based on data distributed through the First Multilingual Entity Task [MET-1]), and on speech input (based on broadcast news). We report results here on standard materials only to quantify performance on data available to the community, namely, MUC-6 and MET-1. Results have been consistently

Unsupervised Models for Named Entity Classification

by Michael Collins, Yoram Singer - In Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora , 1999
"... This paper discusses the use of unlabeled examples for the problem of named entity classification. A large number of rules is needed for coverage of the domain, suggesting that a fairly large number of labeled examples should be required to train a classifier. However, we show that the use of unlabe ..."
Abstract - Cited by 542 (4 self) - Add to MetaCart
algorithms. The first method uses a similar algorithm to that of (Yarowsky 95), with modifications motivated by (Blum and Mitchell 98). The second algorithm extends ideas from boosting algorithms, designed for supervised learning tasks, to the framework suggested by (Blum and Mitchell 98). 1

1.1. The Named Entity Task

by Daniel M. Bikel, Richard Schwartz, Ralph M. Weischedel
"... Abstract. In this paper, we present IdentiFinder™, a hidden Markov model that learns to recognize and classify names, dates, times, and numerical quantities. We have evaluated the model in English (based on data from the Sixth and Seventh Message Understanding Conferences [MUC-6, MUC-7] and broadcas ..."
Abstract - Add to MetaCart
] and broadcast news) and in Spanish (based on data distributed through the First Multilingual Entity Task [MET-1]), and on speech input (based on broadcast news). We report results here on standard materials only to quantify performance on data available to the community, namely, MUC-6 and MET-1. Results have

A learning algorithm for Boltzmann machines

by H. Ackley, E. Hinton, J. Sejnowski - Cognitive Science , 1985
"... The computotionol power of massively parallel networks of simple processing elements resides in the communication bandwidth provided by the hardware connections between elements. These connections con allow a significant fraction of the knowledge of the system to be applied to an instance of a probl ..."
Abstract - Cited by 584 (13 self) - Add to MetaCart
problem in o very short time. One kind of computation for which massively porollel networks appear to be well suited is large constraint satisfaction searches, but to use the connections efficiently two conditions must be met: First, a search technique that is suitable for parallel networks must be found

Discriminative probabilistic models for relational data

by Ben Taskar , 2002
"... In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A standard approach is to classify each entity independently, igno ..."
Abstract - Cited by 415 (12 self) - Add to MetaCart
In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A standard approach is to classify each entity independently

A Machine Learning Approach to Coreference Resolution of Noun Phrases

by Wee Meng Soon, Daniel Chung, Daniel Chung Yong Lim, Yong Lim, Hwee Tou Ng , 2001
"... this paper, we present a learning approach to coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just a certain type of noun phrase (e.g., pronouns) but rather general noun phrases. It also does not rest ..."
Abstract - Cited by 270 (3 self) - Add to MetaCart
that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Our system is the first learning-based system that offers performance comparable to that of state-of-the-art nonlearning systems on these data sets

Aura: an architectural framework for user mobility in ubiquitous computing environments

by João Pedro Sousa, David Garlan, Key Words - In Proceedings of the 3rd Working IEEE/IFIP Conference on Software Architecture , 2002
"... Ubiquitous computing poses a number of challenges for software architecture. One of the most important is the ability to design software systems that accommodate dynamically-changing resources. Resource variability arises naturally in a ubiquitous computing setting through user mobility (a user move ..."
Abstract - Cited by 248 (3 self) - Add to MetaCart
. We argue that those approaches are inadequate, and describe an alternative architectural framework that is better matched to the needs of ubiquitous computing. A key feature of the architecture is that user tasks become first class entities. User proxies, or Auras, use models of user tasks to set up

A statistical model for multilingual entity detection and tracking

by R. Florian, H. Hassan, A. Ittycheriah, H. Jing, N. Kambhatla, X. Luo, N. Nicolov, S. Roukos - In NAACL/HLT , 2004
"... Entity detection and tracking is a relatively new addition to the repertoire of natural language tasks. In this paper, we present a statistical language-independent framework for identifying and tracking named, nominal and pronominal references to entities within unrestricted text documents, and cha ..."
Abstract - Cited by 87 (15 self) - Add to MetaCart
Entity detection and tracking is a relatively new addition to the repertoire of natural language tasks. In this paper, we present a statistical language-independent framework for identifying and tracking named, nominal and pronominal references to entities within unrestricted text documents

Multilingual word sense disambiguation and entity linking for everybody

by Andrea Moro, Francesco Cecconi, Roberto Navigli - In Proceedings of the 13th Internation Conference on Semantic Web (P&D , 2014
"... Abstract. In this paper we present a Web interface and a RESTful API for our state-of-the-art multilingual word sense disambiguation and en-tity linking system. The Web interface has been developed, on the one hand, to be user-friendly for non-specialized users, who can thus easily obtain a first gr ..."
Abstract - Cited by 4 (0 self) - Add to MetaCart
Abstract. In this paper we present a Web interface and a RESTful API for our state-of-the-art multilingual word sense disambiguation and en-tity linking system. The Web interface has been developed, on the one hand, to be user-friendly for non-specialized users, who can thus easily obtain a first

An Efficient Domain-Independent Algorithm for Detecting Approximately Duplicate Database Records

by Alvaro Monge, Charles Elkan , 1997
"... Detecting database records that are approximate duplicates, but not exact duplicates, is an important task. Databases may contain duplicate records concerning the same realworld entity because of data entry errors, because of unstandardized abbreviations, or because of differences in the detailed sc ..."
Abstract - Cited by 215 (2 self) - Add to MetaCart
Detecting database records that are approximate duplicates, but not exact duplicates, is an important task. Databases may contain duplicate records concerning the same realworld entity because of data entry errors, because of unstandardized abbreviations, or because of differences in the detailed
Results 1 - 10 of 1,310