Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Detecting conflicting statements is a foundational text understanding task with applications in information analysis. We propose an appropriate definition of contradiction for NLP tasks and develop available corpora, from which we construct a typology of contradictions. We demonstrate that a system for contradiction needs to make more fine-grained distinctions than the common systems for entailment. In particular, we argue for the centrality of event coreference and therefore incorporate such a component based on topicality. We present the first detailed breakdown of performance on this task. . | Finding Contradictions in Text Marie-Catherine de Marneffe Anna N. Rafferty and Christopher D. Manning Linguistics Department Stanford University Stanford CA 94305 mcdm@stanford.edu Computer Science Department Stanford University Stanford CA 94305 rafferty manning @stanford.edu Abstract Detecting conflicting statements is a foundational text understanding task with applications in information analysis. We propose an appropriate definition of contradiction for NLP tasks and develop available corpora from which we construct a typology of contradictions. We demonstrate that a system for contradiction needs to make more fine-grained distinctions than the common systems for entailment. In particular we argue for the centrality of event coreference and therefore incorporate such a component based on topicality. We present the first detailed breakdown of performance on this task. Detecting some types of contradiction requires deeper inferential paths than our system is capable of but we achieve good performance on types arising from negation and antonymy. 1 Introduction In this paper we seek to understand the ways contradictions occur across texts and describe a system for automatically detecting such constructions. As a foundational task in text understanding Condoravdi et al. 2003 contradiction detection has many possible applications. Consider applying a contradiction detection system to political candidate debates by drawing attention to topics in which candidates have conflicting positions the system could enable voters to make more informed choices between candidates and sift through the amount of available information. Contradiction detection could also be applied to intelligence reports demonstrating which information may need further verification. In bioinfor matics where protein-protein interaction is widely studied automatically finding conflicting facts about such interactions would be beneficial. Here we shed light on the complex picture of contradiction in .
