| // Licensed to the Apache Software Foundation (ASF) under one |
| // or more contributor license agreements. See the NOTICE file |
| // distributed with this work for additional information |
| // regarding copyright ownership. The ASF licenses this file |
| // to you under the Apache License, Version 2.0 (the |
| // "License"); you may not use this file except in compliance |
| // with the License. You may obtain a copy of the License at |
| // |
| // http://www.apache.org/licenses/LICENSE-2.0 |
| // |
| // Unless required by applicable law or agreed to in writing, |
| // software distributed under the License is distributed on an |
| // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| // KIND, either express or implied. See the License for the |
| // specific language governing permissions and limitations |
| // under the License. |
| |
| PACKAGE uima.ruta.example; |
| |
| // learnt using TextRulerExample\data\single |
| |
| SCRIPT uima.ruta.example.Features; |
| Document{-> CALL(Features)}; |
| FirstToken{->MARKONCE(Author, 1, 2)} # LParen; // p=20; n=0 |
| LParen{->MARKONCE(Date, 1, 4)} YearInd RParen PeriodSep; // p=20; n=0 |
| NUM{->MARKONCE(Pages, 1, 4)} SPECIAL NUM LastToken; // p=15; n=0 |
| CW{REGEXP("University")->MARKONCE(Publisher, 1, 5)} EnglishStopWord CW CW CommaSep; // p=1; n=0 |
| PublisherInd{->MARKONCE(Publisher, 1, 2)} CommaSep; // p=1; n=0 |
| CW{REGEXP("Department")->MARKONCE(Institution, 1, 3)} # PeriodSep; // p=1; n=0 |
| NUM{->MARKONCE(Volume, 1, 4)} # RParen CommaSep; // p=6; n=0 |
| NUM{REGEXP("1")->MARKONCE(Volume, 1, 2)} CommaSep; // p=1; n=0 |
| CW{->MARKONCE(Title, 1, 6)} SW SW SW # PeriodSep; // p=13; n=0 |
| CW{REGEXP("Markov")->MARKONCE(Title, 1, 3)} # PERIOD CW; // p=1; n=0 |
| CW{->MARKONCE(Title, 1, 6)} SW EnglishStopWord SW # PeriodSep; // p=5; n=0 |
| CW{REGEXP("Introducing")->MARKONCE(Title, 1, 3)} # PeriodSep; // p=1; n=0 |
| CW{REGEXP("Backtrack")->MARKONCE(Title, 1, 2)} # CW; // p=1; n=0 |
| CW{REGEXP("Verbal")->MARKONCE(Title, 1, 3)} # PeriodSep; // p=1; n=0 |
| CW{REGEXP("Causation")->MARKONCE(Title, 1, 3)} # PeriodSep; // p=1; n=0 |
| CW{REGEXP("Projection")->MARKONCE(Title, 1, 2)} # CW; // p=1; n=0 |
| CW{REGEXP("Proceedings")->MARKONCE(Booktitle, 1, 3)} # CommaSep; // p=1; n=0 |
| CW{REGEXP("Fundamenta")->MARKONCE(Journal, 1, 3)} CW CommaSep; // p=1; n=0 |
| CW{->MARKONCE(Journal, 1, 5)} EnglishStopWord EnglishStopWord CAP CommaSep; // p=1; n=0 |
| FirstNameInitial{->MARKONCE(Journal, 1, 3)} CAP CommaSep; // p=1; n=0 |
| CW{->MARKONCE(Journal, 1, 5)} EnglishStopWord CW # NameLinker NUM CommaSep; // p=2; n=0 |
| CW{REGEXP("Nucleic")->MARKONCE(Journal, 1, 4)} CW CW CommaSep; // p=1; n=0 |
| CW{REGEXP("Journal")->MARKONCE(Journal, 1, 5)} EnglishStopWord CW CW CommaSep; // p=1; n=0 |
| CW{REGEXP("Artificial")->MARKONCE(Journal, 1, 3)} CW CommaSep; // p=2; n=0 |
| CW{REGEXP("Pattern")->MARKONCE(Journal, 1, 4)} CW CW CommaSep; // p=1; n=0 |
| CW{REGEXP("Econometrica")->MARKONCE(Journal, 1, 2)} CommaSep; // p=1; n=0 |
| CW{REGEXP("Journal")->MARKONCE(Journal, 1, 3)} # NameLinker; // p=5; n=0 |
| CW{REGEXP("Evolutionary")->MARKONCE(Journal, 1, 3)} CW CommaSep; // p=1; n=0 |
| CW{->MARKONCE(Location, 1, 3)} FirstName LastToken; // p=2; n=0 |
| FirstName{->MARKONCE(Location, 1, 4)} CommaSep CW LastToken; // p=1; n=0 |
| CW{->MARKONCE(Tech, 1, 5)} PeriodSep SW PeriodSep CommaSep; // p=1; n=0 |