Loading…
Title

Benchmarking semantic capabilities of analogy querying ...

Description
Tics of analogy query algorithms with a special focus on neural embeddings. ... based on these observations, we define three basic types of analogy queries ...
/15
Full Text
Benchmarking Semantic Capabilitiesof Analogy Querying AlgorithmsChristoph Lofi, Athiq Ahamed, Pratima Kulkarni, Ravi ThakkarTechnische Universität Braunschweig38106 Braunschweig, [email protected] Enabling semantically rich query paradigms is one of the core chal-lenges of current information systems research. In this context, due to their im-portance and ubiquity in natural language, analogy queries are of particular in-terest. Current developments in natural language processing and machine learn-ing resulted in some very promising algorithms relying on deep learning neuralword embeddings which might contribute to finally realizing analogy queries.However, it is still quite unclear how well these algorithms work from a semanticpoint of view. One of the problems is that there is no clear consensus on theintended semantics of analogy queries. Furthermore, there are no suitable bench-mark dataset available respecting the semantic properties of real-life analogies.Ther...