RI: EAGER: Exploratory Research on Acquiring and Adapting Sentence Planning Resources for Generating with Discourse Combinatory Categorial Grammar

自然语言生成(NLG)系统旨在通过自动将数据转换为连贯流畅的文本或语音来提高信息的可及性和影响力。然而，开发高质量的NLG系统仍然是一项困难和昂贵的任务，很大程度上是因为弥合内容规划和表面实现之间的差距-这项任务被称为文本{句子规划}-仍然需要广泛的知识工程。这项早期的探索性研究拨款通过使用机器学习和语篇组合范畴语法(DCCG)来研究如何弥合这一差距。以一个餐厅推荐应用程序作为概念验证，该项目探索了以下方法：(1)调整先前获取用于语义分析的词汇化文法条目的工作，以学习从领域通用的语义依存表示到特定于应用的消息表示的映射；(2)扩展学习组合消息的规则的方法；(3)利用获得的资源将内容计划映射到析取逻辑形式(DFL)，其紧凑地指定所选内容的可能实现的范围；以及(4)通过语法专门化提高OpenCCG实现DFL的效率。项目将评估这些新方法的成功并评估该方法的可移植性。通过展示从根本上简化NLG系统建设的方法，该项目有望改变NLG系统的构建方式，从今天的知识密集型方法转变为主要依赖于组装平行的输入-输出对语料库的方法。归根结底，它将促进数据到文本系统以及对话系统中生成组件的开发，包括为视障人士开发的组件。

Natural Language Generation (NLG) systems aim to improve the accessibility and impact of information by turning data into coherent and fluent text or speech, automatically. Developing high-quality NLG systems, however, remains a difficult and costly undertaking, in large part because bridging the gap between content planning and surface realization---a task known as \textit{sentence planning}---continues to require extensive knowledge engineering.This Early Grant for Exploratory Research investigates ways of bridging this gap by employing machine learning together with Discourse Combinatory Categorial Grammar (DCCG). Using a restaurant recommendation application as a proof-of-concept, the project explores methods of (1) adapting previous work on acquiring lexicalized grammar entries for semantic parsing to learn mappings from domain-general semantic dependency representations to application-specific representations of messages; (2) extending the approach to learn rules for combining messages; (3) employing the acquired resources to map content plans to disjunctive logical forms (DLFs), which compactly specify the range of possible realizations of the selected content; and (4) improving the efficiency of realizing DLFs with OpenCCG through grammar specialization.The project will evaluate the success of these novel methods and assess the portability of the approach. By demonstrating methods for radically simplifying the construction of NLG systems, the project promises to transform the way NLG systems are built, from today's knowledge-intensive approach to one that relies primarily on assembling a parallel corpus of input-output pairs. Ultimately, it will facilitate the development of generation components in data-to-text systems as well as dialogue systems, including ones for the visually impaired.