# Understanding Emotion Valence is a Joint Deep Learning Task

arXiv: https://arxiv.org/abs/2305.17422 · HTML: https://mlsanity.com/paper/2305.17422/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 27 May 2023.

## Builds on (most cited first, 20 of 20)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines](https://mlsanity.com/paper/2006.04884/) (2020)
- [Professor Forcing: A New Algorithm for Training Recurrent Networks](https://mlsanity.com/paper/1610.09038/) (2016)
- [BERT for Joint Intent Classification and Slot Filling](https://mlsanity.com/paper/1902.10909/) (2019)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding](https://mlsanity.com/paper/1909.02188/) (2019)
- [A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2101.00816/) (2021)
- [A Co-Interactive Transformer for Joint Slot Filling and Intent Detection](https://mlsanity.com/paper/2010.03880/) (2020)
- [AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models](https://mlsanity.com/paper/2102.05126/) (2021)
- [Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset](https://mlsanity.com/paper/1912.05008/) (2019)
- [Effective Sequence-to-Sequence Dialogue State Tracking](https://mlsanity.com/paper/2108.13990/) (2021)
- [Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networks](https://mlsanity.com/paper/1808.09238/) (2018)
- [Fine-tuning BERT for Joint Entity and Relation Extraction in Chinese Medical Text](https://mlsanity.com/paper/1908.07721/) (2019)
- [GePpeTto Carves Italian into a Language Model](https://mlsanity.com/paper/2004.14253/) (2020)
- [Multi-task dialog act and sentiment recognition on Mastodon](https://mlsanity.com/paper/1807.05013/) (2018)
- [Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model](https://mlsanity.com/paper/2111.09634/) (2021)
- [Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction](https://mlsanity.com/paper/2106.09790/) (2021)
- [Stack-propagation: Improved Representation Learning for Syntax](https://mlsanity.com/paper/1603.06598/) (2016)
- [Annotation of Emotion Carriers in Personal Narratives](https://mlsanity.com/paper/2002.12196/) (2020)

## Abstract (arXiv)

The valence analysis of speakers' utterances or written posts helps to understand the activation and variations of the emotional state throughout the conversation. More recently, the concept of Emotion Carriers (EC) has been introduced to explain the emotion felt by the speaker and its manifestations. In this work, we investigate the natural inter-dependency of valence and ECs via a multi-task learning approach. We experiment with Pre-trained Language Models (PLM) for single-task, two-step, and joint settings for the valence and EC prediction tasks. We compare and evaluate the performance of generative (GPT-2) and discriminative (BERT) architectures in each setting. We observed that providing the ground truth label of one task improves the prediction performance of the models in the other task. We further observed that the discriminative model achieves the best trade-off of valence and EC prediction tasks in the joint prediction setting. As a result, we attain a single model that performs both tasks, thus, saving computation resources at training and inference times.