activity
20162022
most citedComparing heterogeneous entities using artificial neural networks of trainable weighted structural components and machine-learned activation functions

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

3 papers · 1 filter

cs.CL2022

Multilingual Search with Subword TF-IDF

Artit Wangperawong

Multilingual search can be achieved with subword tokenization. The accuracy of traditional TF-IDF approaches depend on manually curated tokenization, stop words and stemming rules,…

cs.CL2019

Question Generation by Transformers

Kettip Kriangchaivech, Artit Wangperawong

A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing r…

cs.CL2018

Attending to Mathematical Language with Transformers

Artit Wangperawong

Mathematical expressions were generated, evaluated and used to train neural network models based on the transformer architecture. The expressions and their targets were analyzed as…