How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue
Neural Natural Language Generation (NLG) systems are well known for their unreliability. To overcome this issue, we propose a data augmentation approach which allows us to restrict the output of a network and guarantee reliability. While this restriction means generation will be less diverse than if randomly sampled, we include experiments that demonstrate the tendency of existing neural generation approaches to produce dull and repetitive text, and we argue that reliability is more important than diversity for this task. The system trained using this approach scored 100{\%} in semantic accuracy on the E2E NLG Challenge dataset, the same as a template system.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDiversityText GenerationSimilar Papers 제목 키워드 기반
Harvesting Creative Templates for Generating Stylistically Varied Restaurant Reviews
Many of the creative and figurative elements that make language exciting are lost in translation in current natural language generation engines. In this paper, we explore a method to harvest templates from positive and n…
Text GenerationTranslationReusable Templates and Guides For Documenting Datasets and Models for Natural Language Processing and Generation: A Case Study of the HuggingFace and GEM Data and Model Cards
Developing documentation guidelines and easy-to-use templates for datasets and models is a challenging task, especially given the variety of backgrounds, skills, and incentives of the people involved in the building of n…
Text GenerationA Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation
Existing syntactically-controlled paraphrase generation (SPG) models perform promisingly with human-annotated or well-chosen syntactic templates. However, the difficulty of obtaining such templates actually hinders the p…
Data AugmentationDiversityParaphrase GenerationRetrieval+1RingSQL: Generating Synthetic Data with Schema-Independent Templates for Text-to-SQL Reasoning Models
Recent advances in text-to-SQL systems have been driven by larger models and improved datasets, yet progress is still limited by the scarcity of high-quality training data. Manual data creation is expensive, and existing…
Context-aware Natural Language Generation for Spoken Dialogue Systems
Natural language generation (NLG) is an important component of question answering(QA) systems which has a significant impact on system quality. Most tranditional QA systems based on templates or rules tend to generate ri…
Dialogue GenerationQuestion AnsweringSpoken Dialogue SystemsText Generation