Marius Pasca
Authored Publications
Google Publications
Other Publications
Sort By
Interpreting Open-Domain Modifiers: Decomposition of Wikipedia Categories into Disambiguated Property-Value Pairs
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP-2020), 6218–6228
Preview abstract
This paper proposes an open-domain method for automatically annotating modifier constituents (20th-century) within Wikipedia categories (20th-century male writers) with properties (date of birth). The annotations offer a semantically-anchored understanding of the role of the constituents in defining the underlying meaning of the categories. In experiments over an evaluation set of Wikipedia categories, the proposed method annotates constituent modifiers as semantically-anchored properties, rather than as mere strings in a previous method. It does so at a better trade-off between precision and recall.
View details
Lightweight Lexical and Semantic Evidence for Detecting Classes Among Wikipedia Articles
Preview
Travis Wolfe
Proceedings of the 12h International Conference on Web Search and Data Mining (WSDM-2019), Melbourne, Australia, pp. 78-86
Finding Needles in an Encyclopedic Haystack: Detecting Classes Among Wikipedia Articles
Preview
Proceedings of the 27th World Wide Web Conference (The 2018 Web Conference) (WWW-2018), Lyon, France, pp. 1267-1276
German Typographers vs. German Grammar: Decomposition of Wikipedia Category Labels into Attribute-Value Pairs
Preview
Proceedings of the 10th International Conference on Web Search and Data Mining (WSDM-2017), Cambridge, United Kingdom, pp. 315-324
Identifying 1950s American Jazz Musicians: Fine-Grained IsA Extraction via Modifier Composition
Preview
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL-2017), Vancouver, Canada, pp. 2099-2109
Revisiting Taxonomy Induction over Wikipedia
Preview
Amit Gupta
Francesco Piccinno
Proceedings of the 26th International Conference on Computational Linguistics (COLING-2016), Osaka, Japan, pp. 2300-2309
Dissecting German Grammar and Swiss Passports: Open-Domain Decomposition of Compositional Entries in Large-Scale Knowledge Repositories
Preview
Hylke Buisman
Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI-2015), Buenos Aires, Argentina, pp. 896-902
Interpreting Compound Noun Phrases Using Web Search Queries
Preview
Proceedings of the 2015 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-2015), Denver, Colorado, pp. 335-344
Acquisition of Open-Domain Classes via Intersective Semantics
Preview
Proceedings of the 23rd International World Wide Web Conference (WWW-2014), Seoul, Korea, pp. 551-562
Acquisition of Noncontiguous Class Attributes from Web Search Queries
Preview
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2014), Gothenburg, Sweden, pp. 386-394
Queries as a Source of Lexicalized Commonsense Knowledge
Preview
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2014), Doha, Qatar, pp. 1081-1091
Open-Domain Fine-Grained Class Extraction from Web Search Queries
Preview
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2013), Seattle, Washington, pp. 403-414
Attribute Extraction from Conjectural Queries
Preview
Proceedings of the 24th International Conference on Computational Linguistics (COLING-2012), Mumbai, India, pp. 2177-2190
Instance-Driven Attachment of Semantic Annotations over Conceptual Hierarchies
Preview
Janara Christensen
Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2012), Avignon, France, pp. 503-513
Asking What No One Has Asked Before: Using Phrase Similarities to Generate Synthetic Web Search Queries
Preview
Proceedings of the 20th ACM Conference on Information and Knowledge Management (CIKM-2011), ACM, Glasgow, Scotland, pp. 1347-1352
Fine-Grained Class Label Markup of Search Queries
Preview
Joseph Reisinger
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL-2011), Portland, Oregon, pp. 1200-1209
Ranking Class Labels Using Query Sessions
Preview
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL-2011), Portland, Oregon, pp. 1607-1615
