# How About Kind of Generating Hedges using End-to-End Neural Models?

arXiv: https://arxiv.org/abs/2306.14696 · HTML: https://mlsanity.com/paper/2306.14696/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 72 references that are in the map.
- First posted on arXiv 26 Jun 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [What makes a good conversation? How controllable attributes affect human judgments](https://mlsanity.com/paper/1902.08654/) (2019)
- [Politeness Transfer: A Tag and Generate Approach](https://mlsanity.com/paper/2004.14257/) (2020)
- [Polite Dialogue Generation Without Parallel Data](https://mlsanity.com/paper/1805.03162/) (2018)
- [Incremental Transformer with Deliberation Decoder for Document Grounded Conversations](https://mlsanity.com/paper/1907.08854/) (2019)
- [Inducing Positive Perspectives with Text Reframing](https://mlsanity.com/paper/2204.02952/) (2022)
- [The Teacher-Student Chatroom Corpus](https://mlsanity.com/paper/2011.07109/) (2020)
- ["You might think about slightly revising the title": identifying hedges in peer-tutoring interactions](https://mlsanity.com/paper/2306.14911/) (2023)
- [Enhancing Self-Disclosure In Neural Dialog Models By Candidate Re-ranking](https://mlsanity.com/paper/2109.05090/) (2021)

## Built on by (most cited first, 3 of 3)

- [EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics](https://mlsanity.com/paper/2408.08782/) (2024)
- [When to generate hedges in peer-tutoring interactions](https://mlsanity.com/paper/2307.15582/) (2023)
- [Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems](https://mlsanity.com/paper/2412.04492/) (2024)

## Abstract (arXiv)

Hedging is a strategy for softening the impact of a statement in conversation. In reducing the strength of an expression, it may help to avoid embarrassment (more technically, ``face threat'') to one's listener. For this reason, it is often found in contexts of instruction, such as tutoring. In this work, we develop a model of hedge generation based on i) fine-tuning state-of-the-art language models trained on human-human tutoring data, followed by ii) reranking to select the candidate that best matches the expected hedging strategy within a candidate pool using a hedge classifier. We apply this method to a natural peer-tutoring corpus containing a significant number of disfluencies, repetitions, and repairs. The results show that generation in this noisy environment is feasible with reranking. By conducting an error analysis for both approaches, we reveal the challenges faced by systems attempting to accomplish both social and task-oriented goals in conversation.