Naslov
Evaluation of Structural Hyperparameters for Text Classification with LSTM Networks

Autori
Frković, Marija ; Čerkez, Ninoslav ; Vrdoljak, Boris ; Skansi, Sandro

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO) / - Opatija : Institute of Electrical and Electronics Engineers (IEEE), 2020, 1145-1150

Skup
43nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2020)

Mjesto i datum
Opatija, Hrvatska, 28.09.2020. - 02.10.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
natural language processing ; LSTM ; structural hyperparameters ; multiclass classification ; binary classification

Sažetak
In natural language processing, most problems can be interpreted as text classification tasks, which makes this type of task a central one. A natural subdivision of more complex types of text classification can be made according to whether the classification is multilabel or multiclass, where both of these can be tackled with either a multiclass classifier or with a combination of several binary classifiers. An example of the problem which offers a natural way of comparing multiclass and binary classification on the same data, which makes the results comparable, is a classification of text author MBTI personality type. The dataset used is PersonalityCafe MBTI. We focus our comparison on structural hyperparameters, which are the hyperparameters pertaining to network structure. Structural hyperparameters are necessary for specifying the network itself, which makes them a primary concern in its construction. The hyperparameters investigated in this paper are the number of hidden layers and layer size. Through a number of experiments, we demonstrate the choice of hyperparameters and conclude with general hyperparameter selection recommendations based on our results.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti, Psihologija, Kognitivna znanost (prirodne, tehničke, biomedicina i zdravstvo, društvene i humanističke znanosti)

POVEZANOST RADA