Document (#42817)

Author

Zhang, Y.
Zhang, C.
Li, J.

Title

Joint modeling of characters, words, and conversation contexts for microblog keyphrase extraction

Source

Journal of the Association for Information Science and Technology. 71(2020) no.5, S.553-567

Year

2020

Abstract

Millions of messages are produced on microblog platforms every day, leading to the pressing need for automatic identification of key points from the massive texts. To absorb salient content from the vast bulk of microblog posts, this article focuses on the task of microblog keyphrase extraction. In previous work, most efforts treat messages as independent documents and might suffer from the data sparsity problem exhibited in short and informal microblog posts. On the contrary, we propose to enrich contexts via exploiting conversations initialized by target posts and formed by their replies, which are generally centered around relevant topics to the target posts and therefore helpful for keyphrase identification. Concretely, we present a neural keyphrase extraction framework, which has 2 modules: a conversation context encoder and a keyphrase tagger. The conversation context encoder captures indicative representation from their conversation contexts and feeds the representation into the keyphrase tagger, and the keyphrase tagger extracts salient words from target posts. The 2 modules were trained jointly to optimize the conversation context encoding and keyphrase extraction processes. In the conversation context encoder, we leverage hierarchical structures to capture the word-level indicative representation and message-level indicative representation hierarchically. In both of the modules, we apply character-level representations, which enables the model to explore morphological features and deal with the out-of-vocabulary problem caused by the informal language style of microblog messages. Extensive comparison results on real-life data sets indicate that our model outperforms state-of-the-art models from previous studies.

Content

https://asistdl.onlinelibrary.wiley.com/doi/10.1002/asi.24279.

Theme

Automatisches Indexieren
Computerlinguistik

Similar documents (author)

1. Zhang, M.; Zhang, Y.: Professional organizations in Twittersphere : an empirical study of U.S. library and information science professional organizations-related Tweets (2020) 4.54

   4.5423746 = sum of:
     4.5423746 = weight(author_txt:zhang in 5775) [ClassicSimilarity], result of:
       4.5423746 = fieldWeight in 5775, product of:
         1.4142135 = tf(freq=2.0), with freq of:
           2.0 = termFreq=2.0
         6.4238877 = idf(docFreq=194, maxDocs=44218)
         0.5 = fieldNorm(doc=5775)
   

2. Zhang, Y.; Zhang, C.: Enhancing keyphrase extraction from microblogs using human reading time (2021) 4.54

   4.5423746 = sum of:
     4.5423746 = weight(author_txt:zhang in 237) [ClassicSimilarity], result of:
       4.5423746 = fieldWeight in 237, product of:
         1.4142135 = tf(freq=2.0), with freq of:
           2.0 = termFreq=2.0
         6.4238877 = idf(docFreq=194, maxDocs=44218)
         0.5 = fieldNorm(doc=237)
   

3. Zhang, J.: TOFIR: A tool of facilitating information retrieval : introduce a visual retrieval model (2001) 4.01

   4.01493 = sum of:
     4.01493 = weight(author_txt:zhang in 7711) [ClassicSimilarity], result of:
       4.01493 = fieldWeight in 7711, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         6.4238877 = idf(docFreq=194, maxDocs=44218)
         0.625 = fieldNorm(doc=7711)
   

4. Zhang, A.: Multimedia file formats on the Internet : a beginner's guide for PC users (1995) 4.01

   4.01493 = sum of:
     4.01493 = weight(author_txt:zhang in 3212) [ClassicSimilarity], result of:
       4.01493 = fieldWeight in 3212, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         6.4238877 = idf(docFreq=194, maxDocs=44218)
         0.625 = fieldNorm(doc=3212)
   

5. Zhang, J.: ¬A representational analysis of relational information displays (1996) 4.01

   4.01493 = sum of:
     4.01493 = weight(author_txt:zhang in 6403) [ClassicSimilarity], result of:
       4.01493 = fieldWeight in 6403, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         6.4238877 = idf(docFreq=194, maxDocs=44218)
         0.625 = fieldNorm(doc=6403)
   

