This article describes the research project aimed at developing a Trilingual Machine translation System for English, Nepali, and Tamang language pairs. This project is expected to address knowledge and communication gaps caused by language barriers and mitigate disparities in the availability of information and knowledge sources in Tamang and Nepali.

This paper presents PCDT, a web-based platform for collecting sentence-aligned parallel corpora through a community-driven approach to support machine translation for under-resourced languages. The tool decentralizes the translation task to the target community and subsequently reviewed by language experts.

Despite being spoken by over 26 million people, Nepali lacks a standardized Information Retrieval (IR) benchmark, preventing systematic evaluation of retrieval models in this low-resource setting. While progress has been made in several Nepali NLP tasks, no publicly available test collection with queries and relevance judgments exists for ad-hoc retrieval task. We propose the creation of a first standardized Nepali IR benchmark supporting monolingual (Nepali queries \rightarrow Nepali documents), cross-lingual (English queries \rightarrow Nepali documents), and code-mixed (Nepali-English queries \rightarrow Nepali documents) retrieval. We argue that Nepali provides a compelling testbed for studying morphology-aware retrieval, code-mixed query processing, and multilingual embedding transfer.

Large Language Models (LLMs) have made significant advancements in Natural Language Processing (NLP) by excelling in various NLP tasks. This study specifically focuses on evaluating the performance of LLMs for Named Entity Recognition (NER) and Part-of-Speech (POS) tagging for a low-resource language, Nepali. The aim is to study the effectiveness of these models for languages with limited resources by conducting experiments involving various parameters and fine-tuning and evaluating two datasets namely, ILPRL and EBIQUITY. In this work, we have experimented with eight LLMs for Nepali NER and POS tagging. While some prior works utilized larger datasets than ours, our contribution lies in presenting a comprehensive analysis of multiple LLMs in a unified setting. The findings indicate that NepBERTa, trained solely in the Nepali language, demonstrated the highest performance with F1-scores of 0.76 and 0.90 in ILPRL dataset. Similarly, it achieved 0.79 and 0.97 in EBIQUITY dataset for NER and POS respectively. This study not only highlights the potential of LLMs in performing classification tasks for low-resource languages but also compares their performance with that of alternative approaches deployed for the tasks.

With the increase in internet access and the ease of writing comments in the Nepali language, fine-grained sentiment analysis of social media comments is becoming more and more pertinent. There are a number of benchmarked datasets for high-resource languages (English, French, and German) in specific domains like restaurants, hotels or electronic goods but not in low-resource languages like Nepali. In this paper, we present our work to create a dataset for the targeted aspect-based sentiment analysis in the social media domain, set up a dataset benchmark and evaluate using various machine learning models. The dataset comprises of code-mixed and code-switched comments extracted from Nepali YouTube videos. We present convincing baselines using a multilingual BERT model for the Aspect Term Extraction task and BiLSTM model for the Sentiment Classification Task achieving 57.978% and 81.60% F1 score respectively.