Weigang Li’s research while affiliated with Harbin Institute of Technology and other places

A new approach of relation extraction is described in this paper. It adopts a bootstrapping model with a novel iteration strategy, which generates more precise examples of specific relation. Compared with previous methods, the proposed method has three main advantages: first, it needs less manual intervention; second, more abundant and reasonable information are introduced to represent a relation pattern; third, it reduces the risk of circular dependency occurrence in bootstrapping. Scalable evaluation methodology and metrics are developed for our task with comparable techniques over TianWang 100G corpus. The experimental results show that it can get 90% precision and have excellent expansibility.

Rather than creating and storing thou-sands of paraphrase examples, para-phrase templates have strong representation capacity and can be used to generate many paraphrase examples. This paper describes a new template representation and generalization method. Combing a semantic diction-ary, it uses multiple semantic codes to represent a paraphrase template. Using an existing search engine to extend the word clusters and generalize the exam-ples. We also design three metrics to measure our generalized templates. The experimental results show that the rep-resentation method is reasonable and the generalized templates have a higher precision and coverage.

Abundant Chinese paraphrasing resource on Internet can be attained from different Chinese translations of one foreign masterpiece. Paraphrases corpus is the corpus that includes sentence pairs to convey the same information. The irregular characteristics of the real monolingual parallel texts, especially without the strictly aligned paragraph boundaries between two translations, bring a challenge to alignment technology. The traditional alignment methods on bilingual texts have some difficulties in competency for doing this. A new method for aligning real monolingual parallel texts using sentence pair's length and location information is described in this paper. The model was motivated by the observation that the location of a sentence pair with certain length is distributed in the whole text similarly. And presently, a paraphrases corpus with about fifty thousand sentence pairs is constructed.