Similar documents (content)

1. Zhang, Y.; Zhang, C.: Enhancing keyphrase extraction from microblogs using human reading time (2021) 0.43

   0.43289185 = sum of:
     0.43289185 = product of:
       1.352787 = sum of:
         0.01591492 = weight(abstract_txt:previous in 237) [ClassicSimilarity], result of:
           0.01591492 = score(doc=237,freq=1.0), product of:
             0.048652206 = queryWeight, product of:
               1.1645238 = boost
               5.2338576 = idf(docFreq=640, maxDocs=44218)
               0.007982377 = queryNorm
             0.3271161 = fieldWeight in 237, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.2338576 = idf(docFreq=640, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
         0.02407948 = weight(abstract_txt:words in 237) [ClassicSimilarity], result of:
           0.02407948 = score(doc=237,freq=2.0), product of:
             0.050892558 = queryWeight, product of:
               1.1910343 = boost
               5.353007 = idf(docFreq=568, maxDocs=44218)
               0.007982377 = queryNorm
             0.47314343 = fieldWeight in 237, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.353007 = idf(docFreq=568, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
         0.04754532 = weight(abstract_txt:salient in 237) [ClassicSimilarity], result of:
           0.04754532 = score(doc=237,freq=1.0), product of:
             0.10091864 = queryWeight, product of:
               1.6771922 = boost
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.007982377 = queryNorm
             0.47112525 = fieldWeight in 237, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
         0.009943374 = weight(abstract_txt:from in 237) [ClassicSimilarity], result of:
           0.009943374 = score(doc=237,freq=2.0), product of:
             0.04070232 = queryWeight, product of:
               1.8448766 = boost
               2.7638826 = idf(docFreq=7577, maxDocs=44218)
               0.007982377 = queryNorm
             0.24429502 = fieldWeight in 237, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.7638826 = idf(docFreq=7577, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
         0.09127013 = weight(abstract_txt:extraction in 237) [ClassicSimilarity], result of:
           0.09127013 = score(doc=237,freq=3.0), product of:
             0.13617213 = queryWeight, product of:
               2.7552197 = boost
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.007982377 = queryNorm
             0.67025554 = fieldWeight in 237, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
         0.11960985 = weight(abstract_txt:posts in 237) [ClassicSimilarity], result of:
           0.11960985 = score(doc=237,freq=1.0), product of:
             0.2533519 = queryWeight, product of:
               4.2017403 = boost
               7.5537524 = idf(docFreq=62, maxDocs=44218)
               0.007982377 = queryNorm
             0.47210953 = fieldWeight in 237, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.5537524 = idf(docFreq=62, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
         0.36815786 = weight(abstract_txt:microblog in 237) [ClassicSimilarity], result of:
           0.36815786 = score(doc=237,freq=2.0), product of:
             0.45215365 = queryWeight, product of:
               6.1489472 = boost
               9.211981 = idf(docFreq=11, maxDocs=44218)
               0.007982377 = queryNorm
             0.81423175 = fieldWeight in 237, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               9.211981 = idf(docFreq=11, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
         0.676266 = weight(abstract_txt:keyphrase in 237) [ClassicSimilarity], result of:
           0.676266 = score(doc=237,freq=4.0), product of:
             0.5924403 = queryWeight, product of:
               8.127358 = boost
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.007982377 = queryNorm
             1.1414922 = fieldWeight in 237, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.0625 = fieldNorm(doc=237)
       0.32 = coord(8/25)
   

2. Martín-Moncunill, D.; García-Barriocanal, E.; Sicilia, M.-A.; Sánchez-Alonso, S.: Evaluating the practical applicability of thesaurus-based keyphrase extraction in the agricultural domain : insights from the VOA3R project (2015) 0.08

