In research on automatic generation of narrative text, story events are often formally represented as a causal graph.When serializing and realizing this causal graph as natural language text, simple approaches produce cumbersome sentences with repetitive syntactic structure, e.g.long chains of "because" clauses.In our research, we show that the fluency of narrative text generated from causal graphs can be improved by applying rule-based grammatical transformations to generate many sentence variations with equivalent semantics, then selecting the variation that has the highest probability using a probabilistic syntactic parser.We evaluate our approach by generating narrative text from causal graphs that encode 100 brief stories involving the same three characters, based on a classic film of experimental social psychology.Crowdsourced workers judged the writing quality of texts generated with ranked transformations as significantly higher than those without, and not significantly lower than human-authored narratives of the same situations.

We present the SimSensei system, a fully automatic virtual agent that conducts interviews to assess indicators of psychological distress. We emphasize on the perception part of the system, a multimodal framework which captures and analyzes user state for both behavioral understanding and interactional purposes.

We present the SimSensei system, a fully automatic virtual agent that conducts interviews to assess indicators of psychological distress. With this demo, we focus our attention on the perception part of the system, a multimodal framework which captures and analyzes user state behavior for both behavioral understanding and interactional purposes. We will demonstrate real-time user state sensing as a part of the SimSensei architecture and discuss how this technology enabled automatic analysis of behaviors related to psychological distress.

Fabrizio Morbini, David DeVault, Kallirroi Georgila, Ron Artstein, David Traum, Louis-Philippe Morency. Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). 2014.

Although data-driven techniques are com-monly used for Natural Language Under-standing in dialogue systems, their effi-cacy is often hampered by the lack of ap-propriate annotated training data in suffi-cient amounts. We present an approach for rapid and cost-effective annotation of training data for classification-based lan-guage understanding in conversational di-alogue systems. Experiments using a web-accessible conversational character that in-teracts with a varied user population show that a dramatic improvement in natural language understanding and a substantial reduction in expert annotation effort can be achieved by leveraging non-expert an-notation.

We address the challenge of interpreting spoken input in a conversational dialogue system with an approach that aims to exploit the close relationship between the tasks of speech recognition and language understanding through joint modeling of these two tasks. Instead of using a standard pipeline approach where the output of a speech recognizer is the input of a language understanding module, we merge multiple speech recognition and utterance classification hypotheses into one list to be processed by a joint reranking model. We obtain substantially improved performance in language understanding in experiments with thousands of user utterances collected from a deployed spoken dialogue system.