RI: Small: Adapting a Natural Logic Reasoning Platform to the Task of Entailment Inference

目前的人工智能系统仍然缺乏处理语言语义的微妙性和人类话语和思维的主题广度所需的知识和推理能力。该项目正在开发一个用于强大的推理引擎（EPITALITY）的词汇和其他一般知识的基本库，该引擎旨在支持无限制的语言理解和推理。所采用的方法利用了对语言的洞察力，基于推理是近年来在“自然逻辑”领域取得的成果，它系统地利用了语言的词级和结构蕴涵特性。这些都很容易在EPITORY中建模，EPITORY使用类似语言的意义表示（情节逻辑）。一些非常普遍的语义属性正在被手动编码，此外，大量的知识项正在通过计算从词汇资源（如WordNet和VerbNet）以及来自大型文本语料库的单词相似性或释义集群中提取。预期的结果是基本词汇和其他常识知识的知识库，这将允许演示许多以前不可行的基于语言的推理，包括正向和反向推理以及现有测试套件中的许多多前提蕴涵推理。这将大大推进基本语言理解和机械化“明显推理”的最新技术水平，并可能应用于基于智能对话的代理（用于问答，辅导，个人帮助等），以及通过机器阅读的知识引导。研究结果将通过会议论文和期刊以及通过提供电子方案和新开发的知识库的网站加以传播。

Current AI systems still lack the knowledge and reasoning abilities needed to handle the semantic subtleties of language and the thematic breadth of human discourse and thinking.This project is developing a basic repertoire of lexical andother general knowledge for use in a powerful inference engine (EPILOG) designed expressly to support unrestricted language understanding and reasoning.The methods being employed exploit the insights into language-basedinference gained in recent years in the area of "natural Logic",which makes systematic use of word-level and structural entailmentproperties of language. These are easily modeled in EPILOG, whichuses a language-like meaning representation (Episodic Logic). Somevery general semantic properties are being manually encoded, and in addition, large numbers of knowledge items are being extractedcomputationally from lexical resources such as WordNet and VerbNet,and from word similarity or paraphrase clusters derived from large text corpora.The expected result is a knowledge base of fundamental lexical andother commonsense knowledge that will allow demonstration of manypreviously infeasible language-based inferences, including both forward and backward reasoning and many multi-premise entailment inferences in existing test suites. This will significantly advance the state of the art in basic language understanding and in mechanizing "obvious inferences", with potential applications to intelligent dialogue-based agents (for question answering, tutoring, personal assistance, etc.), and to knowledge bootstrapping through machine reading. The results will be disseminated both through papers at conferences and in journals, and through web sites making available EPILOG and the newly developed knowledge bases.