Parsing and Its Applications for Conversational Speech
Published 4 October 2006
Matthew Lease, Eugene Charniak, Mark Johnson
Citations13
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper provides an introduction to recent work in statistical parsing and its applications for conversational speech, with particular emphasis on the relationship between parsing and detecting speech repairs.
Abstract
This paper provides an introduction to recent work in statistical parsing and its applications for conversational speech, with particular emphasis on the relationship between parsing and detecting speech repairs. While historically parsing and repair detection have been studied independently, we present a line of research which has spanned the boundary between the two and demonstrated the efficacy of this synergistic approach. Our presentation highlights successes to date, remaining challenges, and promising future work.
Keywords
Computer Science
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
A maximum-entropy-inspired parser
1,496 Citations2000Eugene Charniak
A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.
Computational LinguisticsProbabilistic Top-Down Parsing and Language Modeling
339 Citations2001Brian Roark
A lexicalized probabilistic top-down parser is presented, which performs very well, in terms of both the accuracy of returned parses and the efficiency with which they are found, relative to the best broad-coverage statistical parsers.
Immediate-head parsing for language models
299 Citations2001Eugene Charniak
It is suggested that improvement of the underlying parser should significantly improve the model's perplexity and that even in the near term there is a lot of potential for improvement in immediate-head language models.
Speech repairs, intonational phrases, and discourse markers: modeling speakers' utterances in spoken dialogue
190 Citations1999Peter A. Heeman, James F. Allen
A statistical language model is presented in which the speech recognition problem is redefined so that it includes the identification of POS tags, discourse markers, speech repairs, and intonational phrases.
Edit detection and parsing for transcribed speech
158 Citations2001Eugene Charniak, Mark Johnson
A simple architecture for parsing transcribed speech in which an edited-word detector first removes such words from the sentence string, and then a standard statistical parser trained on transcribedspeech parses the remaining words is presented.
A TAG-based noisy channel model of speech repairs
129 Citations2004Mark Johnson, Eugene Charniak
A noisy channel model of speech repairs, which can identify and correct repairs in speech transcripts, and a novel type of TAG-based transducer is the channel model.
Syntax-based language models for statistical machine translation
110 Citations2003Eugene Charniak, Kevin Knight +1 more
Structural Metadata Research in the EARS Program
63 Citations2006Y. Liu, E. Shriberg +8 more
A representative sample of results shows that combining multiple knowledge sources (words, prosody, syntactic information) is helpful, that prosody is more helpful for news speech than for conversational speech, that word errors significantly impact performance, and that discriminative models generally provide benefit over maximum likelihood models.
A study on richer syntactic dependencies for structured language modeling
46 Citations2001Peng Xu, Ciprian Chelba +1 more
Analysis of parsing performance shows correlation between the quality of the parser and the language model performance (PPL and WER) and the enriched SLM outperforms the baseline 3-gram model in terms of WER when used in isolation as a second pass (N-best re-scoring) language model.
An improved model for recognizing disfluencies in conversational speech
24 Citations2004Mark Johnson, Eugene Charniak +1 more
The ICSI-SRI-UW metadata extraction system
23 Citations2004Elizabeth Shriberg, Andreas Stolcke +5 more
A state-of-the-art system for automatic detection of “metadata” (information beyond the words) in both broadcast news and spontaneous telephone conversations, developed as part of the DARPA EARS Rich Transcription program is described.
Language modeling using efficient best-first bottom-up parsing
20 Citations2004Keith Hall, Mark Johnson
A two-stage best-first bottom-up word-lattice parser that works by using a "figure of merit" that selects lattice paths while simultaneously selecting syntactic category edges for parsing is presented.