Neural Passage Retrieval in Joint Embedding Spaces
[go to overview]
Retrieving passages instead of whole documents can help professionals to acquire new information faster. This is important in domains where time for research is limited and expensive. For example a medical doctor at
an hospital has usually less than an hour per day to look up fresh information for rare cases. We present an approach for retrieving relevant passages in a document collection which leverages two orthogonal semantic embeddings. For this occasion we demonstrate a first prototype implementation as described in [1]. In this talk, we give an overview of our approach to learn a joint vector space representation of these embeddings. We plan to exploit this model to further improve passage and document retrieval tasks.
[1] R. Schneider, S. Arnold, T. Oberhauser, T. Klatt, T. Steffek, and A. Löser, “Smart-MD: Neural Paragraph Retrieval of Medical Topics,” in Companion of the The Web Conference 2018 on The Web Conference 2018, WWW 2018, Lyon , France, April 23-27, 2018, 2018, pp. 203–206.
07.06.18 - 10:15
B 016