Results 1 - 10
of
238
Unsupervised namedentity extraction from the web: An experimental study.
- Artificial Intelligence,
, 2005
"... Abstract The KNOWITALL system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an unsupervised, domain-independent, and scalable manner. The paper presents an overview of KNOW-ITALL's novel architecture and ..."
Abstract
-
Cited by 372 (39 self)
- Add to MetaCart
(Show Context)
Abstract The KNOWITALL system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an unsupervised, domain-independent, and scalable manner. The paper presents an overview of KNOW-ITALL's novel architecture and design principles, emphasizing its distinctive ability to extract information without any hand-labeled training examples. In its first major run, KNOW-ITALL extracted over 50,000 class instances, but suggested a challenge: How can we improve KNOWITALL's recall and extraction rate without sacrificing precision? This paper presents three distinct ways to address this challenge and evaluates their performance. Pattern Learning learns domain-specific extraction rules, which enable additional extractions. Subclass Extraction automatically identifies sub-classes in order to boost recall (e.g., "chemist" and "biologist" are identified as sub-classes of "scientist"). List Extraction locates lists of class instances, learns a "wrapper" for each list, and extracts elements of each list. Since each method bootstraps from KNOWITALL's domain-independent methods, the methods also obviate hand-labeled training examples. The paper reports on experiments, focused on building lists of named entities, that measure the relative efficacy of each method and demonstrate their synergy. In concert, our methods gave KNOWITALL a 4-fold to 8-fold increase in recall at precision of 0.90, and discovered over 10,000 cities missing from the Tipster Gazetteer.
SWORD: A developer toolkit for web service composition
"... The formidable problem of automatic or semi-automatic composition of existing Web services is the subject of much current attention. We address a particular subset of this problem with SWORD, a set of tools for the composition of a class of web services including "information-providing" se ..."
Abstract
-
Cited by 205 (1 self)
- Add to MetaCart
The formidable problem of automatic or semi-automatic composition of existing Web services is the subject of much current attention. We address a particular subset of this problem with SWORD, a set of tools for the composition of a class of web services including "information-providing" services. In SWORD, a service is represented by a rule that expresses that given certain inputs, the service is capable of producing particular outputs. A rule-based expert system is then used to automatically determine whether a desired composite service can be realized using existing services. If so, this derivation is used to construct a plan that when executed instantiates the composite service. As our working prototype and examples demonstrate, SWORD does not require (but could benefit from) wider deployment of emerging service-description standards such as WSDL, SOAP, RDF and DAML. We also distinguish SWORD from some other plausible existing approaches, especially information integration. We show that although SWORD's expressive capabilities are weaker, the abstractions it exposes capture more appropriately the limited kinds of queries supported by typical Web services and thus result in simplicity and efficiency.
Data-Intensive Question Answering
- In Proceedings of the Tenth Text REtrieval Conference (TREC
, 2001
"... this document. There are two difficulties in finding this document in the TREC collection -- pronominal reference must be used to know that 'that month' refers to June, and the query term birthstone needs to be rewritten as birth-stone which occurs in the document. With the wealth of data ..."
Abstract
-
Cited by 171 (18 self)
- Add to MetaCart
this document. There are two difficulties in finding this document in the TREC collection -- pronominal reference must be used to know that 'that month' refers to June, and the query term birthstone needs to be rewritten as birth-stone which occurs in the document. With the wealth of data available on the Web, we can find the answer without solving either of these problems
Web Question Answering: Is More Always Better?
, 2002
"... This paper describes a question answering system that is designed to capitalize on the tremendous amount of data that is now available online. Most question answering systems use a wide variety of linguistic resources. We focus instead on the redundancy available in large corpora as an important res ..."
Abstract
-
Cited by 152 (10 self)
- Add to MetaCart
(Show Context)
This paper describes a question answering system that is designed to capitalize on the tremendous amount of data that is now available online. Most question answering systems use a wide variety of linguistic resources. We focus instead on the redundancy available in large corpora as an important resource. We use this redundancy to simplify the query rewrites that we need to use, and to support answer mining from returned snippets. Our system performs quite well given the simplicity of the techniques being utilized. Experimental results show that question answering accuracy can be greatly improved by analyzing more and more matching passages. Simple passage ranking and n-gram extraction techniques work well in our system making it efficient to use with many backend retrieval engines.
An Analysis of the AskMSR Question-Answering System
- In Proceedings of 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP
, 2002
"... We describe the architecture of the AskMSR question answering system and systematically evaluate contributions of different system components to accuracy. ..."
