Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network

By Yangming Li, Kaisheng Yao, Wanxiang Che, Xiaolong Li, Ting-Wei Liu. 2020

28 citations recorded by the source corpus.

Data-driven approaches using neural networks have achieved promising performances in natural language generation (NLG). However, neural generators are prone to make mistakes, e.g., neglecting an input slot value and generating a redundant slot value. Prior works refer this to hallucination phenomenon. In this paper, we study slot consistency for building reliable NLG systems with all slot values of input dialogue act (DA) properly generated in output sentences. We propose Iterative Rectification Network (IRN) for improving general NLG systems to produce both correct and fluent responses. It applies a bootstrapping algorithm to sample training candidates and uses reinforcement learning to incorporate discrete reward related to slot inconsistency into training. Comprehensive studies have been conducted on multiple benchmark datasets, showing that the proposed methods have significantly reduced the slot error rate (ERR) for all strong baselines. Human evaluations also have confirmed its effectiveness.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Pascale Fung
2. Andrea Madotto
3. Tom Young
4. Wenliang Dai
5. Nayeon Lee
6. Yan Xu
7. Etsuko Ishii
8. Ziwei Ji

In Natural Language Processing

1. Pascale Fung
2. Nayeon Lee
3. Andrea Madotto
4. Etsuko Ishii
5. Yejin Bang
6. Yan Xu
7. Rita Frieske
8. Dan Su

Citations in the corpus

• Survey of Hallucination in Natural Language Generation (2022, methodology): “Moreover, there are some broad metrics, such as Correctness [6, 11, 99, 186], Accuracy [98, 208], and Informativeness [103] considering both missing and additional contents (extrinsic hallucinations) compared to the input source.”
• Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Also tackling the data insufficiency problem, Li et al. (2020a) proposed a method that did not require context-knowledge-response triples for training.”