The system was evaluated on the speaker-independent (SI) portion of DARPA's February 1992 "Dry-Run" WSJ0 test and achieved 17.1% word error without verbalized punctuation (NVP) and 16.6% error with verbalized punctuation (VP). In addition, we increased the amount of training data and reduced the VP error rate to 12.9%. This SI error rate (with a larger amount of training data) equalled the best...

This paper describes a more precise analysis of punctuation for a bi-directional, broad coverage English grammar extracted from the CCGbank (Hockenmaier and Steedman, 2007). We discuss various approaches which have been proposed in the literature to constrain overgeneration with punctuation, and illustrate how aspects of Briscoe’s (1994) influential approach, which relies on syntactic features ...

Although there has been some speculation concerning the role played by punctuation in parsing, there has been amazingly little empirical investigation of the issue. Punctuation appears to be a widely neglected topic. For the most part, where punctuation has been included in parsing studies, investigators have simply assumed that punctuation, such as commas, can be used to effectively disambigua...

This paper investigates the usefulness of sentence-internal prosodic cues in syntactic parsing of transcribed speech. Intuitively, prosodic cues would seem to provide much the same information in speech as punctuation does in text, so we tried to incorporate them into our parser in much the same way as punctuation is. We compared the accuracy of a statistical parser on the LDC Switchboard treeb...

We describe an approach to robust domain-independent syntactic parsing of unrestricted naturally-occurring (English) input. The technique involves parsing sequences of part-ofspeech and punctuation labels using a unification-based grammar coupled with a probabilistic LR parser. We describe the coverage of several corpora using this grammar and report the results of a parsing experiment using pr...

In this paper we develop a maximum-entropy based method for annotating spontaneous conversational speech with punctuation. The goal of this task is to make automatic transcriptions more readable by humans, and to render them into a form that is useful for subsequent natural language processing and discourse analysis. Our basic approach is to view the insertion of punctuation as a form of taggin...

This paper explores the use of machine learning techniques to restore punctuation and case in English text, as part of which it investigates the co-dependence of case information and punctuation. We achieve an overall F-score of .619 for the task using a variety of lexical and contextual features, and iterative retagging.

We report on experiments to measure the effect of speech recognition errors and automatic punctuation insertion errors on the performance of information extraction (entity and relation extraction). The outputs of several recognition systems with a range of word error rates (WER), along with punctuation insertion, were fed into a system that extracts entities and relations from the recognized te...