TY - GEN
T1 - Arabic Medical Community Question Answering Using ON-LSTM and CNN
AU - Balla, Husamelddin A.M.N.
AU - Llorens Salvador, Marisa
AU - Delany, Sarah Jane
N1 - Publisher Copyright:
© 2022 Owner/Author.
PY - 2022/2/18
Y1 - 2022/2/18
N2 - In this paper, we address the problem of Arabic community question answering. We propose a model that leverages both the archived question and answer representations in the similarity computation with the user's question. The proposed model considers the interaction of the user's question with both archived questions and answers separately to address the noisy information problem in Arabic community question answering. The proposed model is a combination of two parts that covers question-question similarity and question-answer relevance. We used twin ON-LSTM with an attention mechanism and Arabic ELMo embeddings as input for the question-question similarity. For the question-answer relevance, we used a combination of twin ON-LSTM and CNN networks which can capture the relevance score even with long answers and questions. We evaluated the proposed model on the biomedical Arabic community question answering dataset cQA-MD. The proposed model outperformed the previous studies evaluated on the same dataset.
AB - In this paper, we address the problem of Arabic community question answering. We propose a model that leverages both the archived question and answer representations in the similarity computation with the user's question. The proposed model considers the interaction of the user's question with both archived questions and answers separately to address the noisy information problem in Arabic community question answering. The proposed model is a combination of two parts that covers question-question similarity and question-answer relevance. We used twin ON-LSTM with an attention mechanism and Arabic ELMo embeddings as input for the question-question similarity. For the question-answer relevance, we used a combination of twin ON-LSTM and CNN networks which can capture the relevance score even with long answers and questions. We evaluated the proposed model on the biomedical Arabic community question answering dataset cQA-MD. The proposed model outperformed the previous studies evaluated on the same dataset.
KW - Answer ranking
KW - Arabic QA
KW - Community question answering
UR - http://www.scopus.com/inward/record.url?scp=85133413423&partnerID=8YFLogxK
U2 - 10.1145/3529836.3529913
DO - 10.1145/3529836.3529913
M3 - Conference contribution
AN - SCOPUS:85133413423
T3 - ACM International Conference Proceeding Series
SP - 298
EP - 307
BT - 2022 14th International Conference on Machine Learning and Computing, ICMLC 2022
PB - Association for Computing Machinery
T2 - 14th International Conference on Machine Learning and Computing, ICMLC 2022
Y2 - 18 February 2022 through 21 February 2022
ER -