Browsing by Author "Gavankar, Chetana"

Now showing 1 - 10 of 10

Automated System for interpreting Non-verbal Communication in Video Conferencing
(International Journal on Computer Science and Engineering, 2010) Gavankar, Chetana
Gesture is a form of non-verbal, action-based communication made with a part of the body and used instead of and/or in combination with verbal communication. People frequently use gestures for more effective inter-personal communication; out of which nearly 55% come from the facial expressions alone. Facial gestures often reveal when people are trying to conceal emotions such as fear, contempt, disgust, surprise, or even unspoken political tensions. Video conferencing captures such facial signals which can be directly processed by suitable image processing system. Facial gestures are more pronounced via eyes and lip region of human face and hence they form the regions of interest (ROI) while processing the video signal. Some of these concepts are used to develop a system which can identify specific human gestures and use their interpretation towards business decision support.
A Comparative Study of Semantic Search Systems
(IEEE, 2020) Gavankar, Chetana
Today’s internet consists of mostly unstructured data, most of it being unusable for average users. With increase in the number of smart devices that are getting access to the web, we have a large set of unlinked data that is not able to communicate. Indirectly, it can be said that the Web is broken. Semantic Web focuses on making the meaning explicit instead of fetching results with the help of word matching. Semantic Web is an extension to the current Web that provides an easier way to find, share, reuse and combine information. In this paper, we are presenting an analysis of the different approaches taken by various semantic web search engines and the comparison between them, thus identifying the advantages and limitation of each search engine.
Context-driven Concept Search across Web Ontologies using Keyword Queries
(ACM Digital Library, 2015-10) Gavankar, Chetana
Concepts in ontologies can be used in many scenarios, including annotation of online resources, automatic ontology population, and document classification to improve web search results. Collectively, tens of millions of concepts have been defined in a large number of ontologies that cover many overlapping domains. The scale, duplication and ambiguity makes concept search a challenging problem. We present a novel concept search approach that exploits structures present in ontologies and constructs contexts to effectively filter the noise in concept search results. The three key components of our approach are (1) a context for each concept extracted from relevant properties and axioms, (2) query interpretation based on the extracted context and (3) result ranking using learning to rank algorithms. We evaluate our approach on a large dataset from BioPortal. Our comprehensive evaluation is performed on 2,062,080 concepts and more than 2,000 queries, using two widely-employed performance metrics: normalized discounted cumulative gain (NDCG) and mean reciprocal rank (MRR). Our approach outperforms BioPortal significantly for multitoken queries that make up a large percentage of total queries.
Efficient Reuse of Structured and Unstructured Resources for Ontology Population
(ACL anthology, 2014) Gavankar, Chetana
We study the problem of ontology population for a domain ontology and present solutions based on semi-automatic techniques. A domain ontology for an organization, often consists of classes whose instances are either specific to, or independent of the organization. E.g. in an academic domain ontology, classes like Professor, Department could be organization (university) specific, while Conference, Programming languages are organization independent. This distinction allows us to leverage data sources both―within the organization and those in the Internet ― to extract entities and populate an ontology. We propose techniques that build on those for open domain IE. Together with user input, we show through comprehensive evaluation, how these semi-automatic techniques achieve high precision. We experimented with the academic domain and built an ontology comprising of over 220 classes. Intranet documents from five universities formed our organization specific corpora and we used open domain knowledge bases like Wikipedia, Linked Open Data, and web pages from the Internet as the organization independent data sources. The populated ontology that we built for one of the universities comprised of over 75,000 instances. We adhere to the semantic web standards and tools and make the resources available in the OWL format. These could be useful for applications such as information extraction, text annotation, and information retrieval.
Enriching An Academic knowledge base using Linked Open Data
(ACL anthology, 2012) Gavankar, Chetana
In this paper we present work done towards populating a domain ontology using a public knowledge base like DBpedia. Using an academic ontology as our target we identify mappings between a subset of its predicates and those in DBpedia and other linked datasets. In the semantic web context, ontology mapping allows linking of independently developed ontologies and inter-operation of heterogeneous resources. Linked open data is an initiative in this direction. We populate our ontology by querying the linked open datasets for extracting instances from these resources. We show how these along with semantic web standards and tools enable us to populate the academic ontology. Resulting instances could then be used as seeds in spirit of the typical bootstrapping paradigm
Enriching Concept Search across Semantic Web Ontologies
(CEUR, 2013) Gavankar, Chetana
Semantic Web ontologies are fast-growing knowledge sources on the Web. Searching relevant concepts from this large repository is a challenging problem. The current Semantic Web search engines provide either (1) coarse-grained search over ontologies or (2) very ne-grained search over individuals.We believe searching and ranking concepts across ontologies provides an ideal granularity for certain tasks such as ontology population and web page annotation. Towards this objective, we propose a novel approach of indexing concepts using ontology axioms in an inverted le structure and ranking them using a dynamic ranking algorithm. Our proposed method is generic and domain-independent. A preliminary evaluation indicates that our proposed method is e ective, outperforming the search function of BioPortal, a large and widely-used ontology repository.
