<p>This study introduces a novel strategy for improving a question-answering system by dynamically selecting the best ensemble technique among RoBERTa, BERT, ALBERT, DistilBERT, and ELECTRA language models. A unique metric based on the Average Confidence Score of these models is used to implement dynamic ensemble strategy selection. We test the proposed technique on JUDVLP-QADB.v1, a freshly created question-answering dataset from public Indian government domains. On the JUDVLP-QADB.v1 dataset, the technique improved Exact Match and F1 score significantly. Our ensemble technique selection experiments are two-step. First, we run the same group ensembles with varied language model settings. Second, we combine the best-performing ensembles from different groups to generate cross-group ensembles, and finally we present a novel system for dynamically selecting the ideal ensemble technique. The suggested technique chose the RoBERTa ensemble for the same group and the RoBERTa and DistilBERT ensemble for the cross group during the assessment. After dynamically picking the right ensemble model, we received a maximum Exact Match score of 69.01 and an F1-Score of 83.69. These values show a 15% and 10.31% increase above baseline models. Our study found that dynamically selecting ensembles based on a parameter improves question-answering system performance on the JUDVLP-QADB.v1 test dataset. Our novel ensemble selection method simplifies the procedure by lowering the difficulty of picking from <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10844_2025_947_Article_IEq1.gif" Format="GIF" Height="43" Rendition="HTML" Resolution="72" Type="Linedraw" Width="47" /> </InlineMediaObject> <EquationSource Format="TEX">\(\left( {\begin{array}{c}n\\ 2\end{array}}\right) \)</EquationSource> <EquationSource Format="MATHML"><math> <mfenced close=")" open="("> <mrow> <mtable> <mtr> <mtd> <mi>n</mi> </mtd> </mtr> <mtr> <mtd> <mrow> <mrow /> <mn>2</mn> </mrow> </mtd> </mtr> </mtable> </mrow> </mfenced> </math></EquationSource> </InlineEquation> different combinations of ensembles from a set of n models.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Dynamic selection of ensemble technique for question answering systems: For Indian government dataset

  • Sandip Pramanik,
  • Subrata Roy Gupta,
  • Nibaran Das

摘要

This study introduces a novel strategy for improving a question-answering system by dynamically selecting the best ensemble technique among RoBERTa, BERT, ALBERT, DistilBERT, and ELECTRA language models. A unique metric based on the Average Confidence Score of these models is used to implement dynamic ensemble strategy selection. We test the proposed technique on JUDVLP-QADB.v1, a freshly created question-answering dataset from public Indian government domains. On the JUDVLP-QADB.v1 dataset, the technique improved Exact Match and F1 score significantly. Our ensemble technique selection experiments are two-step. First, we run the same group ensembles with varied language model settings. Second, we combine the best-performing ensembles from different groups to generate cross-group ensembles, and finally we present a novel system for dynamically selecting the ideal ensemble technique. The suggested technique chose the RoBERTa ensemble for the same group and the RoBERTa and DistilBERT ensemble for the cross group during the assessment. After dynamically picking the right ensemble model, we received a maximum Exact Match score of 69.01 and an F1-Score of 83.69. These values show a 15% and 10.31% increase above baseline models. Our study found that dynamically selecting ensembles based on a parameter improves question-answering system performance on the JUDVLP-QADB.v1 test dataset. Our novel ensemble selection method simplifies the procedure by lowering the difficulty of picking from \(\left( {\begin{array}{c}n\\ 2\end{array}}\right) \) n 2 different combinations of ensembles from a set of n models.