It has been often argued that parentheticals, discourse adverbials and certain parts of speech like interjections do not contribute to the truth conditional content of the assertions of which they are part. In this paper I argue that many of these constructions do contribute a truth conditional content, and I propose a semantics for parentheticals and discourse adverbials that treats these cons...

We have analyzed 607 sentences of spontaneous human-computer speech data containing repairs, drawn from a total corpus of 10,718 sentences. We present here criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction. The criteria involve integration of knowledge from several sources: pattern matching, syntactic and semantic a...

Borrowings and Adaptations. First of all, the author would like to clarify the meanings of the terms "predicative" and "nonpredicative". As is well known, praedicatum in Late Latin means "what has been said (previously)". In Aristotelian and subsequent forms of traditional logic [8,9,11,12,13,14,15,16] a predicate was understood to be one (the one in which something is said about the subject of...

In this paper we describe a new approach for learning dialog act processing. In this approach we integrate a symbolic semantic segmentation parse,: with a learning dialog act network. In order to support the unforeseeable errors and variations of spoken language we have concentrated on robust data-driven learning. This approach already compares favorably with the statistical average plansibilit...

Осетинский язык (< ИРАНСКИЙ < ИНДОЕВРОПЕЙСКИЙ) взаимодействует с русским языком уже как минимум два столетия, и большинство осетин – осетино-русские билингвы. Влияние русского языка на развитие осетинской лексики, в частности проникновение русских слов, для которых нет осетинских аналогов, лексический состав их последующая адаптация (например, скъола ‘школа’, стъол ‘стол’ др.), хо...

This paper describes a new approach and a system SCREEN’ for fault-tolerant speech parsing. Speech parsing describes the syntactic and semantic analysis of spontaneous spoken language. The general approach is based on incremental immediate flat analysis, learning of syntactic and semantic speech parsing, parallel integration of current hypotheses, and the consideration of various forms of speec...

We describe an approach to Machine Translation of transcribed speech, as found in closed captions. We discuss how the colloquial nature and input format peculiarities of closed captions are dealt with in a pre-processing pipeline that prepares the input for effective processing by a core MT system. In particular, we describe components for proper name recognition and input segmentation. We eval...

At home, workplaces or schools, an increasing amount of intelligent robotic systems are starting to be able to help us in our daily life (windows or vacuum cleaners, self-driving cars) [1] and in flexible manufacturing systems [2]. A key feature in these new domains is the close interaction between people and robots. In particular, such robotic systems need to be teachable by non-technical user...

Conversational grunts, such as uhhuh, un-hn, rnrn, and oh are ubiquitous in spoken English, but no satisfactory scheme for transcribing these items exists. This paper describes previous approaches, presents some facts about the phonetics of grunts, proposes a transcription scheme, and evaluates its accuracy. 1 1 T h e I m p o r t a n c e o f C o n v e r s a t i o n a l G r u n t s :Conversation...

This paper describes and evaluates a new technique for measuring confidence in word strings produced by speech recognition systems. It detects misrecognized and out-of-vocabulary words in spontaneous spoken dialogs. The system uses multiple, diverse knowledge sources including acoustics, semantics, pragmatics and discourse to determine if a word string is misrecognized. When likely misrecogniti...