This demonstration paper presents i-Parser, a novel development kit that produces high-performance semantic parsers. i-Parser converts training graphs into sequences written in a context-free language, then our proposed model learns to generate the sequences. With interactive configuration and visualization, users can easily build their own parsers. Benchmark results of i-Parser showed high performances of various parsing tasks in natural language processing.

This paper describes the first report on crosslingual transfer for semantic dependency parsing.We present the insight that there are two different kinds of cross-linguality, namely surface level and semantic level, and try to capture both kinds of cross-linguality by combining annotation projection and model transfer of pre-trained language models.Our experiments showed that the performance of our graph-based semantic dependency parser almost achieved the approximated upper bound.

Backchannel feedback from the spoken dialogue system makes the human-machine interaction more sophisticated. To predict suitable timing and forms, backchannel prediction technology has been studied. Most studies have combined acoustic and lexical features into the model for better prediction. However, extracting lexical features leads to a delay caused by the automatic speech recognition (ASR) process. To make accurate predictions on the basis of delayed ASR outputs, we propose early prediction for backchannel opportunity and backchannel category based on attention-based LSTM mechanisms. The loss is calculated with a weighting value that gradually increases when a sequence is closer to a suitable response timing. The proposed backchannel prediction uses a two-step approach that first detects a backchannel opportunity and then predicts a backchannel category. Evaluation results show that the early prediction model can predict a backchannel opportunity and category better than the current state-of-the-art algorithm even under a 2.0-second ASR delay condition.

Tatsuki Kuribayashi, Hiroki Ouchi, Naoya Inoue, Paul Reisert, Toshinori Miyoshi, Jun Suzuki, Kentaro Inui. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

Bayesian network is a powerful tool to represent patterns inside past data. It can be used to predict future by calculating the posterior probability of future events. Machine learning techniques that can construct a Bayesian network from past data automatically are well developed in recent years. If we consider past data as a sampling set from an original probabilistic distribution, the "learning" process is actually trying to reproduce the original probabilistic distribution from the sampling set. Therefore, the finiteness of size of sampling set will bring uncertainties to the reproduced parameters of constructed Bayesian network. When the constructed Bayesian network is used to predict future, the uncertainties of reproduced parameters will be transferred to the uncertainty of query response. Here, the query response is the posterior probability that we are interested in. Evaluating the uncertainty of query response is critical to some strict industrial applications. Previous researches have proposed a method to evaluate the uncertainty. The consequence is shown as a variance of the query response. However, the conventional method need to work together with the bucket elimination, an exact inference method. Therefore, the conventional method can not deal with large Bayesian networks that used in real applications because of its calculation cost. We proposed a new approach to calculate the uncertainty of query responses by using joint probability distribution in this research. The proposed method can work with any inference method. Therefore, it can give an approximate evaluation even when the Bayesian network is large by using an approximate inference method. To investigate the accuracy of our proposed method, six well used public Bayesian networks are used as test cases. By comparing the approximate results with the exact results, an average error of -13.60% is got.

Moment-based character-normalization methods are known to improve character-recognition accuracy. These methods use the moments of an input image, which has two dimensions because of the thickness of its stroke lines, to estimate transformation parameters, whereas character is essentially composed of one dimensional stroke lines. This implies that these methods overestimate the moments of the thick parts of character strokes. To solve this problem, moment-based normalization methods, which use the moments of a contour image of a character combined with the input image of that character, are proposed. To extract the contours of character strokes, two methods, chain code contour (CC) and gradient contour (GC), are used. Character-recognition experiments on two printed-character databases and on two handwritten-character databases show that the character-recognition accuracies of the proposed methods are comparable to or significantly higher than those of conventional methods. In particular, the proposed methods are more effective for printed-character recognition.

Class-specific feature polynomial classifier (CFPC), a variant of a polynomial classifier (PC), yields high classification accuracy especially in high dimensional feature spaces. However, the computational cost for classification in such a high dimensional space is rather expensive. To overcome this difficulty, we propose a simplified polynomial network (SPN) classifier that reduces the complexity of polynomial networks with little deterioration of classification accuracy. In experiments of handwritten digit recognition on USPS, SPN using features of 30.0 dimensions on average achieved higher classification accuracy and a classification speed about 12.8 times faster than CFPC using features of 250 dimensions. In experiments on MNIST, SPN using features of 40.0 dimensions on average achieved a classification speed about 2.0 times faster than CFPC using features of 100 dimensions with nearly the same classification accuracy.