公开(公告)号：AU2003222602A1

公开(公告)日：2003-11-11

申请号：AU2003222602

申请日：2003-04-10

Applicant: IBM

Inventor： WARD ROBERT TODD ,  EPSTEIN MARK EDWARD ,  JONES SHARON BARBARA

IPC: G06F17/21 ,  G06F17/27 ,  G06F17/28 ,  G06F40/00 ,  G10L15/18 ,  G06F17/20

Abstract: A method of developing natural language understanding (NLU) applications can include determining NLU interpretation information from an NLU training corpus of text using a multi-pass processing technique. The alteration of one pass automatically can alter an input for a subsequent pass. The NLU interpretation information can specify an interpretation of at least part of the NLU training corpus of text. The NLU interpretation information can be stored in a database, and selected items of the NLU interpretation information can be presented in a graphical editor. User specified edits also can be received in the graphical editor.

公开(公告)号：CA2482514A1

公开(公告)日：2003-11-20

申请号：CA2482514

申请日：2003-04-10

Applicant: IBM

Inventor： WARD ROBERT TODD ,  JONES SHARON BARBARA ,  EPSTEIN MARK EDWARD

IPC: G06F17/21 ,  G06F17/27 ,  G06F17/28 ,  G06F40/00 ,  G10L15/18

Abstract: A method of developing natural language understanding (NLU) applications includes determining NLU interpretation information from an NLU training corpus of text using a multi-pass processing technique. The alteration of on e pass automatically can alter an input for a subsequent pass. The NLU interpretation information can specify an interpretation of at least part of the NLU training corpus of text. The NLU interpretation information is store d in a database, and selected items of the NLU interpretation information can be presented in a graphical editor. User specified edits also are received in t he graphical editor.

公开(公告)号：AU2003222602A8

公开(公告)日：2003-11-11

申请号：AU2003222602

申请日：2003-04-10

Applicant: IBM

Inventor： WARD ROBERT TODD ,  JONES SHARON BARBARA ,  EPSTEIN MARK EDWARD

IPC: G06F17/21 ,  G06F17/27 ,  G06F17/28 ,  G06F40/00 ,  G10L15/18

Abstract: A method of developing natural language understanding (NLU) applications can include determining NLU interpretation information from an NLU training corpus of text using a multi-pass processing technique. The alteration of one pass automatically can alter an input for a subsequent pass. The NLU interpretation information can specify an interpretation of at least part of the NLU training corpus of text. The NLU interpretation information can be stored in a database, and selected items of the NLU interpretation information can be presented in a graphical editor. User specified edits also can be received in the graphical editor.