Document (#37046)

Author

Cui, H.

Title

CharaParser for fine-grained semantic annotation of organism morphological descriptions

Source

Journal of the American Society for Information Science and Technology. 63(2012) no.4, S.738-754

Year

2012

Abstract

Biodiversity information organization is looking beyond the traditional document-level metadata approach and has started to look into factual content in textual documents to support more intelligent and semantic-based access. This article reports the development and evaluation of CharaParser, a software application for semantic annotation of morphological descriptions. CharaParser annotates semistructured morphological descriptions in such a detailed manner that all stated morphological characters of an organ are marked up in Extensible Markup Language format. Using an unsupervised machine learning algorithm and a general purpose syntactic parser as its key annotation tools, CharaParser requires minimal additional knowledge engineering work and seems to perform well across different description collections and/or taxon groups. The system has been formally evaluated on over 1,000 sentences randomly selected from Volume 19 of Flora of North American and Part H of Treatise on Invertebrate Paleontology. CharaParser reaches and exceeds 90% in sentence-wise recall and precision, exceeding other similar systems reported in the literature. It also significantly outperforms a heuristic rule-based system we developed earlier. Early evidence that enriching the lexicon of a syntactic parser with domain terms alone may be sufficient to adapt the parser for the biodiversity domain is also observed and may have significant implications.

Similar documents (content)

1. Cui, H.: Competency evaluation of plant character ontologies against domain literature (2010) 0.38

   0.38371336 = sum of:
     0.38371336 = product of:
       1.1991043 = sum of:
         0.057591207 = weight(abstract_txt:grained in 3466) [ClassicSimilarity], result of:
           0.057591207 = score(doc=3466,freq=1.0), product of:
             0.117111154 = queryWeight, product of:
               1.0416341 = boost
               7.8682456 = idf(docFreq=45, maxDocs=44218)
               0.014289109 = queryNorm
             0.49176535 = fieldWeight in 3466, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.8682456 = idf(docFreq=45, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
         0.043494638 = weight(abstract_txt:domain in 3466) [ClassicSimilarity], result of:
           0.043494638 = score(doc=3466,freq=3.0), product of:
             0.08484395 = queryWeight, product of:
               1.2538382 = boost
               4.7355914 = idf(docFreq=1054, maxDocs=44218)
               0.014289109 = queryNorm
             0.5126428 = fieldWeight in 3466, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.7355914 = idf(docFreq=1054, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
         0.1487362 = weight(abstract_txt:flora in 3466) [ClassicSimilarity], result of:
           0.1487362 = score(doc=3466,freq=2.0), product of:
             0.17496932 = queryWeight, product of:
               1.2732011 = boost
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.014289109 = queryNorm
             0.8500701 = fieldWeight in 3466, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
         0.07104118 = weight(abstract_txt:semantic in 3466) [ClassicSimilarity], result of:
           0.07104118 = score(doc=3466,freq=5.0), product of:
             0.11361037 = queryWeight, product of:
               1.7769928 = boost
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.014289109 = queryNorm
             0.6253054 = fieldWeight in 3466, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
         0.14735086 = weight(abstract_txt:descriptions in 3466) [ClassicSimilarity], result of:
           0.14735086 = score(doc=3466,freq=4.0), product of:
             0.19904426 = queryWeight, product of:
               2.3520768 = boost
               5.9223356 = idf(docFreq=321, maxDocs=44218)
               0.014289109 = queryNorm
             0.74029195 = fieldWeight in 3466, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               5.9223356 = idf(docFreq=321, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
         0.31189033 = weight(abstract_txt:biodiversity in 3466) [ClassicSimilarity], result of:
           0.31189033 = score(doc=3466,freq=3.0), product of:
             0.31549925 = queryWeight, product of:
               2.4178548 = boost
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.014289109 = queryNorm
             0.9885613 = fieldWeight in 3466, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
         0.17382929 = weight(abstract_txt:annotation in 3466) [ClassicSimilarity], result of:
           0.17382929 = score(doc=3466,freq=2.0), product of:
             0.27998826 = queryWeight, product of:
               2.78963 = boost
               7.0240583 = idf(docFreq=106, maxDocs=44218)
               0.014289109 = queryNorm
             0.6208449 = fieldWeight in 3466, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.0240583 = idf(docFreq=106, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
         0.24517065 = weight(abstract_txt:morphological in 3466) [ClassicSimilarity], result of:
           0.24517065 = score(doc=3466,freq=1.0), product of:
             0.48830718 = queryWeight, product of:
               4.253952 = boost
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.014289109 = queryNorm
             0.5020828 = fieldWeight in 3466, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.0625 = fieldNorm(doc=3466)
       0.32 = coord(8/25)
   