Recovering Semantics of Tables on the Web
Preview
Petros Venetis
Alon Y. Halevy
Warren Shen
Fei Wu
Gengxin Miao
Proceedings of the VLDB Endowment, vol. 4 (2011), pp. 528-538
The Role of Queries in Ranking Labeled Instances Extracted from Text
Preview
Proceedings of the 23rd International Conference on Computational Linguistics (COLING-2010), pp. 955-962
The Role of Query Sessions in Extracting Instance Attributes from Web Search Queries
Preview
Enrique Robledo-Arnuncio
Ricardo Martin-Brualla
Keith Hall
Proceedings of the 32nd European Conference on Information Retrieval (ECIR-2010), Milton Keynes, United Kingdom, pp. 62-74
Acquisition of Instance Attributes via Labeled and Related Instances
Preview
Enrique Robledo-Arnuncio
Proceedings of the 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-2010), Geneva, Switzerland, pp. 58-65
Finding Meaning on YouTube: Tag Recommendation and Category Discovery
Computer Vision and Pattern Recognition, IEEE (2010)
Preview abstract
We present a system that automatically recommends tags for YouTube
videos solely based on their audiovisual content. We also propose a novel framework
for unsupervised discovery of video categories that exploits knowledge mined
from the World-Wide Web text documents/searches. First, video content to tag
association is learned by training classifiers that map audiovisual
content-based features from millions of videos on YouTube.com to existing
uploader-supplied tags for these videos. When a new video is uploaded, the
labels provided by these classifiers are used to automatically suggest tags
deemed relevant to the video. Our system has learned a vocabulary of over 20,000 tags.
Secondly, we mined large volumes of Web pages and search queries to discover a
set of possible text entity categories and a set of associated is-A
relationships that map individual text entities to categories. Finally, we
apply these is-A relationships mined from web text on the tags learned from
audiovisual content of videos to automatically synthesize a reliable set of
categories most relevant to videos -- along with a mechanism to predict these
categories for new uploads. We then present rigorous rating studies that
establish that: (a) the average relevance of tags automatically recommended by
our system matches the average relevance of the uploader-supplied tags at the
same or better coverage and (b) the average precision@K of video categories
discovered by our system is 70% with K=5.
View details
Latent Variable Models of Concept-Attribute Attachment
Preview
Joseph Reisinger
Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics (ACL-IJCNLP-2009), Singapore, pp. 620-628
Web-Derived Resources for Web Information Retrieval: From Conceptual Hierarchies to Attribute Hierarchies
Preview
Proceedings of the 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-2009), Boston, Massachusetts, pp. 596-603
A Study on Similarity and Relatedness Using Distributional and WordNet-based Approaches
Preview
Eneko Agirre
Keith Hall
Jana Kravalova
Aitor Soroa
Proceedings of the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL-2009), Boulder, Colorado, pp. 19-27
Low-Cost Supervision for Multiple-Source Attribute Extraction
Preview
Joseph Reisinger
Proceedings of the 10th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing-2009), Mexico City, Mexico, pp. 382-393
Outclassing Wikipedia in Open-Domain Information Extraction: Weakly-Supervised Acquisition of Attributes over Conceptual Hierarchies
Preview
Proceedings of the 12th Conference of the European Chapter of the Association of Computational Linguistics (EACL-2009), Athens, Greece, pp. 639-647
Answering Definition Questions via Temporally-Anchored Text Snippets
Preview
Proceedings of the 3rd International Joint Conference on Natural Language Processing (IJCNLP-2008), Hyderabad, India, pp. 411-417
Finding Cars, Goddesses and Enzymes: Parametrizable Acquisition of Labeled Instances for Open-Domain Information Extraction
