No abstract

No abstract

We propose a multi‐strategic concept‐spotting approach for robust spoken language understanding of conversational Korean in a hostile recognition environment such as in‐car navigation and telebanking services. Our concept‐spotting method adopts a partial semantic understanding strategy within a given specific domain since the method tries to directly extract pre‐defined meaning representation slot values from spoken language inputs. In spite of partial understanding, we can efficiently acquire the necessary information to compose interesting applications because the meaning representation slots are properly designed for specific domain‐oriented understanding tasks. We also propose a multi‐strategic method based on this concept‐spotting approach such as a voting method. We present experiments conducted to verify the feasibility of these methods using a variety of spoken Korean data.

Named entity recognition is important in sophisticated information service system such as Question Answering and Text Mining since most of the answer type and text mining unit depend on the named entity type. Therefore we focus on named entity recognition model in Korean. Korean named entity recognition is difficult since each word of named entity has not specific features such as the capitalizing feature of English. It has high dependence on the large amounts of hand-labeled data and the named entity dictionary, even though these are tedious and expensive to create. In this paper, we devise HMM based named entity recognizer to consider various context models. Furthermore, we consider weakly supervised learning technique, CoTraining, to combine labeled data and unlabeled data.

Machine reading comprehension is the task of understanding a given context and finding the correct response in that context. A simple recurrent unit (SRU) is a model that solves the vanishing gradient problem in a recurrent neural network (RNN) using a neural gate, such as a gated recurrent unit (GRU) and long short‐term memory (LSTM); moreover, it removes the previous hidden state from the input gate to improve the speed compared to GRU and LSTM. A self‐matching network, used in R‐Net, can have a similar effect to coreference resolution because the self‐matching network can obtain context information of a similar meaning by calculating the attention weight for its own RNN sequence. In this paper, we construct a dataset for Korean machine reading comprehension and propose an S2‐Net model that adds a self‐matching layer to an encoder RNN using multilayer SRU. The experimental results show that the proposed S2‐Net model has performance of single 68.82% EM and 81.25% F1, and ensemble 70.81% EM, 82.48% F1 in the Korean machine reading comprehension test dataset, and has single 71.30% EM and 80.37% F1 and ensemble 73.29% EM and 81.54% F1 performance in the SQuAD dev dataset.