No abstract

In real-world question-answering (QA) systems, ill-formed questions, such as wrong words, ill word order and noisy expressions, are common and may prevent the QA systems from understanding and answering accurately. In order to eliminate the effect of ill-formed questions, we approach the question refinement task and propose a unified model, Qrefine, to refine the ill-formed questions to well-formed questions. The basic idea is to learn a Seq2Seq model to generate a new question from the original one.To improve the quality and retrieval performance of the generated questions, we make two major improvements: 1) To better encode the semantics of ill-formed questions, we enrich the representation of questions with character embedding and the contextual word embedding such as BERT, besides the traditional context-free word embeddings; 2) To make it capable to generate desired questions, we train the model with deep reinforcement learning techniques that consider an appropriate wording of the generation as an immediate reward and the correlation between generated question and answer as time-delayed long-term rewards. Experimental results on real-world datasets show that the proposed Qrefine can generate refined questions with high readability but fewer mistakes than original questions provided by users. Moreover, the refined questions also significantly improve the accuracy of answer retrieval.

No abstract

This paper reports the submitted discourse relation classification systems of the language information processing group of Beijing Institute of Technology (BIT) to the CoNLL-2016 shared task. In this work, discriminative methods were employed according to the different characteristics of English and Chinese discourse structures. Additionally, distributed representations were introduced to catch the deep semantic relations. Experiments shows their effectiveness on both English and Chinese tasks.

No abstract