4 |
Structured generative models for unsupervised named-entity clustering
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Recognizing disfluencies in conversational speech
|
|
|
|
Abstract:
We present a system for modeling disfluency in conversational speech: repairs, fillers, and self-interruption points (IPs). For each sentence, candidate repair analyses are generated by a stochastic tree adjoining grammar (TAG) noisy-channel model. A probabilistic syntactic language model scores the fluency of each analysis, and a maximum-entropy model selects the most likely analysis given the language model score and other features. Fillers are detected independently via a small set of deterministic rules, and IPs are detected by combining the output of repair and filler detection modules. In the recent Rich Transcription Fall 2004 (RT-04F) blind evaluation, systems competed to detect these three forms of disfluency under two input conditions: a best-case scenario of manually transcribed words and a fully automatic case of automatic speech recognition (ASR) output. For all three tasks and on both types of input, our system was the top performer in the evaluation. ; 8 page(s)
|
|
Keyword:
200400 Linguistics
|
|
URL: http://hdl.handle.net/1959.14/114707
|
|
BASE
|
|
Hide details
|
|
14 |
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Sentence-Internal Prosody Does not Help Parsing the Way Punctuation Does
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Noun-phrase co-occurrence statistics for semi-automatic semantic lexicon construction ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|