A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval
2018
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Preserved Fulltext
The semantics from knowledge graphs are integrated in the distributed representations of their entities, while the ranking is conducted by interaction-based neural ranking networks. ...
This paper presents the Entity-Duet Neural Ranking Model (EDRM), which introduces knowledge graphs to neural search systems. ...
We thank Sogou for providing access to the search log. ...
doi:10.18653/v1/p18-1223
dblp:conf/acl/SunLXL18
fatcat:uoal5wyyzvhylgahyrnisfltpi
Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The semantics from knowledge graphs are integrated in the distributed representations of their entities, while the ranking is conducted by interaction-based neural ranking networks. ...
The two components are learned end-to-end, making EDRM a natural combination of entity-oriented search and neural information retrieval. ...
We thank Sogou for providing access to the search log. ...
arXiv:1805.07591v2
fatcat:ns3hh65qhbbmvfmku6nm4ky6d4
Reliable Knowledge Graph Path Representation Learning
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
A promising approach for this task is a knowledge graph representation learning, which aims to represent entities and relations into low-dimensional vector spaces. ...
Specifically, we combine the representations of intermediate entities and relations on relation paths to learn more meaningful knowledge representations. ...
TKRL [38] takes hierarchical entity types into considerations and makes projection matrices for entities with type encoders. ...
doi:10.1109/access.2020.2973923
fatcat:ux3lx3quwbcithpzwqtendqssu
Learning to Rank Target Types for Entity-Bearing Queries
2017
International Conference on the Theory of Information Retrieval
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
is paper revisits the learning-to-rank approach we proposed for automatically identifying the target entity types of queries [6] . ...
Alternatively, a type-centric model presented in [2] ranks direct term-based representations (pseudo type description documents), built for each type, by aggregating descriptions of entities ...
Our experiments were performed using Nordlys [7] , a toolkit for entity-oriented and semantic search. We employed the Random Forest algorithm for regression as the supervised ranking method. ...
dblp:conf/ictir/GarigliottiB17a
fatcat:xsvr6nq4a5b63pjifmwepfgneq
Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper we explore the problem of making predictions for entities or entity-pairs unseen at training time (and hence without a pre-learned row embedding). ...
Factorizing this sparsely observed matrix yields a learned vector embedding for each row and each column. ...
Arvind Neelakantan is supported by a Google PhD fellowship in machine learning. ...
arXiv:1606.05804v2
fatcat:xcvaurhnsnau5jihsy262wseqi
Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema
2017
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper we explore the problem of making predictions for entities or entity-pairs unseen at training time (and hence without a pre-learned row embedding). ...
Factorizing this sparsely observed matrix yields a learned vector embedding for each row and each column. ...
Arvind Neelakantan is supported by a Google PhD fellowship in machine learning. ...
doi:10.18653/v1/e17-1058
dblp:conf/eacl/McCallumNV17
fatcat:3wbt6jj5ljbhbld6vr2gq67gha
Rule-Guided Compositional Representation Learning on Knowledge Graphs with Hierarchical Types
2021
Mathematics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
information, and logic rules information for representation learning. ...
Since entities have different types of representations in different scenarios, the rich information in the types of entity levels is helpful for obtaining a more complete knowledge representation. ...
entities have different type representations. ...
doi:10.3390/math9161978
fatcat:lhisjpmn6jcxbe7gxqlx3upjj4
Explore Entity Embedding Effectiveness in Entity Retrieval
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our experiments demonstrate the effectiveness of entity embedding based model, which achieves more than 5\% improvement than the previous state-of-the-art learning to rank based entity retrieval model. ...
query related entities and candidate entities for entity retrieval. ...
The learning to rank models is utilized to combine all exact match features and entity soft match feature for the ranking score. ...
arXiv:1908.10554v1
fatcat:zepi5ixl3bfgfnqz5zriodjhtq
A Trio Neural Model for Dynamic Entity Relatedness Ranking
2018
Proceedings of the 22nd Conference on Computational Natural Language Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our model is capable of learning rich and different entity representations in a joint framework. ...
Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. ...
We thank the reviewers for the suggestions on the content and structure of the paper. ...
doi:10.18653/v1/k18-1004
dblp:conf/conll/NguyenTN18
fatcat:liasz2zhpnbnjmqh5dculu4lfa
Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We explore novel machine learning approaches for answering visual-relational queries in web-extracted knowledge graphs. ...
The resulting multi-relational grounding of unseen entity images into a knowledge graph serves as a semantic entity representation. ...
We proposed several novel query types and introduce neural architectures suitable for probabilistic query answering. ...
arXiv:1709.02314v6
fatcat:txfttbx3prch7iflks3wvmkr74
Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The entity converter is designed to transform the entities along paths into the representations in the semantic level similar to relations for reducing the heterogeneity between entities and relations, ...
in which the KGs both with and without type information are considered. ...
KG and learn the distributed representations for entities and relations. ...
arXiv:2010.02602v1
fatcat:7n2rrv3xared5gd62vipfegota
Row-less Universal Schema
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Instead of learning vector representations for each entity pair in our training set, we treat an entity pair as a function of its relation types. ...
types. ...
This work was supported in part by the Center for Intelligent Information Retrieval and the Center for Data Science, in part by The Allen Institute for Artificial Intelligence, and in part by DARPA under ...
arXiv:1604.06361v1
fatcat:vaepmlgbkzc7hlchvfwloddxpm
Row-less Universal Schema
2016
Proceedings of the 5th Workshop on Automated Knowledge Base Construction
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Instead of learning vector representations for each entity pair in our training set, we treat an entity pair as a function of its relation types. ...
types. ...
Acknowledgments We thank Emma Strubell, David Belanger, Luke Vilnis, and Arvind Neelakantan for helpful discussions and edits. ...
doi:10.18653/v1/w16-1312
dblp:conf/akbc/VergaM16
fatcat:v5qt5blwkrguhnvxvrprfc6vga
A Trio Neural Model for Dynamic Entity Relatedness Ranking
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our model is capable of learning rich and different entity representations in a joint framework. ...
Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. ...
We thank the reviewers for the suggestions on the content and structure of the paper. ...
arXiv:1808.08316v3
fatcat:byi3hqroqbbgxmzd2pwha7sdve
Dynamic Collective Entity Representations for Entity Ranking
2016
Proceedings of the Ninth ACM International Conference on Web Search and Data Mining - WSDM '16
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Dynamic collective entity representations for entity ranking Graus, D.P.; Tsagkias, E.; Weerkamp, W.; Meij, E.J.; de Rijke, M. ...
Periodic retraining of the ranker enables higher ranking effectiveness for dynamic collective entity representations. ...
Machine learning We apply machine learning for learning how to weight the different fields that make up an entity representation for optimal retrieval effectiveness. ...
doi:10.1145/2835776.2835819
dblp:conf/wsdm/GrausTWMR16
fatcat:ag72bi6djfembnfuzb2wcpldri
« Previous
Showing results 1 — 15 out of 104,734 results