Preview
Benjamin Van Durme
Proceedings of the 23rd Annual Conference on Artificial Intelligence (AAAI-2008), Chicago, Illinois, pp. 1243-1248
Mining Parenthetical Translations from the Web by Word Alignment
Preview
Dekang Lin
Shaojun Zhao
Benjamin Van Durme
Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-2008), Columbus, Ohio, pp. 994-1002
Turning Web Text and Search Queries into Factual Knowledge: Hierarchical Class Attribute Extraction
Preview
Proceedings of the 23rd Annual Conference on Artificial Intelligence (AAAI-2008), address = {Chicago, Illinois}, pp. 1225-1230
Towards Temporal Web Search
Preview
Proceedings of the 23rd ACM Symposium on Applied Computing (SAC-2008), Fortaleza, Brazil, pp. 1117-1121
Using Structured Text for Large-Scale Attribute Extraction
Preview
Sujith Ravi
Proceedings of the 17th ACM Conference on Information and Knowledge Management (CIKM-2008), pp. 1183-1192
Weakly-Supervised Acquisition of Open-Domain Classes and Class Attributes from Web Documents and Query Logs
Preview
Benjamin Van Durme
Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-2008), pp. 19-27
Weakly-Supervised Acquisition of Labeled Class Instances using Graph Random Walks
Preview
Joseph Reisinger
Rahul Bhagat
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2008), Association for Computational Linguistics, Honolulu, Hawaii, pp. 582-590
Organizing and Searching the World Wide Web of Facts - Step Two: Harnessing the Wisdom of the Crowds
Preview
Proceedings of the 16th International World Wide Web Conference (WWW-2007), pp. 101-110
Weakly-Supervised Discovery of Named Entities Using Web Search Queries
Preview
Proceedings of the 16th ACM Conference on Information and Knowledge Management (CIKM-2007), Lisboa, Portugal, pp. 683-690
What You Seek is What You Get: Extraction of Class Attributes from Query Logs
Preview
Benjamin Van Durme
Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI-07) (2007), pp. 2832-2837
The Role of Documents vs. Queries in Extracting Class Attributes from Text
Preview
Benjamin Van Durme
Nikesh Garera
Proceedings of the 16th ACM Conference on Information and Knowledge Management (CIKM-2007), Lisboa, Portugal, pp. 485-494
Lightweight Web-Based Fact Repositories for Textual Question Answering
Preview
Proceedings of the 16th ACM Conference on Information and Knowledge Management (CIKM-2007), Lisboa, Portugal, pp. 87-96
Organizing and Searching the World Wide Web of Facts - Step One: the One-Million Fact Extraction Challenge
Preview
Dekang Lin
Jeffrey Bigham
Andrei Lifchits
Alpa Jain
Proceedings of the 21st National Conference on Artificial Intelligence (AAAI-06), Boston, Massachusetts (2006), pp. 1400-1405
Using Encyclopedic Knowledge for Named Entity Disambiguation
Preview
Razvan Bunescu
Proceedings of the 11th Conference of the European Chapter of the Association of Computational Linguistics (EACL-2006), Trento, Italy, pp. 9-16
Names and Similarities on the Web: Fact Extraction in the Fast Lane
Preview
Dekang Lin
Jeffrey Bigham
Andrei Lifchits
Alpa Jain
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (COLING-ACL-06), Sydney, Australia (2006), pp. 809-816
Mining Paraphrases from Self-Anchored Web Sentence Fragments
Preview
Proceedings of the 9th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD-2005), Porto, Portugal, pp. 193-204
Finding Instance Names and Alternative Glosses on the Web: WordNet Reloaded
Preview
Proceedings of the 6th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing-2005), Mexico City, Mexico, pp. 280-292
Aligning Needles in a Haystack: Paraphrase Acquisition Across the Web
Preview
Peter Dienes
Proceedings of the 2nd International Joint Conference on Natural Language Processing (IJCNLP-2005), Jeju Island, Republic of Korea, pp. 119-130
Acquisition of Categorized Named Entities for Web Search
Preview
Proceedings of the 13th ACM Conference on Information and Knowledge Management (CIKM-2004), Washington, D.C., pp. 137-145
No Results Found