Here, we want to show that the proposed reduction scheme improves the expected accuracy of the querying result. Let A represent the space of all possible matchings between the query and the target networks, where a matching a uniquely maps the query nodes VQ to a subgraph region in the target network. Besides, let a∗ be the (unknown) matching from A that most nearly represents the true biologic...

In the following we describe the system KoHDaS1 which is an automatic help desk system in a call center that basically leaves the dialogue initiative with the user as far as (s)he wants. The user’s turn circumscribing the problem as a whole is handed to a hierarchy of recurrent plausibility networks which classify the according problem. In the next step the system extracts even only implicitly ...

This paper investigates our experimental results for NTCIR-4 QAC2, the second attempt to evaluate the technology of Japanese question answering (QA). Our basic approach is a combination of information retrieval and named entity (NE) extraction based on pattern matching. The results show that the accuracy of NE extraction crucially affects the overall performance of our system. Additional experi...

Retrieving similar questions is very important in community-based question answering. A major challenge is the lexical gap in sentence matching. In this paper, we propose a convolutional neural tensor network architecture to encode the sentences in semantic space and model their interactions with a tensor layer. Our model integrates sentence modeling and semantic matching into a single model, w...

A Question Answering (QA) system aims to return exact answers to natural language questions. While today information retrieval techniques are quite successful at locating within large collections of documents those that are relevant to a user’s query, QA techniques that extract the exact answer from these retrieved documents still do not obtain very good accuracies. We approached the TREC 2007 ...

This paper presents a hybrid method for finding answers to Definition questions within large text collections. Because candidate answers to Definition questions do not generally fall in clearly defined semantic categories, answer discovery is guided by a combination of pattern matching and WordNet-based question expansion. The method is incorporated in a large opendomain question answering syst...

We describe herein a Web based pattern mining and matching approach to question answering. For each type of questions, a lot of textual patterns can be learned from the Web automatically, using the TREC QA track data as training examples. These textual patterns are assessed by the concepts of support and confidence, which are borrowed from the data mining community. Given a new unseen question,...

Life service information plays an important role in people’s life, such as weather conditions, so the study of how to get life service information has important significance. This paper put forward a question processing method called “integrated semantic algorithm” in Q&A System of life service information. The new algorithm was based on the semantic web, word order similarity algorithm and the...

The large scale of Q&A archives accumulated in community based question answering (CQA) servivces are important information and knowledge resource on the web. Question and answer matching task has been attached much importance to for its ability to reuse knowledge stored in these systems: it can be useful in enhancing user experience with recurrent questions. In this paper, a Word Embedding bas...

We implement multi-perspective context matching for the task of questionanswering on the SQuAD dataset and explore a variety of modifications to this core architecture. In our first modification, we compare the performance of GRUs with that of LSTMs in the original model. Next we attempt to predict the answer’s start index and length rather than its start and end indices. Finally, we introduce ...