LIPI at the NTCIR-16 FinNum-3 Task: Ensembling Transformer Based Models to Detect in-Claim Numerals in Financial Conversations

EasyChair Preprint 7967

Abstract

The third edition of FinNUM shared task, being held with NTCIR-16 presented the challenge of classifying numerals present in financial texts into in-claim or out-of-claim classes. It consisted of two claim detection sub-tasks on i) professional analysts’ reports written in Chinese and ii) earning conference calls transcribed in English. In this paper, we describe the approach our team (LIPI) followed while participating in the English subtask of FinNUM3. This approach consists of ensembling transformer based models with a Logistic Regression model trained using BERT embeddings and handcrafted features. It out-performed the existing baseline and achieved a macro F1 score of 84.73% and micro F1 score of 95.59% on the test set.

Keyphrases: Financial texts, call transcripts, claim detection

@booklet{EasyChair:7967,
  author    = {Sohom Ghosh and Sudip Kumar Naskar},
  title     = {LIPI at the NTCIR-16 FinNum-3 Task: Ensembling Transformer Based Models to Detect in-Claim Numerals in Financial Conversations},
  howpublished = {EasyChair Preprint 7967},
  year      = {EasyChair, 2022}}