A non-exclusive multi-class convolutional neural network for the classification of functional requirements in AUTOSAR software requirement specification text

S Jp, VK Menon, KP Soman, AKR Ojha - IEEE Access, 2022 - ieeexplore.ieee.org
Software Requirement Specification (SRS) describes a software system to be developed
that captures the functional, non-functional, and technical aspects of the stakeholder's …

Indonesian-English Textual Similarity Detection Using Universal Sentence Encoder (USE) and Facebook AI Similarity Search (FAISS)

LD Krisnawati, AW Mahastama, SC Haw… - CommIT …, 2024 - journal.binus.ac.id
The tremendous development in Natural Language Processing (NLP) has enabled the
detection of bilingual and multilingual textual similarity. One of the main challenges of the …

Topic-based unsupervised and supervised dictionary induction

Y Liu, M Piccardi - ACM Transactions on Asian and Low-Resource …, 2023 - dl.acm.org
Word translation is a natural language processing task that provides translation between the
words of a source and a target language. As a task, it reduces to the induction of a bilingual …

Enhancing Named Entity Recognition in Low-Resource Languages: The Crucial Role of Data Sampling in Malayalam

A Gopalakrishnan, KP Soman - 2024 11th International …, 2024 - ieeexplore.ieee.org
This paper focuses on dataset class imbalances to address Named Entity Recognition
(NER) difficulties in low-resource languages like Malayalam. The main goal is to draw …

[PDF][PDF] Automatic detection of grammatical aspect of Russian verbs based on their morphological properties

U Petrunina, H Filip - … Workshop on Resources and Tools for …, 2023 - derimo.ffzg.unizg.hr
Automatic detection of grammatical aspect of Russian verbs based on their morphological
properties Page 1 hhu.de Automatic detection of grammatical aspect of Russian verbs based …

An improved long short-term memory with denoising autoencoder for solving text classification problems

AS Alija, NA Yahaya - Mehran University Research Journal Of …, 2024 - search.informit.org
In the past decade, text classification has been a popular research field for automatically
categorizing documents into relevant categories. Predicting classes for input samples based …

Persona-Driven Dialog Generation: Enhancing User Engagement Through Linguistic Proficiency and Personalization

A Abhishek, R Akhilesh, B Swetha… - International Conference …, 2024 - Springer
In this paper we focus upon building on the existing methods of using persona and auxiliary
information on improving and humanizing a conversational model as there are still …

Named Entity Recognition Using Deep Learning and BERT for Tamil and Hindi Languages

S Menon, JP Sanjanasri, B Premjith… - … Conference on Advances …, 2022 - Springer
Abstract Named Entity Recognition (NER) is a subclass of Information Extraction (IE) activity
that captures text information and meaning of words from unstructured input. NER's goal is to …

Preprint not peer reviewed

A Abhishek, R Akhilesh, B Swetha, V Vindhya Vasini… - papers.ssrn.com
Human-computer interaction has increased drastically over the last decade. Large
Language models hold immense potential in revolutionizing these interactions by …

NECAT-CLWE: A Simple But Efficient Parallel Data Generation Approach for Unsupervised and Semi-Supervised Neural Machine Translation

RA Ibrahim, I Abdulmumin - 3rd Workshop on African Natural Language … - openreview.net
Many languages lack sufficient data to train qualitative translation systems, particularly those
based on the cutting-edge neural machine translation architectures. Recently, it has been …