We address a key problem in grapheme-tophoneme conversion: the ambiguity in mapping grapheme units to phonemes. Rather than using single letters and phonemes as units, we propose ...
In this paper, we present a learning approach to the scenario template task of information extraction, where information filling one template could come from multiple sentences. ...
Information extraction from HTML pages has been conventionally treated as plain text documents extended with HTML tags. However, the growing maturity and correct usage of HTML/XHT...
One problem of data-driven answer extraction in open-domain factoid question answering is that the class distribution of labeled training data is fairly imbalanced. This imbalance...
Michael Wiegand, Jochen L. Leidner, Dietrich Klako...
The paper analyzes peculiarities of preprocessing of learning data represented in object data bases constituted by multiple relational tables with ontology on top of it. Exactly s...