In this paper we present a bootstrapping approach for attribute value extraction that minimizes the need for human intervention. Our approach automatically extracts attribute names and values from semi-structured text, generates a small labelled dataset, and bootstraps it by extracting new values from unstructured text. It is domain/language-independent, relying only on existing semi-structured text to create the initial labeled dataset. We assess the impact of different machine learning approaches to increase precision of the core approach without compromising coverage. We perform an extensive evaluation using e-commerce product data across different categories in two languages and hundreds of thousands of product pages. We show that our approach provides high precision and good coverage. In addition, we study the impact of different methods that address specific sources of error. With error analysis we highlight how these methods complement each other, obtaining insights about the individual methods and the ensamble as a whole.

Traditional automatic question generation often requires hand-crafted templates or sophisticated NLP pipelines. Such approaches, however, require extensive labor and expertise to morphologically analyze the sentences and create the NLP framework. Our works aim to simplify these labors. We conduct a contrastive experiment between two types of sequence learning: statistical-based machine translation and attention-based sequence neural network. These models can be trained end-to-end, and it can capture the pattern between the input sequence and output sequence, thus diminishing the need to prepare a sophisticated NLP pipeline. Automatic evaluation results show that our system outperforms the state-of-the-art rule-based system, and also excels in terms of content quality and fluency according to a subjective human test.

Previous work on example-based chat-oriented dialog systems utilizing real human-to-human conversation has shown promising results. However, most previous methods use relatively simple retrieval techniques, resulting in weakness to out of vocabulary (OOV) database queries and inadequate handling of interactions between words in the sentence. To overcome this problem, in this paper we propose a method to utilize recursive neural network paraphrase identification to improve the accuracy and robustness of example-based dialog response retrieval. We model our dialog-pair database and user input query with distributed word representations, and employ recursive autoencoders and dynamic pooling to determine whether two sentences with arbitrary length have the same meaning. The distributed representations have the potential to improve handling of OOV cases, and the recursive structure can reduce confusion in example matching. We evaluate the system performance based on objective and subjective metrics.