2. Cui, H.; Boufford, D.; Selden, P.: Semantic annotation of biosystematics literature without training examples (2010) 0.34

   0.3376564 = sum of:
     0.3376564 = product of:
       0.93793446 = sum of:
         0.052296933 = weight(abstract_txt:unsupervised in 3422) [ClassicSimilarity], result of:
           0.052296933 = score(doc=3422,freq=1.0), product of:
             0.1098192 = queryWeight, product of:
               1.0086842 = boost
               7.61935 = idf(docFreq=58, maxDocs=44218)
               0.014289109 = queryNorm
             0.47620937 = fieldWeight in 3422, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.61935 = idf(docFreq=58, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.08586832 = weight(abstract_txt:organ in 3422) [ClassicSimilarity], result of:
           0.08586832 = score(doc=3422,freq=1.0), product of:
             0.15284437 = queryWeight, product of:
               1.189983 = boost
               8.988837 = idf(docFreq=14, maxDocs=44218)
               0.014289109 = queryNorm
             0.5618023 = fieldWeight in 3422, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.988837 = idf(docFreq=14, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.025111642 = weight(abstract_txt:domain in 3422) [ClassicSimilarity], result of:
           0.025111642 = score(doc=3422,freq=1.0), product of:
             0.08484395 = queryWeight, product of:
               1.2538382 = boost
               4.7355914 = idf(docFreq=1054, maxDocs=44218)
               0.014289109 = queryNorm
             0.29597446 = fieldWeight in 3422, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.7355914 = idf(docFreq=1054, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.1148954 = weight(abstract_txt:annotates in 3422) [ClassicSimilarity], result of:
           0.1148954 = score(doc=3422,freq=1.0), product of:
             0.18559341 = queryWeight, product of:
               1.3112857 = boost
               9.905128 = idf(docFreq=5, maxDocs=44218)
               0.014289109 = queryNorm
             0.6190705 = fieldWeight in 3422, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.905128 = idf(docFreq=5, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.06573159 = weight(abstract_txt:syntactic in 3422) [ClassicSimilarity], result of:
           0.06573159 = score(doc=3422,freq=1.0), product of:
             0.16114625 = queryWeight, product of:
               1.7279898 = boost
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.014289109 = queryNorm
             0.4079002 = fieldWeight in 3422, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.031770583 = weight(abstract_txt:semantic in 3422) [ClassicSimilarity], result of:
           0.031770583 = score(doc=3422,freq=1.0), product of:
             0.11361037 = queryWeight, product of:
               1.7769928 = boost
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.014289109 = queryNorm
             0.2796451 = fieldWeight in 3422, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.10419279 = weight(abstract_txt:descriptions in 3422) [ClassicSimilarity], result of:
           0.10419279 = score(doc=3422,freq=2.0), product of:
             0.19904426 = queryWeight, product of:
               2.3520768 = boost
               5.9223356 = idf(docFreq=321, maxDocs=44218)
               0.014289109 = queryNorm
             0.52346545 = fieldWeight in 3422, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.9223356 = idf(docFreq=321, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.21289653 = weight(abstract_txt:annotation in 3422) [ClassicSimilarity], result of:
           0.21289653 = score(doc=3422,freq=3.0), product of:
             0.27998826 = queryWeight, product of:
               2.78963 = boost
               7.0240583 = idf(docFreq=106, maxDocs=44218)
               0.014289109 = queryNorm
             0.76037663 = fieldWeight in 3422, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.0240583 = idf(docFreq=106, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
         0.24517065 = weight(abstract_txt:morphological in 3422) [ClassicSimilarity], result of:
           0.24517065 = score(doc=3422,freq=1.0), product of:
             0.48830718 = queryWeight, product of:
               4.253952 = boost
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.014289109 = queryNorm
             0.5020828 = fieldWeight in 3422, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.0625 = fieldNorm(doc=3422)
       0.36 = coord(9/25)
   

