SBIR Phase II: Building a Flexible, Technology Adaptive Architecture to Support Processing of Content by Knowledge Workers

这个小企业创新研究（SBIR）第二阶段项目解决了当今语义分析系统的能力与公共关系、外交事务和危机管理等语言敏感领域的知识工作者（分析师和研究人员）的准确性要求之间的差距。许多组织中的知识工作者监控和分析印刷品和网络报道，以获取感兴趣的内容。当搜索结果量很大时，一些人使用基于语义分析技术的产品或系统对结果进行过滤、分类和评分，这些技术利用了大量的单词、模式和特定于上下文的算法库。然而，用户抱怨这些系统没有达到预期的准确性，缺少反讽、讽刺、隐喻、双关语等修辞手段，以及不正确地解释情绪和话题之间的联系。因此，对准确性要求较高的用户转而使用手动流程来补充或替代技术。在第一阶段工作的基础上，公司将创建和集成更大的内容处理模块集，并增强可插拔架构，以支持在内容处理“管道”中快速插入和测试新模块。一旦商业化，该系统将使知识工作者更快地采用技术。在精度要求较高的领域，对人工判断的需求限制了技术在搜索等离散领域的使用，而在随后的处理步骤中，分析人员必须手动捕获、分类、评分、分析和报告输出。迄今为止的反馈表明，该产品可以大大提高这些领域的专业人员的生产力和效率，并解决了市场上一些令人沮丧的差距。

This Small Business Innovation Research (SBIR) Phase II Project addresses the gap between the capabilities of today's semantic analysis systems and the accuracy requirements of knowledge workers (analysts and researchers) in language-sensitive fields such as public relations, foreign affairs, and crisis management. Knowledge workers in many organizations monitor and analyze print and web coverage for content of interest. When the volume of search results is large, some filter, classify and score the results using products or systems based on semantic analysis technology utilizing extensive libraries of words, patterns, and context-specific algorithms. However, users complain that these systems fall short of desired accuracy, missing rhetorical devices such as irony, sarcasm, metaphors, double entendre, and improperly interpreting connections between sentiment and topics. Users with high thresholds for accuracy thus turn to manual processes to either supplement or substitute for technology. Building upon Phase I work, the company will create and integrate a larger set of content processing modules and enhance a pluggable architecture to support quick insertion and testing of new modules in the content processing "pipeline." Once commercialized, the system will enable more rapid adoption of technology by knowledge workers. In fields with high accuracy requirements, the need for human judgment has constrained technology use to discrete areas like search, while in subsequent processing steps, analysts must manually capture, classify, score, analyze, and report on the output. Feedback to date suggests the product can substantially enhance the productivity and effectiveness of professionals in these fields and that it addresses a number of frustrating gaps in the marketplace.