SMILE: Single-turn to Multi-turn Inclusive Language Expansion via
ChatGPT for Mental Health Support
- URL: http://arxiv.org/abs/2305.00450v2
- Date: Thu, 22 Feb 2024 10:21:56 GMT
- Title: SMILE: Single-turn to Multi-turn Inclusive Language Expansion via
ChatGPT for Mental Health Support
- Authors: Huachuan Qiu, Hongliang He, Shuai Zhang, Anqi Li, Zhenzhong Lan
- Abstract summary: We introduce SMILE, a single-turn to multi-turn inclusive language expansion technique that prompts ChatGPT to rewrite public single-turn dialogues into multi-turn ones.
We generate a large-scale, diverse, and high-quality dialogue dataset named SmileChat comprising 55,165 dialogues in total with an average of 10.4 turns per dialogue.
To better assess the overall quality of SmileChat, we collect a real-life chat dataset comprising 82 counseling dialogues for model evaluation.
- Score: 28.370263099251638
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Developing specialized dialogue systems for mental health support requires
multi-turn conversation data, which has recently garnered increasing attention.
However, gathering and releasing large-scale and real-life multi-turn
conversations to facilitate advancements in mental health presents challenges
due to data privacy protection, as well as the time and cost involved. To
address the challenges related to data scarcity, we introduce SMILE, a
single-turn to multi-turn inclusive language expansion technique that prompts
ChatGPT to rewrite public single-turn dialogues into multi-turn ones. Our work
begins with the analysis of language transformation, validating the feasibility
of the proposed method when compared with other baseline methods. We then
conduct a study on dialogue diversity, including lexical features, semantic
features, and dialogue topics, demonstrating the effectiveness of our proposed
method. Furthermore, we implement an expert evaluation and the results
demonstrate that the dialogues generated with our proposed method are of higher
quality than those generated with other baseline methods. Thus, we employ our
method to generate a large-scale, diverse, and high-quality dialogue dataset
named SmileChat, comprising 55,165 dialogues in total with an average of 10.4
turns per dialogue. Finally, we utilize the collected corpus to develop a
mental health chatbot, MeChat. To better assess the overall quality of
SmileChat, we collect a real-life chat dataset comprising 82 counseling
dialogues for model evaluation. Both automatic and human evaluations
demonstrate that our trained dialogue system exhibits significant improvements,
showcasing that SmileChat is high-quality and practical.
Related papers
- Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting [46.919537239016734]
Large language models (LLMs) have simplified the implementation of multi-turn dialogues.
It remains challenging to deliver satisfactory performance in low-resource domain, like psychological dialogue dialogue.
We propose a knowledge-driven progressive thought prompting method to guide LLM to generate psychology-related dialogue.
arXiv Detail & Related papers (2024-06-24T12:02:56Z) - BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues [72.65163468440434]
This report provides a preliminary evaluation of existing large language models for human-style multi-turn chatting.
We prompt large language models (LLMs) to generate a full multi-turn dialogue based on the ChatSEED, utterance by utterance.
We find GPT-4 can generate human-style multi-turn dialogues with impressive quality, significantly outperforms its counterparts.
arXiv Detail & Related papers (2023-10-20T16:53:51Z) - Response-act Guided Reinforced Dialogue Generation for Mental Health
Counseling [25.524804770124145]
We present READER, a dialogue-act guided response generator for mental health counseling conversations.
READER is built on transformer to jointly predict a potential dialogue-act d(t+1) for the next utterance (aka response-act) and to generate an appropriate response u(t+1)
We evaluate READER on HOPE, a benchmark counseling conversation dataset.
arXiv Detail & Related papers (2023-01-30T08:53:35Z) - Emotion Recognition in Conversation using Probabilistic Soft Logic [17.62924003652853]
emotion recognition in conversation (ERC) is a sub-field of emotion recognition that focuses on conversations that contain two or more utterances.
We implement our approach in a framework called Probabilistic Soft Logic (PSL), a declarative templating language.
PSL provides functionality for the incorporation of results from neural models into PSL models.
We compare our method with state-of-the-art purely neural ERC systems, and see almost a 20% improvement.
arXiv Detail & Related papers (2022-07-14T23:59:06Z) - HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on
Tabular and Textual Data [87.67278915655712]
We present a new dialogue dataset, HybriDialogue, which consists of crowdsourced natural conversations grounded on both Wikipedia text and tables.
The conversations are created through the decomposition of complex multihop questions into simple, realistic multiturn dialogue interactions.
arXiv Detail & Related papers (2022-04-28T00:52:16Z) - Speaker and Time-aware Joint Contextual Learning for Dialogue-act
Classification in Counselling Conversations [15.230185998553159]
We develop a novel dataset, named HOPE, to provide a platform for the dialogue-act classification in counselling conversations.
We collect 12.9K utterances from publicly-available counselling session videos on YouTube, extract their transcripts, clean, and annotate them with DAC labels.
We propose SPARTA, a transformer-based architecture with a novel speaker- and time-aware contextual learning for the dialogue-act classification.
arXiv Detail & Related papers (2021-11-12T10:30:30Z) - Dialogue History Matters! Personalized Response Selectionin Multi-turn
Retrieval-based Chatbots [62.295373408415365]
We propose a personalized hybrid matching network (PHMN) for context-response matching.
Our contributions are two-fold: 1) our model extracts personalized wording behaviors from user-specific dialogue history as extra matching information.
We evaluate our model on two large datasets with user identification, i.e., personalized dialogue Corpus Ubuntu (P- Ubuntu) and personalized Weibo dataset (P-Weibo)
arXiv Detail & Related papers (2021-03-17T09:42:11Z) - Rethinking Dialogue State Tracking with Reasoning [76.0991910623001]
This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data.
Empirical results demonstrate that our method significantly outperforms the state-of-the-art methods by 38.6% in terms of joint belief accuracy for MultiWOZ 2.1.
arXiv Detail & Related papers (2020-05-27T02:05:33Z) - TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented
Dialogue [113.45485470103762]
In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling.
To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling.
arXiv Detail & Related papers (2020-04-15T04:09:05Z) - You Impress Me: Dialogue Generation via Mutual Persona Perception [62.89449096369027]
The research in cognitive science suggests that understanding is an essential signal for a high-quality chit-chat conversation.
Motivated by this, we propose P2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding.
arXiv Detail & Related papers (2020-04-11T12:51:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.