3. Pirkola, A.: Morphological typology of languages for IR (2001) 0.09

   0.08817652 = sum of:
     0.08817652 = product of:
       0.73480433 = sum of:
         0.082164496 = weight(abstract_txt:syntactic in 4476) [ClassicSimilarity], result of:
           0.082164496 = score(doc=4476,freq=1.0), product of:
             0.16114625 = queryWeight, product of:
               1.7279898 = boost
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.014289109 = queryNorm
             0.5098753 = fieldWeight in 4476, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.078125 = fieldNorm(doc=4476)
         0.039713226 = weight(abstract_txt:semantic in 4476) [ClassicSimilarity], result of:
           0.039713226 = score(doc=4476,freq=1.0), product of:
             0.11361037 = queryWeight, product of:
               1.7769928 = boost
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.014289109 = queryNorm
             0.34955636 = fieldWeight in 4476, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.078125 = fieldNorm(doc=4476)
         0.6129266 = weight(abstract_txt:morphological in 4476) [ClassicSimilarity], result of:
           0.6129266 = score(doc=4476,freq=4.0), product of:
             0.48830718 = queryWeight, product of:
               4.253952 = boost
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.014289109 = queryNorm
             1.2552071 = fieldWeight in 4476, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.078125 = fieldNorm(doc=4476)
       0.12 = coord(3/25)
   

4. Jacquemin, C.: Spotting and discovering terms through natural language processing (2001) 0.09

   0.08722588 = sum of:
     0.08722588 = product of:
       0.5451617 = sum of:
         0.06573159 = weight(abstract_txt:syntactic in 119) [ClassicSimilarity], result of:
           0.06573159 = score(doc=119,freq=1.0), product of:
             0.16114625 = queryWeight, product of:
               1.7279898 = boost
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.014289109 = queryNorm
             0.4079002 = fieldWeight in 119, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.0625 = fieldNorm(doc=119)
         0.031770583 = weight(abstract_txt:semantic in 119) [ClassicSimilarity], result of:
           0.031770583 = score(doc=119,freq=1.0), product of:
             0.11361037 = queryWeight, product of:
               1.7769928 = boost
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.014289109 = queryNorm
             0.2796451 = fieldWeight in 119, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4743214 = idf(docFreq=1369, maxDocs=44218)
               0.0625 = fieldNorm(doc=119)
         0.20248888 = weight(abstract_txt:parser in 119) [ClassicSimilarity], result of:
           0.20248888 = score(doc=119,freq=1.0), product of:
             0.39054283 = queryWeight, product of:
               3.2946632 = boost
               8.29569 = idf(docFreq=29, maxDocs=44218)
               0.014289109 = queryNorm
             0.5184806 = fieldWeight in 119, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.29569 = idf(docFreq=29, maxDocs=44218)
               0.0625 = fieldNorm(doc=119)
         0.24517065 = weight(abstract_txt:morphological in 119) [ClassicSimilarity], result of:
           0.24517065 = score(doc=119,freq=1.0), product of:
             0.48830718 = queryWeight, product of:
               4.253952 = boost
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.014289109 = queryNorm
             0.5020828 = fieldWeight in 119, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.0625 = fieldNorm(doc=119)
       0.16 = coord(4/25)
   

5. Snajder, J.; Dalbelo Basic, B.D.; Tadic, M.: Automatic acquisition of inflectional lexica for morphological normalisation (2008) 0.07

   0.070961595 = sum of:
     0.070961595 = product of:
       0.88701993 = sum of:
         0.13634115 = weight(abstract_txt:lexicon in 2910) [ClassicSimilarity], result of:
           0.13634115 = score(doc=2910,freq=4.0), product of:
             0.11293245 = queryWeight, product of:
               1.0228817 = boost
               7.7265954 = idf(docFreq=52, maxDocs=44218)
               0.014289109 = queryNorm
             1.2072805 = fieldWeight in 2910, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               7.7265954 = idf(docFreq=52, maxDocs=44218)
               0.078125 = fieldNorm(doc=2910)
         0.7506788 = weight(abstract_txt:morphological in 2910) [ClassicSimilarity], result of:
           0.7506788 = score(doc=2910,freq=6.0), product of:
             0.48830718 = queryWeight, product of:
               4.253952 = boost
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.014289109 = queryNorm
             1.5373085 = fieldWeight in 2910, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               8.033325 = idf(docFreq=38, maxDocs=44218)
               0.078125 = fieldNorm(doc=2910)
       0.08 = coord(2/25)