In this paper, we aim to learn a semantic database given a text corpus. Specifically, we focus on predicting whether or not a pair of entities are related by the hypernym relation, also known as the 'is-a' or 'type-of' relation. We learn a neural network model for this task. The model is given as input a description of the words and the context from the text corpus in which a pair of nouns (ent...

Digital trees, or tries, were introduced thirty years ago for sublinear-time retrieval of substrings from large texts. They were exploited for this, as a well-known example, by the University of Waterloo project to put the New Oxford English Dictionary onto CD-ROM. We have recently improved the performance of trie techniques for text and shown their use in searches for approximations to a given...

Many valuable text databases on the web have noncrawlable contents that are “hidden” behind search interfaces. Metasearchers are helpful tools for searching over multiple such “hidden-web” text databases at once through a unified query interface. An important step in the metasearching process is database selection, or determining whch databases are the most relevant for a given user query. Our ...

As the number and diversity of text databases on the Internet increases rapidly, users are faced with finding the text databases that are relevant to the user query. Identifying the relevant text databases out of many candidates for a given query is called the text database discovery problem. In this paper, we propose a neural net based approach to the text database discovery problem. First, we...

One of the distinctive features of Information Retrieval systems comparing to Database Management systems, is that they offer better compression for posting lists, resulting in better I/O performance and thus faster query evaluation. In this paper, we introduce database representations of the index that reduce the size (and thus the disk I/Os) of the posting lists. This is not achieved by redes...