We use the interpretation of vague scalar predicates like small as an illustration of how systematic semantic models of dialogue context enable the derivation of useful, fine-grained utterance interpretations from radically underspecified semantic forms. Because dialogue context suffices to determine salient alternative scales and relevant distinctions along these scales, we can infer implicit ...

This paper describes recent research on a natural-language-generation system that is based on planning. A system named KAMP is described that is capable of producing English sentences as part of a plan to enlist the cooperation of another agent in achieving a goal involving a change in the physical state of the world. The planner uses knowledge about the different subgoals to be achieved and li...

Utterances in situated activity are about the world. Theories and systems normally capture this by assuming references must be resolved to real-world entities in utterance understanding. We describe a number of puzzles and problems for this approach, and propose an alternative semantic representation using discourse relations that link utterances to the nonlinguistic context to capture the cont...

Language identification (LID) systems typically employ ivectors as fixed length representations of utterances. However, it may not be possible to reliably estimate i-vectors from short utterances, which in turn could lead to reduced language identification accuracy. Recently, Long Short Term Memory networks (LSTMs) have been shown to better model short utterances in the context of language iden...

We address the issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages. Help message generation for OOG utterances is a challenge because language understanding based on automatic speech recognition (ASR) of OOG utterances is usually erroneous; important words are often misrecognized or missing from such utterances. Our grammar verification method uses a ...

In this paper, we propose a method to improve the speech recognition accuracy for web search utterances to a spoken dialogue system. Speech data with a dialogue system are obtained by our speech-oriented information guidance system, ”Takemaru-kun” [1], which has been in operation at a public community center since November 2002. From the results of manual labeling of the utterances, child utter...

AbstructWe have compared the performance of four approaches for automatic language identification of speech utterances: Gaussian mixture model (GMM) classification; single-language phone recognition followed by languagedependent, interpolated n-gram language modeling (PRLM); parallel PRLM, which uses multiple single-language phone recognizers, each trained in a different language; and languaged...

Red Zora and Her Gang1 (orig. Die rote und ihre Bande) is a 1941 novel by the German-Swiss author Kurt Held (Kurt Kläber), inspired Croatian mentality history. While it was enormously popular in Germany, translation issued only 2017. In this paper, we analyse hypothetical position of within canon children’s literature established at time written. tends towards realism shaping reality based on u...

Our study addresses the relationship between teacher talk and children’s conceptual learning in early science instruction. We examined role of N = 32 kindergarten classes. The teachers were video-recorded at beginning a four-week instruction phase while assisting group children who dealing with unit on floating sinking. coding included expressions that pertinent to content (content-specific voc...