simple_bioc 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +18 -0
- data/Gemfile +4 -0
- data/LICENSE +20 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +8 -0
- data/lib/simple_bioc/annotation.rb +11 -0
- data/lib/simple_bioc/bioc_reader.rb +102 -0
- data/lib/simple_bioc/bioc_writer.rb +93 -0
- data/lib/simple_bioc/collection.rb +15 -0
- data/lib/simple_bioc/document.rb +29 -0
- data/lib/simple_bioc/location.rb +10 -0
- data/lib/simple_bioc/node.rb +12 -0
- data/lib/simple_bioc/node_base.rb +14 -0
- data/lib/simple_bioc/passage.rb +29 -0
- data/lib/simple_bioc/relation.rb +14 -0
- data/lib/simple_bioc/sentence.rb +20 -0
- data/lib/simple_bioc/version.rb +3 -0
- data/lib/simple_bioc.rb +14 -0
- data/simple_bioc.gemspec +27 -0
- data/spec/simple_bioc_spec.rb +14 -0
- data/xml/BioC.dtd +146 -0
- data/xml/PMID-8557975-simplified-sentences-tokens.xml +492 -0
- data/xml/PMID-8557975-simplified-sentences.xml +49 -0
- data/xml/abbr.key +71 -0
- data/xml/abbr.xml +1 -0
- data/xml/ascii.key +29 -0
- data/xml/ascii.xml +3 -0
- data/xml/everything-sentence.xml +1 -0
- data/xml/everything.key +8 -0
- data/xml/everything.xml +1 -0
- data/xml/lemma.key +51 -0
- data/xml/lemma.xml +1 -0
- data/xml/pos.key +49 -0
- data/xml/pos.xml +1 -0
- data/xml/sentence.key +36 -0
- data/xml/sentence.xml +1 -0
- metadata +153 -0
data/xml/pos.key
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
pos key
|
2
|
+
|
3
|
+
collection: 10 random PubMed documents with ASCII text split into
|
4
|
+
sentences and tokens by the MedPost tokenizer
|
5
|
+
|
6
|
+
Original source sentence.xml
|
7
|
+
|
8
|
+
source: PubMed
|
9
|
+
|
10
|
+
date: yyyymmdd. Date documents downloaded from PubMed
|
11
|
+
|
12
|
+
document: Title and possibly abstract from a PubMed reference
|
13
|
+
|
14
|
+
id: PubMed id
|
15
|
+
|
16
|
+
passage: Either title or abstract
|
17
|
+
|
18
|
+
infon["type"]: "title" or "abstract"
|
19
|
+
|
20
|
+
offset: The original Unicode byte offsets were not updated after
|
21
|
+
the ASCII conversion.
|
22
|
+
|
23
|
+
PubMed is extracted from an XML file, so literal offsets
|
24
|
+
would not be useful. Title has an offset of zero, while
|
25
|
+
the abstract is assumed to begin after the title and one
|
26
|
+
space. These offsets at least sequence the abstract after
|
27
|
+
the title.
|
28
|
+
|
29
|
+
sentence: One sentence of the passage as determined by the
|
30
|
+
MedPost sentence splitter
|
31
|
+
|
32
|
+
offset: A document offset to where the sentence begins in the
|
33
|
+
passage. Sum of the passage offset and the local offset
|
34
|
+
within the passage.
|
35
|
+
|
36
|
+
annotation: tokens in the sentence with their part-of-speech.
|
37
|
+
the annotations are of "type" "token"
|
38
|
+
|
39
|
+
infon["POS"]: The Penn Treebank part of speech tag as determined
|
40
|
+
by the MedPost biomedical part-of-speech tagger
|
41
|
+
|
42
|
+
location: offset: A document offset to where the annotated text
|
43
|
+
begins in the sentence. Sum of the sentence
|
44
|
+
offset and the local offset within the
|
45
|
+
sentence.
|
46
|
+
|
47
|
+
length: The length of the token.
|
48
|
+
|
49
|
+
text: ASCII text of the token.
|