no code implementations • 16 Dec 2023 • Tatsuya Akutsu, Avraham A. Melkman, Atsuhiro Takasu
We also show that a bag of $n$ decision trees can be represented by a bag of $T$ decision trees each with polynomial size if $n-T$ is a constant and a small classification error is allowed.
no code implementations • 2 Oct 2023 • Zhe Zhang, Karol Lasocki, Yi Yu, Atsuhiro Takasu
The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics.
no code implementations • 5 Jun 2023 • Zhe Zhang, Yi Yu, Atsuhiro Takasu
Lyrics-to-melody generation is an interesting and challenging topic in AI music research field.
1 code implementation • 27 Mar 2023 • Phuc Nguyen, Nam Tuan Ly, Hideaki Takeda, Atsuhiro Takasu
Table answering questions from business documents has many challenges that require understanding tabular structures, cross-document referencing, and additional numeric computations beyond simple search queries.
1 code implementation • 15 Mar 2023 • Nam Tuan Ly, Atsuhiro Takasu
Most of the previous methods focus on a non-end-to-end approach which divides the problem into two separate sub-problems: table structure recognition; and cell-content recognition and then attempts to solve each sub-problem independently using two separate systems.
Ranked #2 on Table Recognition on PubTabNet
1 code implementation • 14 Mar 2023 • Nam Tuan Ly, Atsuhiro Takasu, Phuc Nguyen, Hideaki Takeda
In this paper, we propose a weakly supervised model named WSTabNet for table recognition that relies only on HTML (or LaTeX) code-level annotations of table images.
4 code implementations • 30 Sep 2022 • Hung Nghiep Tran, Atsuhiro Takasu
Knowledge graph embedding aims to predict the missing relations between entities in knowledge graphs.
Ranked #1 on Link Prediction on YAGO3-10
1 code implementation • IEEE Access 2022 • Umaporn Padungkiatwattana, Thitiya Sae-Diae, Saranya Maneeroj, Atsuhiro Takasu
The aim is to model user and item behavior over the user–item interaction sequence while considering local representations that contain specific characteristics of both user and item in the sequence.
1 code implementation • 22 Jun 2021 • Tung Doan, Atsuhiro Takasu
Second, we develop a stochastic variant of the proposed model.
no code implementations • 12 May 2021 • Binh Nguyen, Atsuhiro Takasu
Despite that MF is a powerful method, it suffers from not be able to identifying strong associations of closely related items.
2 code implementations • 29 Jun 2020 • Hung Nghiep Tran, Atsuhiro Takasu
Knowledge graph embedding methods perform this task by representing entities and relations as embedding vectors and modeling their interactions to compute the matching score of each triple.
Ranked #1 on Link Prediction on KG20C
1 code implementation • 17 Sep 2019 • Hung Nghiep Tran, Atsuhiro Takasu
The knowledge graph can be modeled by knowledge graph embedding methods, which represent entities and relations as embedding vectors in semantic space, then model the interactions between these embedding vectors.
no code implementations • 21 Aug 2019 • ThaiBinh Nguyen, Atsuhiro Takasu
In this paper, we propose a model that leverages the information hidden in the item co-click (i. e., items that are often clicked together by a user) into learning item representations.
1 code implementation • 27 Mar 2019 • Hung Nghiep Tran, Atsuhiro Takasu
In this paper, we propose a multi-embedding interaction mechanism as a new approach to uniting and generalizing these models.
Ranked #17 on Link Prediction on WN18
no code implementations • 3 Nov 2018 • Binh Nguyen, Atsuhiro Takasu
In this paper, we propose BASTEXT, an efficient model of shopping baskets and the texts associated with the products (e. g., product titles).
1 code implementation • 17 May 2018 • ThaiBinh Nguyen, Atsuhiro Takasu
Matrix factorization is one of the most efficient approaches in recommender systems.
no code implementations • 5 May 2017 • ThaiBinh Nguyen, Atsuhiro Takasu
One of the most efficient methods in collaborative filtering is matrix factorization, which finds the latent vector representations of users and items based on the ratings of users to items.