Improving Question Answering Using Named Entity Recognition

Toral, Antonio; Noguera, Elisa; Llopis, Fernando; Muñoz, Rafael

doi:10.1007/11428817_17

Cited by 22 publications

(11 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several works are presented concerning NL Querying [17,27], NL and Schema Design [18,25], NL and DB interfaces [3,19], and Question Answering [23,26]. As far as we are aware of, related literature on NL and databases, has focused on totally different issues such as the interpretation of users' phrasal questions to a database language, e.g., SQL, or to the automatic database design, e.g., with the usage of ontologies [24].…”

Section: Related Workmentioning

confidence: 98%

Synthesizing structured text from logical database subsets

Simitsis

Koutrika

Alexandrakis

et al. 2008

Proceedings of the 11th International Conference on Extending Database Technology: Advances in Database Technology

View full text Add to dashboard Cite

In the classical database world, information access has been based on a paradigm that involves structured, schema-aware, queries and tabular answers. In the current environment, however, where information prevails in most activities of society, serving people, applications, and devices in dramatically increasing numbers, this paradigm has proved to be very limited. On the query side, much work has been done on moving towards keyword queries over structured data. In our previous work, we have touched the other side as well, and have proposed a paradigm that generates entire databases in response to keyword queries. In this paper, we continue in the same direction and propose synthesizing textual answers in response to queries of any kind over structured data. In particular, we study the transformation of a dynamically-generated logical database subset into a narrative through a customizable, extensible, and templatebased process. In doing so, we exploit the structured nature of database schemas and describe three generic translation modules for different formations in the schema, called unary, split, and join modules. We have implemented the proposed translation procedure into our own database front end and have performed several experiments evaluating the textual answers generated as several features and parameters of the system are varied. We have also conducted a set of experiments measuring the effectiveness of such answers on users. The overall results are very encouraging and indicate the promise that our approach has for several applications.

show abstract

Section: Related Workmentioning

confidence: 98%

Synthesizing structured text from logical database subsets

Simitsis

Koutrika

Alexandrakis

et al. 2008

Proceedings of the 11th International Conference on Extending Database Technology: Advances in Database Technology

View full text Add to dashboard Cite

show abstract

“…Proper identification and classification of named entities (NEs) are very big challenge to the NLP researchers. Geological NER has applications in several domains including information extraction, information retrieval, question answering [8], automatic summarization, machine translation [9] etc from Geological text. Named entity recognition (NER) (also known as entity identification and entity extraction) is a subtask of information extraction that seeks to locate and classify atomic elements in text into predefined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc.…”

Section: Geological Named Entity Recognitionmentioning

confidence: 99%

Conditional Random Field Based Named Entity Recognition in Geological text

Sobhana¹,

Mitra²,

Ghosh³

2010

IJCA

View full text Add to dashboard Cite

The paper describes about the development of a Named Entity Recognition (NER) system for Geological text using Conditional Random Fields (CRFs). The system makes use of the different contextual information of the words along with the variety of features that are helpful in predicting the various named entity (NE) classes. The NE tagged geological corpus was developed from the collection of scientific reports and articles on the geology of the Indian subcontinent has been used to build up the system. The training set consists of more than 2 lakh words and has been manually annotated with a NE tag set of seventeen tags. The system is able to recognize 17 classes of NEs with 75.8% Fmeasure.

show abstract

“…The problem of facilitating the naïve user has been thoroughly discussed in the field of natural language processing (NLP). For the last couple of decades, several works are presented concerning NL Querying [26,15], NL and Schema Design [23,14,4], NL and DB interfaces [17,2], and Question Answering [25,22]. Related literature on NL and databases, has focused on totally different issues such as the interpretation of users' phrasal questions to a database language, e.g., SQL, or to the automatic database design, e.g., with the usage of ontologies [24].…”

Section: Related Workmentioning

confidence: 99%

An Enhanced Search Interface for Information Discovery from Digital Libraries

Koutrika

Simitsis

2006

Research and Advanced Technology for Digital Libraries

View full text Add to dashboard Cite

Libraries, museums, and other organizations make their electronic contents available to a growing number of users on the Web. A large fraction of the information published is stored in structured or semi-structured form. However, most users have no specific knowledge of schemas or structured query languages for accessing information stored in (relational or XML) databases. Under these circumstances, the need for facilitating access to information stored in databases becomes increasingly more important. Précis queries are free-form queries that instead of simply locating and connecting values in tables, they also consider information around these values that may be related to them. Therefore, the answer to a précis query might also contain information found in other parts of the database. In this paper, we describe a précis query answering prototype system that generates personalized presentation of short factual information précis in response to keyword queries.

show abstract

Improving Question Answering Using Named Entity Recognition

Cited by 22 publications

References 4 publications

Synthesizing structured text from logical database subsets

Synthesizing structured text from logical database subsets

Conditional Random Field Based Named Entity Recognition in Geological text

An Enhanced Search Interface for Information Discovery from Digital Libraries

Contact Info

Product

Resources

About