Xiaojiang Liu

Learn More
Traditional relation extraction methods require pre-specified relations and relation-specific human-tagged examples. Bootstrapping systems significantly reduce the number of training examples, but they usually apply heuristic-based methods to combine a set of strict hard rules, which limit the ability to generalize and thus generate a low recall.(More)
Internet users regularly have the need to find biographies and facts of people of interest. Wikipedia has become the first stop for celebrity biographies and facts. However, Wikipedia can only provide information for celebrities because of its neutral point of view (NPOV) editorial policy. In this paper we propose an integrated bootstrapping framework named(More)
This paper presents a semantic parsing and reasoning approach to automatically solving math word problems. A new meaning representation language is designed to bridge natural language text and math expressions. A CFG parser is implemented based on 9,600 semi-automatically created grammar rules. We conduct experiments on a test set of over 1,500 number word(More)
The two most important tasks in entity information summarization from the Web are named entity recognition and relation extraction. Little work has been done toward an integrated statistical model for understanding both named entities and their relationships. Most of the previous works on relation extraction assume the named entities are pre-given. The(More)
Web-scale relation extraction is crucial to building the Web people search engines. Previous extraction models, such as Snowball, focus only on single type extraction, while the real applications always require as many as possible types of relation. In this paper, we propose a novel Web-scale relation extraction framework Multi-Type Snowball(More)
End-to-end delay guarantees are critical to many delay-sensitive applications. To ensure such a guarantee on a flow path, the existing approaches usually statically divide its end-to-end delay requirement into per-hop delay requirements. However, such static path-level resource allocations often cause unbalanced resource reservations and bottlenecks in a(More)
In this thesis, we present an analytical framework to provide statistical end-ta-end delay guarantees to network traffic with a novel packet scheduling scheme, namely the Global multi-hop Scheduling (GMS). We first introduce background literature, then present the framework and performance analysis of this proposed scheduling mechanism, which considers(More)
In this paper, 4-(dicyanomethylene)-2-t-butyl-6(1,1,7,7-tetramethyljulolidyl-9-enyl)-4H-pyran (DCJTB) has been used in interface modification of dye-sensitized solar cells (DSCs) with combined effects of retarding charge recombination and Förster resonant energy transfer (FRET). DCJTB interface modification significantly improved photovoltaic performance of(More)
INTRODUCTION In order to evaluate water quality of a canal system, the spatial pattern of protozoan communities in response to physicochemical variables was studied in the Hangzhou section of the Grand Canal, northern China during a 1-year cycle (February 2008-January 2009). MATERIALS AND METHODS Protozoan samples were monthly collected at six sampling(More)
This paper presents a deep neural solver to automatically solve math word problems. In contrast to previous statistical learning approaches, we directly translate math word problems to equation templates using a recurrent neural network (RNN) model, without sophisticated feature engineering. We further design a hybrid model that combines the RNN model and a(More)