Filtering by
- Creators: Bansal, Srividya
- Creators: Carradini, Stephen
Question Answering systems have been around for quite some time and are a sub-field of information retrieval and natural language processing. The task of any Question Answering system is to seek an answer to a free form factual question. The difficulty of pinpointing and verifying the precise answer makes question answering more challenging than simple information retrieval done by search engines. Text REtrieval Conference (TREC) is a yearly conference which provides large - scale infrastructure and resources to support research in information retrieval domain. TREC has a question answering track since 1999 where the questions dataset contains a list of factual questions (Vorhees & Tice, 1999). DBpedia (Bizer et al., 2009) is a community driven effort to extract and structure the data present in Wikipedia.
The research objective of this thesis is to develop a novel approach to Question Answering based on a composition of conventional approaches of Information Retrieval and Natural Language processing. The focus is also on exploring the use of a structured and annotated knowledge base as opposed to an unstructured knowledge base. The knowledge base used here is DBpedia and the final system is evaluated on the TREC 2004 questions dataset.
The purpose of this project was to evaluate the State Bar of New Mexico's (SBNM) new podcast series, SBNM is Hear. The podcast was initially developed as a member outreach tool and a new platform for professional development and survey questions were developed to gauge the podcast’s effectiveness in these two areas. An electronic survey was deployed to active members of the SBNM through email. Respondents were asked questions regarding their demographics, whether they had listened to the series, and what content they would like to hear in the future. The survey resulted in 103 responses, of which 60% indicated that they had not listened to the podcast. The results showed that listenership was evenly divided between generations and that more females listened to at least one episode. The open-ended responses indicated that the two cohorts of respondents (listeners and non- listeners) viewed the podcast a potential connection to the New Mexico judiciary. Future recommendations include conducting an annual survey to continue to understand the effectiveness of the podcast and solicit feedback for continued growth and improvement
The main focus of this thesis is to use visual description of a landmark by choosing the most diverse pictures that best describe all the details of the queried location from community-contributed datasets. For this, an end-to-end framework has been built, to retrieve relevant results that are also diverse. Different retrieval re-ranking and diversification strategies are evaluated to find a balance between relevance and diversification. Clustering techniques are employed to improve divergence. A unique fusion approach has been adopted to overcome the dilemma of selecting an appropriate clustering technique and the corresponding parameters, given a set of data to be investigated. Extensive experiments have been conducted on the Flickr Div150Cred dataset that has 30 different landmark locations. The results obtained are promising when evaluated on metrics for relevance and diversification.