# A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss

arXiv: https://arxiv.org/abs/2106.10619 · HTML: https://mlsanity.com/paper/2106.10619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 20 Jun 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation](https://mlsanity.com/paper/1703.09902/) (2017)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Adversarial Learning for Neural Dialogue Generation](https://mlsanity.com/paper/1701.06547/) (2017)
- [Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge](https://mlsanity.com/paper/1901.07931/) (2019)
- [Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/1704.00057/) (2017)
- [Learning an Unreferenced Metric for Online Dialogue Evaluation](https://mlsanity.com/paper/2005.00583/) (2020)
- [A Survey of Available Corpora for Building Data-Driven Dialogue Systems](https://mlsanity.com/paper/1512.05742/) (2015)
- [Extending Neural Generative Conversational Model using External Knowledge Sources](https://mlsanity.com/paper/1809.05524/) (2018)

## Abstract (arXiv)

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training objectives do not foster generating alternate responses to a context. But, the effects of minimizing an alternate training objective that fosters a model to generate alternate response and score it on semantic similarity has not been well studied. We hypothesize that a language generation model can improve on its diversity by learning to generate alternate text during training and minimizing a semantic loss as an auxiliary objective. We explore this idea on two different sized data sets on the task of next utterance generation in goal oriented dialogues. We make two observations (1) minimizing a semantic objective improved diversity in responses in the smaller data set (Frames) but only as-good-as minimizing the NLL in the larger data set (MultiWoZ) (2) large language model embeddings can be more useful as a semantic loss objective than as initialization for token embeddings.