Search Results for author:
Found 17 papers, 10 papers with code
On the Trade-off between the Number of Nodes and the Number of Trees in a Random Forest
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.
Syllable-level lyrics generation from melody exploiting character-level language model
The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics.
Controllable Lyrics-to-Melody Generation
Lyrics-to-melody generation is an interesting and challenging topic in AI music research field.
TabIQA: Table Questions Answering on Business Document Images
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.
An End-to-End Multi-Task Learning Model for Image-based Table Recognition
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
Rethinking Image-based Table Recognition Using Weakly Supervised Methods
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.
MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction
Knowledge graph embedding aims to predict the missing relations between entities in knowledge graphs.
Ranked #1 on
Link Prediction
on YAGO3-10
ARERec: Attentive Local Interaction Model for Sequential Recommendation
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.
Kernel Clustering with Sigmoid-based Regularization for Efficient Segmentation of Sequential Data
Second, we develop a stochastic variant of the proposed model.
Co-Factorization Model for Collaborative Filtering with Session-based Data
Despite that MF is a powerful method, it suffers from not be able to identifying strong associations of closely related items.
Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
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
Exploring Scholarly Data by Semantic Query on Knowledge Graph Embedding Space
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.
Boosting the Rating Prediction with Click Data and Textual Contents
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.
Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction Perspective
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
Learning Representations from Product Titles for Modeling Shopping Transactions
In this paper, we propose BASTEXT, an efficient model of shopping baskets and the texts associated with the products (e. g., product titles).
NPE: Neural Personalized Embedding for Collaborative Filtering
Matrix factorization is one of the most efficient approaches in recommender systems.
A Probabilistic Model for the Cold-Start Problem in Rating Prediction using Click Data
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.
