Template Guided Text Generation for Task Oriented Dialogue

By Mihir Kale, Abhinav Rastogi. 2020

84 citations recorded by the source corpus.

Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language. In this work, we investigate two methods for Natural Language Generation (NLG) using a single domain-independent model across a large number of APIs. First, we propose a schema-guided approach which conditions the generation on a schema describing the API in natural language. Our second method investigates the use of a small number of templates, growing linearly in number of slots, to convey the semantics of the API. To generate utterances for an arbitrary slot combination, a few simple templates are first concatenated to give a semantically correct, but possibly incoherent and ungrammatical utterance. A pre-trained language model is subsequently employed to rewrite it into coherent, natural sounding text. Through automatic metrics and human evaluation, we show that our method improves over strong baselines, is robust to out-of-domain inputs and shows improved sample efficiency.

Subfields: 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 Natural Language Processing

Citations in the corpus

Structure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task (2021, methodology): “Following Kale and Rastogi (2020), we also tried converting the inputs into semi-natural text (Table 2) using their templates.”
CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems (2021, methodology): “We use the same 5/10-shot training split as in Kale and Rastogi (2020a) because they both contain utterances for every dialog act and slot present in the full training set.”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Visual Dialogue Kamezawa et al. (2020) PhotoBook A dataset for task-oriented visual dialogues.”
Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems (2020, methodology): “C L ] 2 0 A ug 2 02 0 Further, a template rewriting schema based on T5 (Raffel et al., 2019) was developed by Kale and Rastogi (2020) for few-shot NLG in two wellknown datasets.”
Towards Table-to-Text Generation with Numerical Reasoning (2021, methodology): “T is converted to a ﬂat string P T = w 1 , ..., w | P T | , similar to that used in many prior work (Wang et al., 2020; Chen et al., 2020a; Kale and Rastogi, 2020b), where w i denotes the i -th word in para-graph P T with length | P T | .”
Pre-Trained Language Models for Text Generation: A Survey (2022, result): “[87] further designed a manual schema to better convert previous results into a natural language.”
A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models (2022, unknown): “…Input:dialoguecontent,additionalstructural information(e.g.,persona,emotion,intent,template,etc.) Output:Dialogueresponse Persona[126,127,157,167,168] politeness[36,92],Sentiment[35,113,129,145], Template[55,139], ground-truthreference[97,105,109,147] Storytelling Input:Storyelements”