nxt meets the icsi corpus

12
NXT meets the ICSI Corpus Jean Carletta and Jonathan Kilgour University of Edinburgh HCRC Language Technology Group

Upload: laszlo

Post on 13-Jan-2016

56 views

Category:

Documents


0 download

DESCRIPTION

NXT meets the ICSI Corpus. Jean Carletta and Jonathan Kilgour University of Edinburgh HCRC Language Technology Group. ICSI Meeting Corpus. 75 natural meetings from research groups close-talking and far-field microphones orthographic transcription "speech quality" tags (e.g., emphasis) - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: NXT meets the ICSI Corpus

NXT meets the ICSI Corpus

Jean Carletta and Jonathan Kilgour

University of Edinburgh

HCRC Language Technology Group

Page 2: NXT meets the ICSI Corpus

ICSI Meeting Corpus

• 75 natural meetings from research groups– close-talking and far-field microphones

• orthographic transcription

• "speech quality" tags (e.g., emphasis)

• dialogue acts using MRDA

• hot spots

Page 3: NXT meets the ICSI Corpus

The NITE XML Toolkit

• library support for data handling and search using a data model that can express both timing and complex structure

• multiple file stand-off XML data storage

• some standard GUIs, data utilities

• library support for writing tailored GUIs

Page 4: NXT meets the ICSI Corpus
Page 5: NXT meets the ICSI Corpus

extract from Bdb001.A.words.xml

<w nite:id="Bdb001.w.1,342" starttime="356.39" endtime="" c="W">time</w> <w nite:id="Bdb001.w.1,343" starttime="" endtime="" c="HYPH">-</w> <w nite:id="Bdb001.w.1,344" starttime="" endtime="356.59" c="W">line</w>

extract from Bdb001.A.speech-quality.xml<speechquality nite:id="Bdb001.emphasis.16" type="emphasis"> <nite:child href="Bdb001.A.words.xml#id(Bdb001.w.1,342)..id(Bdb001.w.1,344)" /> </speechquality>

Stand-off XML

Page 6: NXT meets the ICSI Corpus

Tasks

• pre-NXT: up-translation and tokenization

• hand annotation (topic segmentation, dialogue acts, extractive summaries, ...)

• automatic annotation/indexing by query match

Page 7: NXT meets the ICSI Corpus
Page 8: NXT meets the ICSI Corpus

Queries in NXT

($a w):(TEXT($a) ~ /th.*/)::($s speechquality):($s ^ $a) && ($s@type="emphasis")

 • Find instances of words starting with “th”• For each find instances of speech quality tags of

type "emphasis" that dominate the word• Discard words that are not dominated by at least one

such tagUse queries to understand data, verify quality, index.

Page 9: NXT meets the ICSI Corpus

NXT as Meeting Browser

• Browser = display + signal indexing +

search

• NXT data displays:– synchronize with signal– highlight search results

Page 10: NXT meets the ICSI Corpus
Page 11: NXT meets the ICSI Corpus

Issues

• Already can't load all the ICSI data at once on some machines

• NXT supports display of one meeting at a time but browsing may be over several meetings

• Really complicated queries are often too slow for browser response times

Key: Pre-indexing of query results, tailored data builds

Page 12: NXT meets the ICSI Corpus

Conclusions

• NXT available, free, open source, useful in a surprising number of ways

http://www.ltg.ed.ac.uk/NITE