Filters








1,256 Hits in 8.0 sec

Generalizing from relevance feedback using named entity wildcards

Abhimanyu Lad, Yiming Yang
2007 Proceedings of the sixteenth ACM conference on Conference on information and knowledge management - CIKM '07  
This paper proposes news ways of generalizing from relevance feedback by augmenting the traditional bagof-words query model with named entity wildcards that are anchored in context.  ...  The use of wildcards allows generalization beyond specific words, while contextual restrictions limit the wildcard-matching to entities related to the user's query.  ...  GENERALIZING FROM FEEDBACK In this section, we describe how we extend our adaptive filtering component by augmenting the bag-of-words query models with named entity based wildcards.  ... 
doi:10.1145/1321440.1321541 dblp:conf/cikm/LadY07 fatcat:grfbbqlsarcglmmep5cvy4kxze

Stuctured Queries for Legal Search

Yangbo Zhu, Le Zhao, Jamie Callan, Jaime G. Carbonell
2007 Text Retrieval Conference  
Named-Entity tags, LingPipe sentence breaker and metadata fields of the original documents are used to generate the field information.  ...  This paper reports the experiments of using Indri for the main and routing (relevance feedback) tasks in the TREC 2007 Legal Track.  ...  In the experiments BBN's Named-Entity tagger − Identifinder and the LingPipe 5 sentence breaker are used for generating additional annotations.  ... 
dblp:conf/trec/ZhuZCC07 fatcat:y56lrl5vdbdojjjkil5pvlqvdm

Exploring the Legal Discovery and Enterprise Tracks at the University of Iowa

Brian Almquist, Viet Ha-Thuc, Aditya Kumar Sehgal, Robert J. Arens, Padmini Srinivasan
2007 Text Retrieval Conference  
Our implementation of Okapi-BM25 used parameters k 1 = 1.2, and B = 0.75.  ...  Okapi reranking The Lucene default scoring system was used to retrieve and rank an initial collection of documents.  ...  Expert Search Candidate identification We developed regular expressions to identify email ids and use the Stanford NER system to identify 'PERSON' named-entities.  ... 
dblp:conf/trec/AlmquistHSAS07 fatcat:fuzm2hklhrh7rpy23l5h2pmrti

CHALKBOARD: ONTOLOGY-BASED PATHWAY MODELING AND QUALITATIVE INFERENCE OF DISEASE MECHANISMS

DANIEL L. COOK, JESSE C. WILEY, JOHN H. GENNARI
2006 Biocomputing 2007  
reasoning that computes causal chains and feedback loops within the network of entities and reactions.  ...  We believe that pathway reasoning capabilities and in silico experiments will become a critical component of the hypothesis generation phase of modern biological research.  ...  We also include "wildcard" classes (Wildcard producer, Wildcard producer flow, Wildcard change action) for representing entities and actions whose physical basis is unknown.  ... 
doi:10.1142/9789812772435_0003 fatcat:iclxjztns5ah7jz5asya56mnsa

Pattern Learning for Detecting Defect Reports and Improvement Requests in App Reviews [article]

Gino V.H. Mangnoesing, Maria Mihaela Trusca, Flavius Frasincar
2020 arXiv   pre-print
Additionally, we experiment with a distantly-supervised SVM that makes use of noisy labels generated by patterns.  ...  Using a real-world dataset of app reviews, we show that the automatically learned patterns outperform the manually created ones, to be generated.  ...  Whereas the pool contains all entity types and the wildcard, for the case of Part-Of-Speech (POS) and Literal terminals we select only the most relevant nodes.  ... 
arXiv:2004.08793v1 fatcat:kvz52fw6rbag7aqv5htf4rjvai

Pattern Learning for Detecting Defect Reports and Improvement Requests in App Reviews [chapter]

Gino V. H. Mangnoesing, Maria Mihaela Truşcǎ, Flavius Frasincar
2020 Lecture Notes in Computer Science  
Additionally, we experiment with a distantly-supervised SVM that makes use of the noisy labels generated by patterns.  ...  Online reviews are an important source of feedback for understanding customers.  ...  Whereas the pool contains all entity types and the wildcard, for the case of POS and Literal terminals we select only the most relevant nodes.  ... 
doi:10.1007/978-3-030-51310-8_12 fatcat:t4rtz65vxnbw5moto5a4ocg6da

Personal Information Management [chapter]

Newton Lee
2012 Facebook Nation  
., RSS/ATOM) from "life-tracking" web sites as sensor streams.  ...  To make behaviors easy and natural for end-users to specify, Atomate features a constrained natural language interface (CNLI) that guides and accelerates input using predictive auto-complete and correction  ...  | wildcard-type | coref-expr predicate-expr → named-predicate | new-predicate-name object-value-expr → named-or-wildcard-entity | primitive-value entity-property-chain → named-entity | named-entity "'  ... 
doi:10.1007/978-1-4614-5308-6_12 fatcat:bnfjwikrx5cn3ophjhg4da367a

