This paper presents a method for learning a semantic parser from ambiguous supervision. Training data consists of natural language sentences annotated with multiple potential mean...
Multiagent environments are often highly dynamic and only partially observable which makes deliberative action planning computationally hard. In many such environments, however, a...
In morphologically rich languages such as Arabic, the abundance of word forms resulting from increased morpheme combinations is significantly greater than for languages with fewer...
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
Carolina Parada, Mark Dredze, Abhinav Sethy, Ariya...
In this paper, we present a social model for software agent conversations for action based on social commitments and their negotiation. We depart from the premises that conversati...