Typing candidate answers using type coercion

Murdock, J. William; Kalyanpur, Aditya; Welty, Chris; Fan, Jialu; Ferrucci, David; Gondek, David; Zhang, L.; Kitamura, Hiroshi

doi:10.1147/jrd.2012.2187036

Cited by 34 publications

(66 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been many works studying the expected answer types of a question [1,27,28,33,34,35]. Directly applying their methodology to our setting is not trivial.…”

Section: Answer Type Related Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Open Domain Question Answering via Semantic Enrichment

Sun

Yih

et al. 2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

Most recent question answering (QA) systems query largescale knowledge bases (KBs) to answer a question, after parsing and transforming natural language questions to KBsexecutable forms (e.g., logical forms). As a well-known fact, KBs are far from complete, so that information required to answer questions may not always exist in KBs. In this paper, we develop a new QA system that mines answers directly from the Web, and meanwhile employs KBs as a significant auxiliary to further boost the QA performance.Specifically, to the best of our knowledge, we make the first attempt to link answer candidates to entities in Freebase, during answer candidate generation. Several remarkable advantages follow: (1) Redundancy among answer candidates is automatically reduced. (2) The types of an answer candidate can be effortlessly determined by those of its corresponding entity in Freebase. (3) Capitalizing on the rich information about entities in Freebase, we can develop semantic features for each answer candidate after linking them to Freebase. Particularly, we construct answer-type related features with two novel probabilistic models, which directly evaluate the appropriateness of an answer candidate's types under a given question. Overall, such semantic features turn out to play significant roles in determining the true answers from the large answer candidate pool. The experimental results show that across two testing datasets, our QA system achieves an 18% ∼ 54% improvement under F1 metric, compared with various existing QA systems.

show abstract

“…There have been many works studying the expected answer types of a question [1,27,28,33,34,35]. Directly applying their methodology to our setting is not trivial.…”

Section: Answer Type Related Featuresmentioning

confidence: 99%

“…In our QA system, we develop features that evaluate the appropriateness of an answer candidate's types under a question. Previous works such as [1,11,27,28,30,33,34,35] on predicting the expected answer types of a question are related. In [28], Li et al classify questions into a hierarchy of classes.…”

Section: Related Workmentioning

confidence: 99%

Open Domain Question Answering via Semantic Enrichment

Sun

Yih

et al. 2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

show abstract

“…IBM Watson [8] is a massively parallel question answering system that integrates its responses among many different sources, including DBpedia [2], Wikipedia and WordNet. Instead of the standard approach, candidates are generated first using multiple interpretations and are then selected based on a combination of scores.…”

Section: Related Workmentioning

confidence: 99%

“…Table 2 presents the different question words which give information about the expected answer type (EAT). Some SQA approaches, such as IBM Watson [8], use the EAT to filter out wrong answer candidates and thus improve the precision of the answer. On the corpus however, the information gained using EATs is small, as 47…”

Section: Related Workmentioning

confidence: 99%

Towards question answering on statistical linked data

Höffner

Lehmann

2014

Proceedings of the 10th International Conference on Semantic Systems

View full text Add to dashboard Cite

As an increasing amount of statistical data is published as linked data, intuitive ways of satisfying information needs and getting new insights out of the data become more and more important. Question answering systems provide such an intuitive interface by translating natural language queries into SPARQL, which is the native query language of RDF knowledge bases. Statistical data, however, is structurally very different from other data and cannot be queried using existing approaches. We analyze the particularities of statistical data represented in the RDF Data Cube Vocabulary in relation to question answering and sketch a new question answering algorithm on statistical data. In order to estimate typical user questions, a statistical question corpus is compiled and its elements are categorized.

show abstract

“…IBM Watson utilized some pieces of information available as a part of DBpedia dataset. The primary use of this information was to type candidate answers using type coercion [86]. Though it utilized a small chunk of the LOD datasets, its overall impact was around 5% towards improving the accuracy of the answers generated by Watson.…”

Section: Applicationsmentioning

confidence: 99%

Linked open data alignment & querying

Jain

2013

SIGWEB Newsl.

View full text Add to dashboard Cite

Linked Open Data Alignment & Querying.The recent emergence of the Linked Data approach for publishing data represents a major step forward in realizing the original vision of a web that can "understand and satisfy the requests of people and machines to use the web content" i.e. the Semantic Web. This new approach has resulted in the Linked Open Data (LOD) Cloud, which includes more than 295 large datasets contributed by experts belonging to diverse communities such as geography, entertainment, and life sciences. However, the current interlinks between datasets in the LOD Cloud as we will illustrate are too shallow to realize much of the benefits promised. If this limitation is left unaddressed, then the LOD Cloud will merely be more data that suffers from the same kinds of problems, which plague the Web of Documents, and hence the vision of the Semantic Web will fall short.This thesis presents a comprehensive solution to address the issue of alignment and relationship identification using a bootstrapping based approach. By alignment we mean the process of determining correspondences between classes and properties of ontologies. We identify subsumption, equivalence and part-of relationship between classes. The work identifies part-of relationship between instances. Between properties we will establish subsumption and equivalence relationship. By bootstrapping we mean the process of being able to utilize the information which is contained within the datasets for improving the data within them. The work showcases use of bootstrapping based methods to identify and create richer relationships between LOD datasets. The BLOOMS project (http://wiki.knoesis.org/index.php/BLOOMS) and the PLATO project, both built as part of this research, have provided evidence to the feasibility and the applicability of the solution.

show abstract

Typing candidate answers using type coercion

Cited by 34 publications

References 20 publications

Open Domain Question Answering via Semantic Enrichment

Open Domain Question Answering via Semantic Enrichment

Towards question answering on statistical linked data

Linked open data alignment & querying

Contact Info

Product

Resources

About