Identifying negative or speculative narrative frag- ments from facts is crucial for deep understanding on natu- ral language processing （NLP）. In this paper, we firstly con- struct a Chinese corpus which consists of three sub-corpora from different resources. We also present a general framework for Chinese negation and speculation identification. In our method, first, we propose a feature-based sequence labeling model to detect the negative or speculative cues. In addition, a cross-lingual cue expansion strategy is proposed to increase the coverage in cue detection. On this basis, this paper presents a new syntactic structure-based framework to identify the linguistic scope of a negative or speculative cue, instead of the traditional chunking-based framework. Experimental results justify the usefulness of our Chinese corpus and the appropriateness of our syntactic structure-based framework which has showed significant improvement over the state-of-the-art on Chinese negation and speculation identification.
篇章是论元经过语义关联和结构化组织形成的自然语言文体.篇章分析研究的核心任务之一是解释论元的语义关系,其中,显式关系因具有直观线索而易于检测,目前检测精度高达90%;相对而言,隐式关系因缺乏直观线索而难于检测,目前精度仅约40%.针对这一问题,基于一种"论元平行则关系平行"的假设,并利用显式篇章关系易于检测的特点,通过平行论元的识别与平行关系的消歧,实现了一种显式关系平行推理隐式关系的隐式篇章关系检测方法.利用标准宾州篇章关系树库(Penn discourse Tree Bank,简称PDTB)对这一检测方法进行评测,结果显示,精确率提升达17.26%.