   0.08006595 = sum of:
     0.08006595 = product of:
       0.6672163 = sum of:
         0.007031027 = weight(abstract_txt:from in 2106) [ClassicSimilarity], result of:
           0.007031027 = score(doc=2106,freq=1.0), product of:
             0.04070232 = queryWeight, product of:
               1.8448766 = boost
               2.7638826 = idf(docFreq=7577, maxDocs=44218)
               0.007982377 = queryNorm
             0.17274266 = fieldWeight in 2106, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.7638826 = idf(docFreq=7577, maxDocs=44218)
               0.0625 = fieldNorm(doc=2106)
         0.07452174 = weight(abstract_txt:extraction in 2106) [ClassicSimilarity], result of:
           0.07452174 = score(doc=2106,freq=2.0), product of:
             0.13617213 = queryWeight, product of:
               2.7552197 = boost
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.007982377 = queryNorm
             0.54726136 = fieldWeight in 2106, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.0625 = fieldNorm(doc=2106)
         0.58566356 = weight(abstract_txt:keyphrase in 2106) [ClassicSimilarity], result of:
           0.58566356 = score(doc=2106,freq=3.0), product of:
             0.5924403 = queryWeight, product of:
               8.127358 = boost
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.007982377 = queryNorm
             0.9885613 = fieldWeight in 2106, 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=2106)
       0.12 = coord(3/25)
   

3. Toutanova, K.; Klein, D.; Manning, C.D.; Singer, Y.: Feature-rich Part-of-Speech Tagging with a cyclic dependency network (2003) 0.07

   0.07397648 = sum of:
     0.07397648 = product of:
       0.3698824 = sum of:
         0.02387238 = weight(abstract_txt:previous in 1059) [ClassicSimilarity], result of:
           0.02387238 = score(doc=1059,freq=1.0), product of:
             0.048652206 = queryWeight, product of:
               1.1645238 = boost
               5.2338576 = idf(docFreq=640, maxDocs=44218)
               0.007982377 = queryNorm
             0.49067414 = fieldWeight in 1059, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.2338576 = idf(docFreq=640, maxDocs=44218)
               0.09375 = fieldNorm(doc=1059)
         0.025540145 = weight(abstract_txt:words in 1059) [ClassicSimilarity], result of:
           0.025540145 = score(doc=1059,freq=1.0), product of:
             0.050892558 = queryWeight, product of:
               1.1910343 = boost
               5.353007 = idf(docFreq=568, maxDocs=44218)
               0.007982377 = queryNorm
             0.5018444 = fieldWeight in 1059, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.353007 = idf(docFreq=568, maxDocs=44218)
               0.09375 = fieldNorm(doc=1059)
         0.047977753 = weight(abstract_txt:contexts in 1059) [ClassicSimilarity], result of:
           0.047977753 = score(doc=1059,freq=1.0), product of:
             0.088694304 = queryWeight, product of:
               1.9257088 = boost
               5.7699614 = idf(docFreq=374, maxDocs=44218)
               0.007982377 = queryNorm
             0.54093385 = fieldWeight in 1059, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7699614 = idf(docFreq=374, maxDocs=44218)
               0.09375 = fieldNorm(doc=1059)
         0.039807886 = weight(abstract_txt:representation in 1059) [ClassicSimilarity], result of:
           0.039807886 = score(doc=1059,freq=1.0), product of:
             0.086197525 = queryWeight, product of:
               2.1920958 = boost
               4.926098 = idf(docFreq=871, maxDocs=44218)
               0.007982377 = queryNorm
             0.46182168 = fieldWeight in 1059, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.926098 = idf(docFreq=871, maxDocs=44218)
               0.09375 = fieldNorm(doc=1059)
         0.23268422 = weight(abstract_txt:tagger in 1059) [ClassicSimilarity], result of:
           0.23268422 = score(doc=1059,freq=2.0), product of:
             0.201699 = queryWeight, product of:
               2.9039867 = boost
               8.701155 = idf(docFreq=19, maxDocs=44218)
               0.007982377 = queryNorm
             1.1536211 = fieldWeight in 1059, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.701155 = idf(docFreq=19, maxDocs=44218)
               0.09375 = fieldNorm(doc=1059)
       0.2 = coord(5/25)
   

