Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning

10/04/2020
by   Yifan Gao, et al.
0

Sentence function is an important linguistic feature indicating the communicative purpose in uttering a sentence. Incorporating sentence functions into conversations has shown improvements in the quality of generated responses. However, the number of utterances for different types of fine-grained sentence functions is extremely imbalanced. Besides a small number of high-resource sentence functions, a large portion of sentence functions is infrequent. Consequently, dialogue generation conditioned on these infrequent sentence functions suffers from data deficiency. In this paper, we investigate a structured meta-learning (SML) approach for dialogue generation on infrequent sentence functions. We treat dialogue generation conditioned on different sentence functions as separate tasks, and apply model-agnostic meta-learning to high-resource sentence functions data. Furthermore, SML enhances meta-learning effectiveness by promoting knowledge customization among different sentence functions but simultaneously preserving knowledge generalization for similar sentence functions. Experimental results demonstrate that SML not only improves the informativeness and relevance of generated responses, but also can generate responses consistent with the target sentence functions.

READ FULL TEXT
research
07/24/2019

Fine-Grained Sentence Functions for Short-Text Conversation

Sentence function is an important linguistic feature referring to a user...
research
05/14/2019

Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems

Natural language generation (NLG) is an essential component of task-orie...
research
08/07/2021

Generating Personalized Dialogue via Multi-Task Meta-Learning

Conventional approaches to personalized dialogue generation typically re...
research
04/30/2017

Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

Different from other sequential data, sentences in natural language are ...
research
09/10/2021

Knowledge-Aware Meta-learning for Low-Resource Text Classification

Meta-learning has achieved great success in leveraging the historical le...
research
12/22/2020

Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation

Human doctors with well-structured medical knowledge can diagnose a dise...
research
10/22/2022

MetaASSIST: Robust Dialogue State Tracking with Meta Learning

Existing dialogue datasets contain lots of noise in their state annotati...

Please sign up or login with your details

Forgot password? Click here to reset