Search Results for author: Tadachika Ozono

Found 7 papers, 0 papers with code

Lyricist-Singer Entropy Affects Lyric-Lyricist Classification Performance

no code implementations17 Oct 2023 Mitsuki Morita, Masato Kikuchi, Tadachika Ozono

Our results suggest that further analyses of the features contributing to lyric-lyricist classification performance on the lowest lyricist-singer entropy group may improve the feature extraction task for lyricists.

Classification

Conservative Likelihood Ratio Estimator for Infrequent Data Slightly above a Frequency Threshold

no code implementations28 Oct 2022 Masato Kikuchi, Yuhi Kusakabe, Tadachika Ozono

A naive likelihood ratio (LR) estimation using the observed frequencies of events can overestimate LRs for infrequent data.

Developing a Component Comment Extractor from Product Reviews on E-Commerce Sites

no code implementations13 Jul 2022 Shogo Anda, Masato Kikuchi, Tadachika Ozono

We determined proper labels based for the words identified through pattern matching from product reviews to create the training data.

Data Augmentation

Product Information Browsing Support System Using Analytic Hierarchy Process

no code implementations17 Dec 2021 Weijian Li, Masato Kikuchi, Tadachika Ozono

Large-scale e-commerce sites can collect and analyze a large number of user preferences and behaviors, and thus can recommend highly trusted products to users.

Decision Making Information Retrieval +1

Feature Selective Likelihood Ratio Estimator for Low- and Zero-frequency N-grams

no code implementations5 Nov 2021 Masato Kikuchi, Mitsuo Yoshida, Kyoji Umemura, Tadachika Ozono

However, because this method deals with a large number of discrete values, the running time and memory usage for estimation are problematic.

Document Classification feature selection

Development of an Extractive Title Generation System Using Titles of Papers of Top Conferences for Intermediate English Students

no code implementations8 Oct 2021 Kento Kaku, Masato Kikuchi, Tadachika Ozono, Toramatsu Shintani

The results show that our evaluation model can identify top-conference titles more effectively than intermediate English and beginner students.

Cannot find the paper you are looking for? You can Submit a new open access paper.