TechTexC: Classification of Technical Texts using Convolution and Bidirectional Long Short Term Memory Network
This work provides a competitive solution for classifying technical texts into coarse-grained domains and fine-grained computer science sub-domains, which is useful for organizing and retrieving technical documents.
This paper describes TechTexC, a technical text classification system developed for the TechDofication 2020 shared task. The system uses a combined CNN-BiLSTM model, which achieved F1 scores up to 84.37 on development data and accuracies up to 79.97% on test data for various sub-tasks of technical domain and sub-domain classification.
This paper illustrates the details description of technical text classification system and its results that developed as a part of participation in the shared task TechDofication 2020. The shared task consists of two sub-tasks: (i) first task identify the coarse-grained technical domain of given text in a specified language and (ii) the second task classify a text of computer science domain into fine-grained sub-domains. A classification system (called 'TechTexC') is developed to perform the classification task using three techniques: convolution neural network (CNN), bidirectional long short term memory (BiLSTM) network, and combined CNN with BiLSTM. Results show that CNN with BiLSTM model outperforms the other techniques concerning task-1 of sub-tasks (a, b, c and g) and task-2a. This combined model obtained f1 scores of 82.63 (sub-task a), 81.95 (sub-task b), 82.39 (sub-task c), 84.37 (sub-task g), and 67.44 (task-2a) on the development dataset. Moreover, in the case of test set, the combined CNN with BiLSTM approach achieved that higher accuracy for the subtasks 1a (70.76%), 1b (79.97%), 1c (65.45%), 1g (49.23%) and 2a (70.14%).