Opened 8 years ago
Last modified 7 years ago
#44 new project
punctuation detection and correction
| Reported by: | xkovar3 | Owned by: | xkovar3 |
|---|---|---|---|
| Priority: | major | Milestone: | |
| Component: | SET | Keywords: | long |
| Cc: | Due Date: |
Description (last modified by )
recent development:
- punct. grammar improved by Machura
- good evaluation by Zemkova
- paper submitted to TSD, accepted, contains also comparison with tools from Liberec
Next:
- retry with ASR data from Marek Boháč and compare with results of their automaton (in mails)
- use <clause> from normal SET grammar
- semantic information?
- more negative rules?
- tune for ASR data?
- create a nice demo page
Attachments (1)
Change History (7)
comment:1 Changed 8 years ago by
| Description: | modified (diff) |
|---|
Changed 8 years ago by
| Attachment: | malyCorp (1).txt added |
|---|
comment:2 Changed 8 years ago by
| Description: | modified (diff) |
|---|
comment:3 Changed 8 years ago by
| Description: | modified (diff) |
|---|
comment:4 Changed 8 years ago by
| Description: | modified (diff) |
|---|
comment:5 Changed 7 years ago by
| Keywords: | long added |
|---|
recent project in PA153 in progress aimed at punctuation in spoken texts -- wannabe paper with Liberec people
comment:6 Changed 7 years ago by
progress with Jakub Machura on further development: Details in mails from him on 3rd and 4th Nov
Note: See
TracTickets for help on using
tickets.
ASR data from Liberec, for tuning