GIR Experiments with Forostar at GeoCLEF 2007

Simon E. Overell, João Magalhães, Stefan M. Rüger
2007 Conference and Labs of the Evaluation Forum  
We compare the results from orthogonal text with no geographic entities and only geographic entities with standard text retrieval and combined text and geographic relevance methods.  ...  The text and named entity analysis and retrieval methods of Forostar are described in detail. We also detail our placename disambiguation and geographic relevance ranking methods.  ...  The geographic, text and named entity relevance are then combined using Lucene's Vector Space Model. We perform blind relevance feedback on the text fields only.  ... 
dblp:conf/clef/OverellMR07a fatcat:vqa7cf5idrh2jl63ti46udxwjq

RBEM

Erik Tromp, Mykola Pechenizkiy
2013 Proceedings of the Second International Workshop on Issues of Sentiment Discovery and Opinion Mining - WISDOM '13  
RBEM uses several kinds of heuristic rules to create an emissive model on polarity patterns. We extensively experiment with our approach on English and Dutch messages extracted from Twitter.  ...  Thus we also illustrate that RBEM can be used in multilingual settings and is applicable to social media characterized by use of not always regular language constructs.  ...  Enriching the model via the relevance feedback from the user is also feasible and automating this process is one of the directions of our further work.  ... 
doi:10.1145/2502069.2502077 dblp:conf/kdd/TrompP13 fatcat:yk3p64salffx5np3t5lytcuvfu

Thresher

Andrew Hogue, David Karger
2005 Proceedings of the 14th international conference on World Wide Web - WWW '05  
We then use the tree edit distance between the DOM subtrees of these examples to create a general pattern, or wrapper, for the content, and allow the user to bind RDF classes and predicates to the nodes  ...  We describe Thresher, a system that lets non-technical users teach their browsers how to extract semantic web content from HTML documents on the World Wide Web.  ...  To use the Web Scraper, a user must analyze the HTML source of a document and provide explicit delimiters for relevant information.  ... 
doi:10.1145/1060745.1060762 dblp:conf/www/HogueK05 fatcat:e2i722hhkfbfxaop6r6ph7ge5q

Supporting BioMedical Information Retrieval: The BioTracer Approach [chapter]

Heri Ramampiaro, Chen Li
2011 Lecture Notes in Computer Science  
The results from our experiments using the TREC 2004 Genomic Track collection are promising.  ...  The techniques also allow users to affect the ranking according to their view of relevance.  ...  To be able to evaluate this approach, we simulated the user relevant feedback process using the relevance information from the test collection.  ... 
doi:10.1007/978-3-642-23740-9_4 fatcat:p7v22begxvbj5mcg5i2f6cloum

ProSWIP: Property-Based Data Access for Semantic Web Interactive Programming [chapter]

Silviu Homoceanu, Philipp Wille, Wolf-Tilo Balke
2013 Lecture Notes in Computer Science  
The Semantic Web has matured from a mere theoretical vision to a variety of ready-to-use linked open data sources currently available on the Web.  ...  To alleviate these problems, we developed an iterative approach that builds on human feedback.  ...  While Title, Description and URL are quite general (1,5 million entities), Director, Actors and especially Genre significantly reduce the number of relevant entities.  ... 
doi:10.1007/978-3-642-41335-3_12 fatcat:5fjlj3wdurg4zn47yna4chtal4

Gui --- phooey!

Max Van Kleek, Michael Bernstein, David R. Karger, mc schraefel
2007 Proceedings of the 20th annual ACM symposium on User interface software and technology - UIST '07  
Freeform text entry suffers from none of these limitations but produces data that is hard to retrieve or visualize.  ...  Similarly, this feedback gives the opportunity for the user to see what entities Jourknow has matched in the pidgin expression, if any, and to allow the user to correct its name resolution if necessary  ...  Jourknow offers search and faceted browsing based on tags, entities, and relations for finding relevant text scraps and entities.  ... 
doi:10.1145/1294211.1294247 dblp:conf/uist/KleekBKs07 fatcat:nkmfj6kyxzdc5njfy3rlkysise

PATTY: A Taxonomy of Relational Patterns with Semantic Types

Ndapandula Nakashole, Gerhard Weikum, Fabian M. Suchanek
2012 Conference on Empirical Methods in Natural Language Processing  
It harnesses the rich type system and entity population of large knowledge bases. The PATTY taxonomy comprises 350,569 pattern synsets.  ...  This paper presents PATTY: a large resource for textual patterns that denote binary relations between entities. The patterns are semantically typed and organized into a subsumption taxonomy.  ...  In fact, it would be straightforward to adjust PATTY to using surface-form noun phrases rather than disambiguated entities, as long as we have means to infer at least coarse-grained types (e.g., person  ... 
dblp:conf/emnlp/NakasholeWS12 fatcat:fsz2rzm4affcjb6jeepbly65ne

User-driven relational models for entity-relation search and extraction

Jay Urbain
2012 Proceedings of the 1st Joint International Workshop on Entity-Oriented and Semantic Search - JIWES '12  
, discover new relations from known entities, and discover new entities from known relations.  ...  By using a relational model, evidence can be leveraged across entity and relation instances.  ...  The user can provide relevance feedback to the system. The same NLP process is used for parsing document sentences and queries.  ... 
doi:10.1145/2379307.2379312 fatcat:7lixxcmrd5cure3mj3dgg6rxam
« Previous Showing results 1 — 15 out of 1,256 results