Abstract
-
Cited by 116 (4 self)
- Add to MetaCart
(Show Context)
We describe the architecture of the AskMSR question answering system and systematically evaluate contributions of different system components to accuracy.
Web-Scale Information Extraction in KnowItAll
, 2004
"... Manually querying search engines in order to accumulate a large body of factual information is a tedious, error-prone process of piecemeal search. Search engines retrieve and rank potentially relevant documents for human perusal, but do not extract facts, assess confidence, or fuse information from ..."
Abstract
-
Cited by 96 (6 self)
- Add to MetaCart
Manually querying search engines in order to accumulate a large body of factual information is a tedious, error-prone process of piecemeal search. Search engines retrieve and rank potentially relevant documents for human perusal, but do not extract facts, assess confidence, or fuse information from multiple documents. This paper introduces KNOWITALL, a system that aims to automate the tedious process of extracting large collections of facts from the web in an autonomous, domain-independent, and scalable manner.
Learning by googling
"... The goal of giving a well-defined meaning to information is currently shared by endeavors such as the Semantic Web as well as by current trends within Knowledge Management. They all depend on the large-scale formalization of knowledge and on the availability of formal metadata about information reso ..."
Abstract
-
Cited by 83 (3 self)
- Add to MetaCart
The goal of giving a well-defined meaning to information is currently shared by endeavors such as the Semantic Web as well as by current trends within Knowledge Management. They all depend on the large-scale formalization of knowledge and on the availability of formal metadata about information resources. However, the question how to provide the necessary formal metadata in an effective and efficient way is still not solved to a satisfactory extent. Certainly, the most effective way to provide such metadata as well as formalized knowledge is to let humans encode them directly into the system, but this is neither efficient nor feasible. Furthermore, as current social studies show, individual knowledge is often less powerful than the collective knowledge of a certain community. As a potential way out of the knowledge acquisition bottleneck, we present a novel methodology that acquires collective knowledge from the World Wide Web using the Google TM API. In particular, we present PANKOW, a concrete instantiation of this methodology which is evaluated in two experiments: one with the aim of classifying novel instances with regard to an existing ontology and one with the aim of learning sub-/superconcept relations.
Exploiting syntactic and shallow semantic kernels for question answer classification
- In Proc. of ACL-07
, 2007
"... We study the impact of syntactic and shallow semantic information in automatic classification of questions and answers and answer re-ranking. We define (a) new tree structures based on shallow semantics encoded in Predicate Argument Structures (PASs) and (b) new kernel functions to exploit the repre ..."
Abstract
-
Cited by 76 (30 self)
- Add to MetaCart
(Show Context)
We study the impact of syntactic and shallow semantic information in automatic classification of questions and answers and answer re-ranking. We define (a) new tree structures based on shallow semantics encoded in Predicate Argument Structures (PASs) and (b) new kernel functions to exploit the representational power of such structures with Support Vector Machines. Our experiments suggest that syntactic information helps tasks such as question/answer classification and that shallow semantics gives remarkable contribution when a reliable set of PASs can be extracted, e.g. from answers. 1
Methods for domain-independent information extraction from the web: an experimental comparison
- in: Proceedings of the Nineteenth National Conference on Artificial Intelligence, AAAI
"... Our KNOWITALL system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an autonomous, domain-independent, and scalable manner. In its first major run, KNOWITALL extracted over 50,000 facts with high precision, but ..."
Abstract
-
Cited by 72 (11 self)
- Add to MetaCart
Our KNOWITALL system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an autonomous, domain-independent, and scalable manner. In its first major run, KNOWITALL extracted over 50,000 facts with high precision, but suggested a challenge: How can we improve KNOWITALL’s recall and extraction rate without sacrificing precision? This paper presents three distinct ways to address this challenge and evaluates their performance. Rule Learning learns domain-specific extraction rules. Subclass Extraction automatically identifies sub-classes in order to boost recall. List Extraction locates lists of class instances, learns a “wrapper ” for each list, and extracts elements of each list. Since each method bootstraps from KNOWITALL’s domain-independent methods, no hand-labeled training examples are required. Experiments show the relative coverage of each method and demonstrate their synergy. In concert, our methods gave KNOWITALL a 4-fold to 19-fold increase in recall, while maintaining high precision, and discovered 10,300 cities missing from the Tipster Gazetteer. 1.
