arXiv subjects

Eiko Yamamoto

Publications and source records attributed to Eiko Yamamoto.

3 recordsLinked to original sources

arXiv2017

Polysemy Detection in Distributed Representation of Word Sense

In this paper, we propose a statistical test to determine whether a given word is used as a polysemic word or not. The statistic of the word in this test roughly corresponds to the fluctuation in the senses of the neighboring words a nd the word itself. Even though the sense of a word corresponds to a single vector, we discuss how polysemy of the words affects the position of vectors. Finally, we also explain the method to detect this effect.

cs.DS↗

arXiv2017

Finding Association Rules by Direct Estimation of Likelihood Ratios

In this paper, we propose a cost function that corresponds to the mean square errors between estimated values and true values of conditional probability in a discrete distribution. We then obtain the values that minimize the cost function. This minimization approach can be regarded as the direct estimation of likelihood ratios because the estimation of conditional probability can be regarded as the estimation of likelihood ratio by the definition of conditional probability. When we use the estimated value as the strength of association rules for data mining, we find that it outperforms a well-used method called Apriori.

stat.AP↗

arXiv2017

Using Conservative Estimation for Conditional Probability instead of Ignoring Infrequent Case

There are several estimators of conditional probability from observed frequencies of features. In this paper, we propose using the lower limit of confidence interval on posterior distribution determined by the observed frequencies to ascertain conditional probability. In our experiments, this method outperformed other popular estimators.

cs.IT↗