no code implementations • 4 Nov 2019 • Jamshid Mozafari, Afsaneh Fatemi, Mohammad Ali Nematbakhsh
The empirical results of applying the model on the TrecQA Raw, TrecQA Clean, and WikiQA datasets demonstrate that using a robust language model such as BERT can enhance the performance.
no code implementations • 3 Sep 2019 • Jamshid Mozafari, Mohammad Ali Nematbakhsh, Afsaneh Fatemi
In this research, a model is proposed to select the most relevant answers to the factoid question from the candidate answers.
no code implementations • 15 Nov 2013 • Mohammad Mehdi Keikha, Mohammad Ali Nematbakhsh, Behrouz Tork Ladani
Then, we propose a new strategy, which enables us to utilize the structural information of ontologies to get weights of matchers, for the similarity aggregation task.