Amharic English question answering system bridges language barrier
Amharic-English Cross-Language Question Answering Using Statistical Machine Translation, Named Entity Recognition, and Semantic Indexing
Computation and Language
Summary
Many websites are written in English, making it hard for speakers of languages like Amharic to find information. The paper describes a system that helps people ask questions in Amharic or English and get answers from documents in the other language. It uses machine translation, identifies names and places in Amharic text, and understands meanings in both languages to find the best answers. Their tests showed the system works fairly well, even with limited data to train on.
What this means in practice
- •For multilingual web developers: Create web tools that let users ask questions in Amharic and get answers from English content, or vice versa, improving access across languages with limited resources.
- •For digital library managers: Enable searching and answering questions across Amharic and English documents in mixed-language digital collections with semantic awareness.
Authors
Emebet Bekele, Fekade Getahun
Abstract
The predominance of English-language Web content creates an information-access barrier for speakers of low-resource languages such as Amharic. This paper presents the design, imple-mentation, and evaluation of a bidirectional Amharic-English cross-language question answering (CLQA) system that allows a user to formulate a natural-language question in either Amharic or English and retrieve an answer from documents written in the other language. The system integrates a statistical machine translation (SMT) component for query translation, a maximum-entropy named entity recognition (NER) component for Amharic text processing, semantic-based indexing, question analysis, passage retrieval, and answer extraction. A domain-diverse Amharic-English parallel corpus was used to train the SMT component, while monolingual cor-pora supported language modeling. Documents were normalized, tokenized, stemmed, indexed, and semantically enriched before retrieval. The original evaluation used precision and recall as the principal effectiveness measures. For Amharic-to-English retrieval, the system achieved 72% precision and 79% recall; for English-to-Amharic retrieval, it achieved 65% precision and 70% recall. These findings show that a modular translation-and-retrieval architecture can provide useful cross-language access even under low-resource conditions. This revised article preserves the original experimental claims while situating them in the context of subsequent multilingual transformer and Amharic QA research.