4. Tseng, Y.-H.; Lin, C.-J.; Lin, Y.-I.: Text mining techniques for patent analysis (2007) 0.07

   0.07229507 = sum of:
     0.07229507 = product of:
       0.4518442 = sum of:
         0.017026763 = weight(abstract_txt:words in 935) [ClassicSimilarity], result of:
           0.017026763 = score(doc=935,freq=1.0), product of:
             0.050892558 = queryWeight, product of:
               1.1910343 = boost
               5.353007 = idf(docFreq=568, maxDocs=44218)
               0.007982377 = queryNorm
             0.33456293 = fieldWeight in 935, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.353007 = idf(docFreq=568, maxDocs=44218)
               0.0625 = fieldNorm(doc=935)
         0.022162665 = weight(abstract_txt:identification in 935) [ClassicSimilarity], result of:
           0.022162665 = score(doc=935,freq=1.0), product of:
             0.06067096 = queryWeight, product of:
               1.3004317 = boost
               5.8446846 = idf(docFreq=347, maxDocs=44218)
               0.007982377 = queryNorm
             0.3652928 = fieldWeight in 935, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8446846 = idf(docFreq=347, maxDocs=44218)
               0.0625 = fieldNorm(doc=935)
         0.07452174 = weight(abstract_txt:extraction in 935) [ClassicSimilarity], result of:
           0.07452174 = score(doc=935,freq=2.0), product of:
             0.13617213 = queryWeight, product of:
               2.7552197 = boost
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.007982377 = queryNorm
             0.54726136 = fieldWeight in 935, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.0625 = fieldNorm(doc=935)
         0.338133 = weight(abstract_txt:keyphrase in 935) [ClassicSimilarity], result of:
           0.338133 = score(doc=935,freq=1.0), product of:
             0.5924403 = queryWeight, product of:
               8.127358 = boost
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.007982377 = queryNorm
             0.5707461 = fieldWeight in 935, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.0625 = fieldNorm(doc=935)
       0.16 = coord(4/25)
   

5. Daudaravicius, V.: ¬A framework for keyphrase extraction from scientific journals (2016) 0.07

   0.07213881 = sum of:
     0.07213881 = product of:
       0.6011568 = sum of:
         0.014915061 = weight(abstract_txt:from in 2930) [ClassicSimilarity], result of:
           0.014915061 = score(doc=2930,freq=2.0), product of:
             0.04070232 = queryWeight, product of:
               1.8448766 = boost
               2.7638826 = idf(docFreq=7577, maxDocs=44218)
               0.007982377 = queryNorm
             0.36644253 = fieldWeight in 2930, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.7638826 = idf(docFreq=7577, maxDocs=44218)
               0.09375 = fieldNorm(doc=2930)
         0.07904225 = weight(abstract_txt:extraction in 2930) [ClassicSimilarity], result of:
           0.07904225 = score(doc=2930,freq=1.0), product of:
             0.13617213 = queryWeight, product of:
               2.7552197 = boost
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.007982377 = queryNorm
             0.58045834 = fieldWeight in 2930, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.09375 = fieldNorm(doc=2930)
         0.50719947 = weight(abstract_txt:keyphrase in 2930) [ClassicSimilarity], result of:
           0.50719947 = score(doc=2930,freq=1.0), product of:
             0.5924403 = queryWeight, product of:
               8.127358 = boost
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.007982377 = queryNorm
             0.85611916 = fieldWeight in 2930, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.131938 = idf(docFreq=12, maxDocs=44218)
               0.09375 = fieldNorm(doc=2930)
       0.12 = coord(3/25)