Identifying Conflicting Information in Texts
نویسندگان
چکیده
Understanding relationships between text passages is key for information analysis. We focus here on the contradiction relationship, and build a system to detect conflicting statements. We show that such a system needs to make more fine-grained distinctions than the common systems for entailment. Also, we argue for the centrality of event coreference and therefore incorporate a component based on topicality. We propose a typology of contradictions that naturally arise in text, and give the first detailed breakdown of performance for the contradiction detection task. Although detecting some types of contradiction requires deeper inferential paths than our system is capable of, we achieve good performance on types arising from negation and antonymy.
منابع مشابه
Running head: GRAPHS AND CONFLICTING SCIENCE-RELATED TEXTS
When reading conflicting science-related texts, readers may attend to cues which allow them to assess plausibility. One such plausibility cue is the use of graphs in the texts, which are regarded as typical of ‘hard science’. The goal of our study was to investigate the effects of the presence of graphs on the perceived plausibility and situation model strength for conflicting science-related t...
متن کاملTowards a Better Understanding of Critiques about Ancient Texts using Argumentation
Ancient texts are interpreted by critics in order to assign them a given semantics. However, the semantics to be associated to these texts is not unique and different critics may have different conflicting opinions about their “correct” interpretation. In this paper, we propose to adopt argumentation theory, a technique to manage conflicting information, together with Semantic Web languages and...
متن کاملIdentifying Information Structure in Expository Texts
Identification of ‘information structure’ (organization of information within an utterance) is crucial for processing contextually-appropriate linguistic forms in many NLP systems. This paper presents a theory and a procedure to identify information structure in expository texts in English, and also an evaluation method that is used to validate the results of the identification process for real...
متن کاملAn Evaluation Method for Identifying Information Structure
To correctly deal with context-dependent linguistic forms in NLP systems, the literature has pointed out the importance of identifying ‘information structure’ (organization of information within an utterance). However, there has been no report of evaluating such procedures. This paper presents a noble evaluation procedure and compares three models of identifying information structure in exposit...
متن کاملCorpus-Based Thesaurus Construction for Image Retrieval in Specialist Domains
This paper explores the use of texts that are related to an image collection, also known as collateral texts, for building thesauri in specialist domains to aid in image retrieval. Corpus linguistic and information extraction methods are used for identifying key terms and semantic relationships in specialist texts that may be used for query expansion purposes. The specialist domain context impo...
متن کامل