Explicit Query Interpretation and Diversification for Context-Driven Concept Search Across Ontologies
(Springer, 2016) Gavankar, Chetana
Finding relevant concepts from a corpus of ontologies is useful in many scenarios, such as document classification, web page annotation, and automatic ontology population. Many millions of concepts are contained in a large number of ontologies across diverse domains. A SPARQL-based query demands the knowledge of the structure of ontologies and the query language, whereas user-friendlier and, simpler keyword-based approaches suffer from false positives. This is because concept descriptions in ontologies may be ambiguous and may overlap. In this paper, we propose a keyword-based concept search framework, which (1) exploits the structure and semantics in ontologies, by constructing contexts for each concept; (2) generates the interpretations of a query; and (3) balances the relevance and diversity of search results. A comprehensive evaluation against the domain-specific BioPortal and the general-purpose Falcons on widely-used performance metrics demonstrates that our system outperforms both.
Semi-automatic dictionary curation for domain-specific ontologies
(IEEE, 2013) Gavankar, Chetana
Within the broad area of information extraction, we study the problem of effective dictionary curation in an enterprise setting. Equipped with an ontology, representative of the domain of an enterprise, our approach populates the attributes of leaf nodes of the ontology with instances extracted from the enterprise corpus. For an attribute of interest, given a few seed examples or indicative features for the attribute, we first obtain a ranked list of 'list pages' potentially containing additional dictionary terms. Our ranking model ranks pages from the enterprise corpus based on their 'list' content using several visual and lexical features. We gather users' judgement of the result pages and the model continuously learns from this feedback. We compare different techniques of dictionary curation using rule based extractors and visual features of pages. Based on rule writing exercise, we show the benefit of dictionaries for leaf node attributes, in writing rule based extractors for higher level nodes in an ontology. We have implemented a dictionary curation system based on these ideas. Experimental analysis using academic domain ontology and universities corpora, reveal (in the context of enterprise analytics) (i) the merit of dictionary support in rule based information extraction (ii) the viability and effectiveness of an interactive approach for dictionary creation.
A Utility Tool for Personalised Medicine
(ACM Digital Library, 2018) Gavankar, Chetana
Biomedical research is drowning in data, yet starving for knowledge. As the volume of scientific literature is growing unprecedentedly, revolutionary measures are needed for data management. Accessibility, analysis and mining knowledge from this textual data has become a very important task. One such source is NCBI that houses a series of databases (PubMed) relevant to biotechnology and bio-medicine. It is an important resource for bioinformatics tools and services. In this paper, a system is proposed that encases all the biomedical articles of PubMed as needed by bioinformaticians. Using machine learning and natural language processing, the tool aims at assisting clinicians and biomedical researchers to understand and graphically represent the relevance of gene in a given disease context. It will also support entity-specific bio-curation searches to get a list of most effective drugs for a particular disease. The system is evaluated by using standard information retrieval measures namely, Precision, Recall and F-score to measure the relevance of search results.
A Utility Tool for Personalised Medicine
(ACM Digital Library, 2018) Gavankar, Chetana
Biomedical research is drowning in data, yet starving for knowledge. As the volume of scientific literature is growing unprecedentedly, revolutionary measures are needed for data management. Accessibility, analysis and mining knowledge from this textual data has become a very important task. One such source is NCBI that houses a series of databases (PubMed) relevant to biotechnology and bio-medicine. It is an important resource for bioinformatics tools and services. In this paper, a system is proposed that encases all the biomedical articles of PubMed as needed by bioinformaticians. Using machine learning and natural language processing, the tool aims at assisting clinicians and biomedical researchers to understand and graphically represent the relevance of gene in a given disease context. It will also support entity-specific bio-curation searches to get a list of most effective drugs for a particular disease. The system is evaluated by using standard information retrieval measures namely, Precision, Recall and F-score to measure the relevance of search results.