# Multi-Task Learning for Coherence Modeling

## TL;DR

This paper introduces a hierarchical multi-task neural network for discourse coherence assessment, effectively predicting document coherence and grammatical roles, and demonstrating state-of-the-art results across various domains and tasks.

## Contribution

It presents a novel multi-task learning framework that jointly models coherence and grammatical roles, improving generalization and performance in coherence evaluation.

## Key findings

- Achieved state-of-the-art results on coherence prediction tasks
- Effective across multiple domains and real-world applications
- Improved coherence assessment through multi-task learning

## Abstract

We address the task of assessing discourse coherence, an aspect of text quality that is essential for many NLP tasks, such as summarization and language assessment. We propose a hierarchical neural network trained in a multi-task fashion that learns to predict a document-level coherence score (at the network's top layers) along with word-level grammatical roles (at the bottom layers), taking advantage of inductive transfer between the two tasks. We assess the extent to which our framework generalizes to different domains and prediction tasks, and demonstrate its effectiveness not only on standard binary evaluation coherence tasks, but also on real-world tasks involving the prediction of varying degrees of coherence, achieving a new state of the art.