TAILIEUCHUNG - Báo cáo khoa học: "Unsupervised Detection of Downward-Entailing Operators By Maximizing Classification Certainty"

We propose an unsupervised, iterative method for detecting downward-entailing operators (DEOs), which are important for deducing entailment relations between sentences. Like the distillation algorithm of Danescu-Niculescu-Mizil et al. (2009), the initialization of our method depends on the correlation between DEOs and negative polarity items (NPIs). However, our method trusts the initialization more and aggressively separates likely DEOs from spurious distractors and other words, unlike distillation, which we show to be equivalent to one iteration of EM prior re-estimation. Our method is also amenable to a bootstrapping method that co-learns DEOs and NPIs, and achieves the best results in identifying. | Unsupervised Detection of Downward-Entailing Operators By Maximizing Classification Certainty Jackie CK Cheung and Gerald Penn Department of Computer Science University of Toronto Toronto ON M5S 3G4 Canada j cheung gpenn @ Abstract We propose an unsupervised iterative method for detecting downward-entailing operators DEOs which are important for deducing entailment relations between sentences. Like the distillation algorithm of Danescu-Niculescu-Mizil et al. 2009 the initialization of our method depends on the correlation between DEOs and negative polarity items NPIs . However our method trusts the initialization more and aggressively separates likely DEOs from spurious distractors and other words unlike distillation which we show to be equivalent to one iteration of EM prior re-estimation. Our method is also amenable to a bootstrapping method that co-learns DEOs and NPIs and achieves the best results in identifying DEOs in two corpora. 1 Introduction Reasoning about text has been a long-standing challenge in NLP and there has been considerable debate both on what constitutes inference and what techniques should be used to support inference. One task involving inference that has recently received much attention is that of recognizing textual entailment RTE in which the goal is to determine whether a hypothesis sentence can be entailed from a piece of source text Bentivogli et al. 2010 for example . An important consideration in RTE is whether a sentence or context produces an entailment relation for events that are a superset or subset of the original sentence MacCartney and Manning 2008 . By default contexts are upward-entailing allowing reasoning from a set of events to a superset of events as seen in 1 . In the scope of a downward-entailing operator DEO however this entailment relation is reversed such as in the scope of the classical DEO not 2 . There are also operators which are neither upward- nor downward entailing such as the expression .

• Báo cáo khoa học
• Unsupervised Detection
• Downward Entailing Operators
• Maximizing Classification Certainty
• scientific reports
• model language
• process natural language
• Journal of Computer Science and Cybernetics
• An evaluation method for unsupervised anomaly detection algorithms
• An evaluation method
• Unsupervised anomaly detection algorithms
• Intrusion detection in network security
• A Bootstrapping Approach
• Cue Phrase Variants
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• BMC Bioinformatics
• Cell detection
• Deep learning
• Semi supervised learning
• Unsupervised domain adaptation
• Generalization capabilities
• Social sciences and humanities
• Self reported experiences
• Corruption on twitter
• Unsupervised machine learning
• Natural language processing
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• Single cell
• Matrix factorization
• Pattern detection
• Unsupervised learning
• Anomaly detection
• Algorithmically generated domain names
• Malicious domain names
• Domain name modeling
• Fast flux
• Gene expression
• Intron evolution
• Transcript evolution
• RNA processing
• Coding sequence