# TMLab SRPOL at SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums

## TL;DR

This paper presents a neural network-based system for fact-checking in community forums, achieving second place in SemEval 2019 Task 8, utilizing deep residual networks and sentence embeddings.

## Contribution

The paper introduces a Deeply Regularized Residual Neural Network with Universal Sentence Encoder embeddings for fact-checking in community questions, along with ensemble methods for improved performance.

## Key findings

- Achieved second place in SemEval 2019 Task 8
- Demonstrated effectiveness of residual neural networks with sentence embeddings
- Showed ensemble methods enhance fact-checking accuracy

## Abstract

The article describes our submission to SemEval 2019 Task 8 on Fact-Checking in Community Forums. The systems under discussion participated in Subtask A: decide whether a question asks for factual information, opinion/advice or is just socializing. Our primary submission was ranked as the second one among all participants in the official evaluation phase. The article presents our primary solution: Deeply Regularized Residual Neural Network (DRR NN) with Universal Sentence Encoder embeddings. This is followed by a description of two contrastive solutions based on ensemble methods.