1-3hit |
Shogo OKADA Mi HANG Katsumi NITTA
This study focuses on modeling the storytelling performance of the participants in a group conversation. Storytelling performance is one of the fundamental communication techniques for providing information and entertainment effectively to a listener. We present a multimodal analysis of the storytelling performance in a group conversation, as evaluated by external observers. A new multimodal data corpus is collected through this group storytelling task, which includes the participants' performance scores. We extract multimodal (verbal and nonverbal) features regarding storytellers and listeners from a manual description of spoken dialog and from various nonverbal patterns, including each participant's speaking turn, utterance prosody, head gesture, hand gesture, and head direction. We also extract multimodal co-occurrence features, such as head gestures, and interaction features, such as storyteller utterance overlapped with listener's backchannel. In the experiment, we modeled the relationship between the performance indices and the multimodal features using machine-learning techniques. Experimental results show that the highest accuracy (R2) is 0.299 for the total storytelling performance (sum of indices scores) obtained with a combination of verbal and nonverbal features in a regression task.
Youwei LU Shogo OKADA Katsumi NITTA
We propose a novel method, built upon the hierarchical Dirichlet process hidden semi-Markov model, to reveal the content structures of unstructured domain-specific texts. The content structures of texts consisting of sequential local contexts are useful for tasks, such as text retrieval, classification, and text mining. The prominent feature of our model is the use of the recursive uniform partitioning, a stochastic process taking a view different from existing HSMMs in modeling state duration. We show that the recursive uniform partitioning plays an important role in avoiding the rapid switching between hidden states. Remarkably, our method greatly outperforms others in terms of ranking performance in our text retrieval experiments, and provides more accurate features for SVM to achieve higher F1 scores in our text classification experiments. These experiment results suggest that our method can yield improved representations of domain-specific texts. Furthermore, we present a method of automatically discovering the local contexts that serve to account for why a text is classified as a positive instance, in the supervised learning settings.
Toshiko WAKAKI Ken SATOH Katsumi NITTA Seiichiro SAKURAI
In the commonsense reasoning, priorities among rules are often required to be found out in order to derive the desired conclusion as a theorem of the reasoning. In this paper, first we present the bottom-up and top-down abduction procedures to compute skeptical explanations and secondly show that priorities of circumscription to infer a desired theorem can be abduced as a skeptical explanation in abduction. In our approach, the required priorities can be computed based on the procedure to compute skeptical explanations provided in this paper as well as Wakaki and Satoh's method of compiling circumscription into extended logic programs. The method, for example, enables us to automatically find the adequate priority w. r. t. the Yale Shooting Problem to express a human natural reasoning in the framework of circumscription.