In order to fuse word-level and sentence-level information from different semantic spaces, the authors propose a hybrid optimization framework to optimize word-level information while simultaneously incorporate sentence-level information as constraints. The optimization is conducted by iterative unit substitutions. The performance on DUC benchmark datasets demonstrates the effectiveness of proposed framework in terms of ROUGE evaluation.

A framework to transform natural language questions into computer-understoodable structured queries is presented. The authors propose to use query semantic graph to represent the semantics in Chinese questions, and adopt predicate and entity disambiguation to match the query graph to the schema of a knowledge base. The authors collect a benchmark of 42 frequently-asked questions randomly sampled from 3 categories of Baidu Knows, including person, location and organization. Experiment results show that proposed framework can effectively convert natural language questions into SPARQL queries, and lay a good foundation for the next generation of intelligent question answering systems.

The authors propose a new method C-TERN to recognize and normalize the temporal expression in military story based on cascade finite state automata. Firstly, C-TERN recognizes the temporal expression in military story, and layers the temporal information extracted from general language and military language, and recognizes the temporal by layer. Then, in the procedure of temporal expression normalization, C-TERN ratiocinates and normalizes the simple/specify time, duration time, absolute and relative temporal expression in four steps. The method pays special attention to the correctness of the regulation extraction, the dispelling of the collision between regulations, and the reasonability of the matching method. The experimental results on multi-information show that proposed method can recognize and normalize the absolute and relative temporal expression as well as the simple/specify time and duration time effectively. It can better meets the temporal information processing needs in military applications.

The authors concentrate on exploiting the background knowledge to address the semantic analysis in content-based filtering. An Ontology Based Similarity Model (OBSM) is proposed to calculate the news-user similarity through collaboratively built ontological structures. In order to deal with the noisy nature of these coarse-grained structures, an ontology based clustering model is introduced into the framework, called X-OBSM, which clusters concepts of a user profile on a coarse-grained ontology. Experiment results show that both OBSM and X-OBSM outperform the baselines by a large margin, specifically, X-OBSM performs better than OBSM in both quality and efficiency.

The authors propose an approach to extract topic sentences that describe key event from a news article. Considering the special structure of news articles, the relations between news articles and key events reported in them is studied, as well as the characteristics of a news headline in three aspects: information, form and language. A novel method based on the information aspect of a headline is used to extract a topic sentence which contains the key event information from a news story. The method first classifies a news headline as informative or non-informative, and then considers text and semantic features of a sentence, such as word frequency, sentence length, location in the text and word co-concurrency with the headline, to evaluate the importance for each sentence and select the most important one as the topic sentence. Experiment results show that this method can identify a topic sentence accurately and the proposed approach makes a good preparation for event information extraction.