Flexible parsing of discretely uttered sentences

Borghesi, Luigi; Favareto, C.

doi:10.3115/991813.991819

Cited by 7 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core idea is to begin with the most reliable classifier first, and inform those below it. This idea also appeared in the early IBM MT models (Brown et al, 1993) and in the "islands of reliability" approaches to parsing and speech (Borghesi and Favareto, 1982;Corazza et al, 1991). D'Souza and Ng (2013) recently combined a rule-based model with a machine learned model, but lacked the fine-grained formality of a cascade of sieves.…”

Section: Event Ordering Modelsmentioning

confidence: 93%

Dense Event Ordering with a Multi-Pass Architecture

Chambers

Cassidy

McDowell

et al. 2014

TACL

144

View full text Add to dashboard Cite

The past 10 years of event ordering research has focused on learning partial orderings over document events and time expressions. The most popular corpus, the TimeBank, contains a small subset of the possible ordering graph. Many evaluations follow suit by only testing certain pairs of events (e.g., only main verbs of neighboring sentences). This has led most research to focus on specific learners for partial labelings. This paper attempts to nudge the discussion from identifying some relations to all relations. We present new experiments on strongly connected event graphs that contain ∼10 times more relations per document than the TimeBank. We also describe a shift away from the single learner to a sieve-based architecture that naturally blends multiple learners into a precision-ranked cascade of sieves. Each sieve adds labels to the event graph one at a time, and earlier sieves inform later ones through transitive closure. This paper thus describes innovations in both approach and task. We experiment on the densest event graphs to date and show a 14% gain over state-of-the-art.

show abstract

Section: Event Ordering Modelsmentioning

confidence: 93%

Dense Event Ordering with a Multi-Pass Architecture

Chambers

Cassidy

McDowell

et al. 2014

TACL

144

View full text Add to dashboard Cite

show abstract

“…Normally they are used in a strict left to right fashion and embody syntactic and semantic constraints on individual sentences. These constraints are represented in some form of probabilisfic or semantic network which does not change from utterance to utterance [2,8]. Today, state-of-the-art speech recognizers can achieve word accuracy rates in excess of 95% when using grammars of perplexity 30 -60.…”

Section: Overviewmentioning

confidence: 99%

The Minds System: Using Context and Dialog to Enhance Speech Recognition

Young¹

1989

View full text Add to dashboard Cite

Contextual knowledge has traditionally been used in multi-sentential textual understanding systems. In contrast, this paper describes a new approach toward using contextual, dialog-based knowledge for speech recognition. To demonstrate this approach, we have built MINDS, a system which uses contextual knowledge to predictively generate expectations about the conceptual content that may be expressed in a system user's next utterance. These expectations are expanded to constrain the possible words which may be matched from an incoming speech signal. To prevent system rigidity and allow for diverse user behavior, the system creates layered predictions which range from very specific to very general. Each time new information becomes available from the ongoing dialog, MINDS generates a different set of layered predictions for processing the next utterance. The predictions contain constraints derived from the contextual, dialog level knowledge sources and each prediction is translated into a grammar usable by our speech recognizer, SPHINX. Since speech recognizers use grammars to dictate legal word sequences and to constrain the recognition process, the dynamically generated grammars reduce the number of word candidates considered by the recognizer. The results demonstrate that speech recognition accuracy is greatly enhanced through the use of predictions. OVERVIEWOne of the primary problems in speech recognition research is effectively analyzing very large, complex search spaces. As search space size increases, recognition accuracy decreases. Previous research in the speech recognition area illustrates that knowledge can compensate for search by constraining the exponential growth of a search space and thus increasing recognition accuracy [12,4,8]. The most common approach to constraining a search space is to use a grammar. The grammars used for speech recognition dictate legal word sequences. Normally they are used in a strict left to right fashion and embody syntactic and semantic constraints on individual sentences. These constraints are represented in some form of probabilisfic or semantic network which does not change from utterance to utterance [2,8]. Today, state-of-the-art speech recognizers can achieve word accuracy rates in excess of 95% when using grammars of perplexity 30 -60. As the number of word alternatives at each point in time increases (or as perplexity increases) performance of these systems decreases rapidly. Given this level of performance, recently researchers have begun using speech in computer problem solving applications. Using speech as an input medium for computer applications has resulted in two important findings. First, the grammars necessary to ensure some minimal coverage of a user's language have perplexities which are an order of magnitude larger than those used in today's high performing speech systems [18]. Second, the use of speech in problem solving tasks permits knowledge sources beyond the sentence level to be used to compensate for the extra search entailed by the inc...

show abstract

Towards Habitable Systems

Young

Ward

1996

Recent Research Towards Advanced Man-Machine Interface Through Spoken Language

View full text Add to dashboard Cite

Flexible parsing of discretely uttered sentences

Cited by 7 publications

References 0 publications

Dense Event Ordering with a Multi-Pass Architecture

Dense Event Ordering with a Multi-Pass Architecture

The Minds System: Using Context and Dialog to Enhance Speech Recognition

Towards Habitable Systems

Contact Info

Product

Resources

About