Search Results

In this paper we focus on Sentence retrieval which is similar to Document retrieval but with a smaller unit of retrieval. Using data pre-processing in document retrieval is generally considered useful. When it comes to sentence retrieval the situation is not that clear. In this paper we use TF-ISF (term frequency – inverse sentence frequency)…

This paper focuses on a string encoding algorithm, which produces sparse distributed representations of text data. A characteristic feature of the algorithm described here, is that it works without tokenizing the text and can avoid other data preparation steps, such as stemming and lemmatization. The text can be of arbitrary size, whether it is a…