Language:

Relational retrieval using a combination of path-constrained random walks

Machine learning, 2010-10, Vol.81 (1), p.53-67 [Peer Reviewed Journal]

The Author(s) 2010 ;2015 INIST-CNRS ;ISSN: 0885-6125 ;EISSN: 1573-0565 ;DOI: 10.1007/s10994-010-5205-8

Full text available

Citations Cited by

Actions
1. Add to My Research
2. Remove from My Research
3. E-mail
4. Print
5. Permalink
6. Citation
7. EasyBib
8. EndNote
9. RefWorks
10. Delicious
11. Export RIS
12. Export BibTeX

Title:
Relational retrieval using a combination of path-constrained random walks
Author: Lao, Ni ; Cohen, William W.
Subjects: Algorithms ; Applied sciences ; Artificial Intelligence ; Combinatorics ; Combinatorics. Ordered structures ; Computer Science ; Computer science; control theory; systems ; Control ; Exact sciences and technology ; Graph theory ; Graphs ; Information retrieval ; Information retrieval. Graph ; Information systems. Data bases ; Mathematics ; Mechatronics ; Memory organisation. Data processing ; Metadata ; Natural Language Processing (NLP) ; Random walk theory ; Robotics ; Sciences and techniques of general use ; Simulation and Modeling ; Software ; Speech and sound recognition and synthesis. Linguistics ; Theoretical computing
Is Part Of: Machine learning, 2010-10, Vol.81 (1), p.53-67
Description: Scientific literature with rich metadata can be represented as a labeled directed graph. This graph representation enables a number of scientific tasks such as ad hoc retrieval or named entity recognition (NER) to be formulated as typed proximity queries in the graph. One popular proximity measure is called Random Walk with Restart (RWR), and much work has been done on the supervised learning of RWR measures by associating each edge label with a parameter. In this paper, we describe a novel learnable proximity measure which instead uses one weight per edge label sequence : proximity is defined by a weighted combination of simple “path experts”, each corresponding to following a particular sequence of labeled edges. Experiments on eight tasks in two subdomains of biology show that the new learning method significantly outperforms the RWR model (both trained and untrained). We also extend the method to support two additional types of experts to model intrinsic properties of entities: query-independent experts , which generalize the PageRank measure, and popular entity experts which allow rankings to be adjusted for particular entities that are especially important.
Publisher: Boston: Springer US
Language: English
Identifier: ISSN: 0885-6125
EISSN: 1573-0565
DOI: 10.1007/s10994-010-5205-8
Source: Alma/SFX Local Collection
ProQuest Central

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Relational retrieval using a combination of path-constrained random walks

The Author(s) 2010 ;2015 INIST-CNRS ;ISSN: 0885-6125 ;EISSN: 1573-0565 ;DOI: 10.1007/s10994-010-5205-8

Searching Remote Databases, Please Wait