What question did this study set out to answer?

The research focuses on classifying financial arguments based on their temporal references.

April 1, 2026Open Access

SCaLAR IT at the NTCIR-18 FinArg-2: Temporal Inference of Financial Arguments

Key Points

The research focuses on classifying financial arguments based on their temporal references.
Participated in the NTCIR-18 FinArg-2 Task.
Utilized a BERT-based model combined with knowledge-based and temporal feature extraction techniques.
Extracted features using STANZA and integrated them with BERT embeddings.
Calculated performance metrics including Micro and Macro F1 scores.
The initial model achieved a Micro F1 score of 70.24%.
The Macro F1 score of 67.85% was recorded, outperforming many competing teams.
Incorporating additional temporal features further improved the Macro F1 score.

Abstract

The SCaLAR IT team participated in the Detection of Argument Temporal References subtask of the NTCIR-18 FinArg-2 Task. This paper presents our approach to solving the classification of financial arguments based on temporal references. We explored multiple ar- chitectures combining a BERT-based model with knowledge-based and temporal feature extraction techniques. To improve the perfor- mance,integrated BERT with TF-IDF based temporal features were extracted using STANZA and BERT embeddings to enhance tempo- ral reference detection. Our first model BERTForSequenceClassifier achieves the Micro F1 score of 70.24% and Macro F1 score of 67.85% outperforming most approaches of other teams. However incorpo- rating additional temporal features improved the Macro F1 score, indicating better performance across all classes. We analyze the effectiveness of different feature representations in our research.

SCaLAR IT at the NTCIR-18 FinArg-2: Temporal Inference of Financial Arguments

Key Points

Abstract

Cite This Study

Also Consider

Also Consider