III: Small: Interactive Construction of Complex Query Models

这个研究项目将调查并实现SearchIE，这是一种基于搜索的信息“提取”方法。SearchIE将允许快速、个性化、情景地识别文本中的对象或动作的类型，这些类型可能对复杂的搜索任务有用。现代搜索引擎通常提供某种机制，以指示仅当查询关键字出现在人名或位置中时，该关键字才与文档匹配。为了实现这一点，注释员在文本中找到并标记了大量的人名(例如)，应用了机器学习算法来学习哪些低级特征指示名称类型，然后在文档集合中运行该类型的结果分类器。然后，就可以编写一个表示“巴黎用作人名而不是地点”的查询。不幸的是，现有的方法并不适用于对新的、意想不到的类型感兴趣的搜索者--例如捕鲸船的名字、维多利亚女王海军的军官、当地的酒吧。目前还不能处理这样的例子，因为分类器需要提前训练和运行，这是一个昂贵的数据标记过程，对于许多搜索任务来说太令人望而生畏。由于在线信息收集几乎总是从搜索开始，并且经常涉及在找到的文本中识别感兴趣的项目，因此将这两者结合在一起有可能使两者都发生实质性的变化。SearchIE方法使人们可以根据他们的主题兴趣构建个性化的提取程序。其结果是，这项技术可以显著减少将查询集中到相关信息所需的时间，从而从根本上改善对外行和专业人士的在线搜索。似乎从未将信息提取任务直接作为搜索任务来处理。SearchIE在将信息检索(搜索)思维引入提取问题方面是独一无二的，它提供了新的功能，这些功能要么是不可能的，要么是在传统的“注释然后检测”问题模型中极其困难的。这个项目将调查SearchIE方法提出的基本问题。哪些模型可以在新的环境中最好地集成提取和搜索，在新的环境中它们可以真正同时发生？搜索者如何描述和编辑感兴趣类型的模型？交互开发的模型可以成为机器学习模型的跳板吗？什么时候有足够的信息来做到这一点？使用主题上下文来限制提取的范围是否提供了使用SearchIE的方法预期的准确度收益？需要对数据结构进行哪些修改才能完全实现SearchIE，从而使其既高效又有效？这种方法在其他标准测试集合上的表现如何？解决系统和算法问题是可能对搜索和提取产生重大影响的根本性问题。欲了解更多信息，请访问该项目的网站http://ciir.cs.umass.edu/research/searchie.

This research program will investigate and implement SearchIE, a search-based approach to information "extraction." SearchIE will allow rapid, personalized, situational identification of types of objects or actions in text, where those types are likely to be useful for a complex search task. Modern search engines often provide some mechanism to indicate that a query keyword matches a document only if it occurs in the name of a person or in a location. To make that possible, annotators found and marked a large number of people names (for example) in text, a machine learning algorithm was applied to learn which low-level features are indicative of the name type, and then a resulting classifier for that type is run across the collection of documents. It is then possible to write a query that means "paris used as a person's name rather than a location." Unfortunately, the existing approaches do not serve searchers interested in novel, unanticipated types - for example, names of whaling ships, officers in Queen Victoria's navy, local watering holes. Such examples cannot be handled currently because the classifiers need to be trained and run ahead of time, an expensive data labeling process that is too daunting for many search tasks. Since on-line information gathering almost always starts with search and frequently involves identifying items of interest in the found text, bringing these two together has the potential to change both substantially. The SearchIE approach makes it possible for someone to build personalized extractors contextualized by their topical interests. The result is that the technology can radically improve online searching for lay persons as well as professionals by significantly reducing the time needed to focus queries into relevant information. It does not appear that the information extraction task has ever been approached directly as a search task. SearchIE is unique in bringing an information retrieval (search) mindset to the extraction problem, providing new capabilities that are either impossible or extremely difficult in the traditional "annotate then detect" model of the problem. This project will investigate the fundamental issues raised by the SearchIE approach. What models can best integrate extraction and search in new settings where they can truly happen simultaneously? How can a searcher describe and edit a model for the types of interest? Can an interactively developed model be a springboard into a machine learned model and when is there enough information to do that? Does using topical context to limit the scope of extraction provide the expected accuracy gains using SearchIE's approach? What data structure modifications are needed to fully implement SearchIE so that it is efficient as well as effective? How well does this approach fare on additional standard test collections? Addressing the systems and algorithmic issues are fundamental problems that have the potential to greatly impact both search and extraction. For further information, see the project's web site at http://ciir.cs.umass.edu/research/searchie.