Learn More
Negative expressions are common in natural language text and play a critical role in information extraction. However, the performances of current systems are far from satisfaction, largely due to its focus on intrasentence information and its failure to consider inter-sentence information. In this paper, we propose a graph model to enrich intrasentence(More)
Scope detection is a key task in information extraction. This paper proposes a new approach for tree kernel-based scope detection by using the structured syntactic parse information. In addition, we have explored the way of selecting compatible features for different part-of-speech cues. Experiments on the BioScope corpus show that both constituent and(More)
This paper introduces the theory of algorithm results of different image processing techniques in lane marking line recognition, including binarize, edge detection and lane extraction. Analyze and compare the accuracy of the each stages of processing algorithms, reliability and real - time performance. And then compare the various combinations of algorithms(More)
Wei Zheng, Yu Zhang, Bowei Zou, Yu Hong, Ting Liu Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001 E-mail: {zw, zhangyu, bwzou hy, tliu}@ir.hit.edu.cn Abstract: As an important subtask of topic detection and tracking, topic tracking identifies and collects relevant stories on certain topics from information(More)
Identifying negative or speculative narrative fragments from facts is crucial for deep understanding on natural language processing (NLP). In this paper, we firstly construct 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,(More)
Due to the commonality in natural language, negation focus plays a critical role in deep understanding of context. However, existing studies for negation focus identification major on supervised learning which is timeconsuming and expensive due to manual preparation of annotated corpus. To address this problem, we propose an unsupervised word-topic graph(More)