Mengqiu Wang

Learn More
This paper presents a syntax-driven approach to question answering, specifically the answer-sentence selection problem for short-answer questions. Rather than using syntactic features to augment existing statistical classifiers (as in previous work), we build on the idea that questions and their (correct) answers relate to each other via loose but(More)
SAVE: Source Address Validity Enforcement Protocol Jun Li Jelena Mirkovic Mengqiu Wang Peter Reiher Lixia Zhang ABSTRACT Many network attacks forge the source address in their IP packets to block traceback. Recently, research activity has focused on packet-tracing mechanisms to counter this deception. Unfortunately, these mechanisms are either too expensive(More)
A range of Natural Language Processing tasks involve making judgments about the semantic relatedness of a pair of sentences, such as Recognizing Textual Entailment (RTE) and answer selection for Question Answering (QA). A key challenge that these tasks face in common is the lack of explicit alignment annotation between a sentence pair. We capture the(More)
Different languages contain complementary cues about entities, which can be used to improve Named Entity Recognition (NER) systems. We propose a method that formulates the problem of exploring such signals on unannotated bilingual text as a simple Integer Linear Program, which encourages entity tags to agree via bilingual constraints. Bilingual NER(More)
While social interactions are critical to understanding consumer behavior, the relationship between social and commerce networks has not been explored on a large scale. We analyze Taobao, a Chinese consumer marketplace that is the world's largest e-commerce website. What sets Taobao apart from its competitors is its integrated instant messaging tool, which(More)
Many problems in NLP require solving a cascade of subtasks. Traditional pipeline approaches yield to error propagation and prohibit joint training/decoding between subtasks. Existing solutions to this problem do not guarantee non-violation of hard-constraints imposed by subtasks and thus give rise to inconsistent results, especially in cases where(More)
NLP models have many and sparse features, and regularization is key for balancing model overfitting versus underfitting. A recently repopularized form of regularization is to generate fake training data by repeatedly adding noise to real data. We reinterpret this noising as an explicit regularizer, and approximate it with a second-order formula that can be(More)
This paper discusses a general architecture for intelligent software agents. It can be used to construct agents that engage in high-level reasoning by employing standard reasoning engines as plug-in components, while communicating with other agents by means of the standard FIPA-based communication protocols. The approach discussed uses internal micro-agents(More)