Document (#32951)

Author

Dorr, B.J.
Gaasterland, T.

Title

Exploiting aspectual features and connecting words for summarization-inspired temporal-relation extraction

Source

Information processing and management. 43(2007) no.6, S.1681-1704

Year

2007

Abstract

This paper presents a model that incorporates contemporary theories of tense and aspect and develops a new framework for extracting temporal relations between two sentence-internal events, given their tense, aspect, and a temporal connecting word relating the two events. A linguistic constraint on event combination has been implemented to detect incorrect parser analyses and potentially apply syntactic reanalysis or semantic reinterpretation - in preparation for subsequent processing for multi-document summarization. An important contribution of this work is the extension of two different existing theoretical frameworks - Hornstein's 1990 theory of tense analysis and Allen's 1984 theory on event ordering - and the combination of both into a unified system for representing and constraining combinations of different event types (points, closed intervals, and open-ended intervals). We show that our theoretical results have been verified in a large-scale corpus analysis. The framework is designed to inform a temporally motivated sentence-ordering module in an implemented multi-document summarization system.

Theme

Automatisches Abstracting

Similar documents (author)

1. Dorr, B.J.: Large-scale dictionary construction for foreign language tutoring and interlingual machine translation (1997) 5.81

   5.81187 = sum of:
     5.81187 = weight(author_txt:dorr in 3244) [ClassicSimilarity], result of:
       5.81187 = fieldWeight in 3244, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.298992 = idf(docFreq=10, maxDocs=44218)
         0.625 = fieldNorm(doc=3244)
   

2. Dorr, B.J.; Olsen, M.B.: Multilingual generation : the role of telicity in lexical choice and syntactic realization (1996) 4.65

   4.649496 = sum of:
     4.649496 = weight(author_txt:dorr in 536) [ClassicSimilarity], result of:
       4.649496 = fieldWeight in 536, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.298992 = idf(docFreq=10, maxDocs=44218)
         0.5 = fieldNorm(doc=536)
   

3. Oard, D.W.; Dorr, B.J.: Evaluating cross-laguage text filtering effectiveness (1998) 4.65

   4.649496 = sum of:
     4.649496 = weight(author_txt:dorr in 6214) [ClassicSimilarity], result of:
       4.649496 = fieldWeight in 6214, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.298992 = idf(docFreq=10, maxDocs=44218)
         0.5 = fieldNorm(doc=6214)
   

4. Schacter, J.; Chung, G.K.W.K.; Dorr, A.: Children's Internet searching on complex problems : performance and process analyses (1998) 3.49

   3.487122 = sum of:
     3.487122 = weight(author_txt:dorr in 3552) [ClassicSimilarity], result of:
       3.487122 = fieldWeight in 3552, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.298992 = idf(docFreq=10, maxDocs=44218)
         0.375 = fieldNorm(doc=3552)
   

5. Zajic, D.M.; Dorr, B.J.; Lin, J.: Single-document and multi-document summarization techniques for email threads using sentence compression (2008) 3.49

   3.487122 = sum of:
     3.487122 = weight(author_txt:dorr in 2105) [ClassicSimilarity], result of:
       3.487122 = fieldWeight in 2105, product of:
         1.0 = tf(freq=1.0), with freq of:
           1.0 = termFreq=1.0
         9.298992 = idf(docFreq=10, maxDocs=44218)
         0.375 = fieldNorm(doc=2105)
   

Similar documents (content)

1. Ou, S.; Khoo, C.S.G.; Goh, D.H.: Multi-document summarization of news articles using an event-based framework (2006) 0.35

   0.3491841 = sum of:
     0.3491841 = product of:
       1.0912004 = sum of:
         0.044320785 = weight(abstract_txt:document in 657) [ClassicSimilarity], result of:
           0.044320785 = score(doc=657,freq=4.0), product of:
             0.08259926 = queryWeight, product of:
               1.1242427 = boost
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.017115707 = queryNorm
             0.53657603 = fieldWeight in 657, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
         0.074688084 = weight(abstract_txt:framework in 657) [ClassicSimilarity], result of:
           0.074688084 = score(doc=657,freq=8.0), product of:
             0.09283864 = queryWeight, product of:
               1.1918906 = boost
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.017115707 = queryNorm
             0.80449355 = fieldWeight in 657, product of:
               2.828427 = tf(freq=8.0), with freq of:
                 8.0 = termFreq=8.0
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
         0.07600565 = weight(abstract_txt:implemented in 657) [ClassicSimilarity], result of:
           0.07600565 = score(doc=657,freq=2.0), product of:
             0.14910029 = queryWeight, product of:
               1.5104669 = boost
               5.767298 = idf(docFreq=375, maxDocs=44218)
               0.017115707 = queryNorm
             0.5097619 = fieldWeight in 657, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.767298 = idf(docFreq=375, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
         0.10192474 = weight(abstract_txt:multi in 657) [ClassicSimilarity], result of:
           0.10192474 = score(doc=657,freq=3.0), product of:
             0.15839344 = queryWeight, product of:
               1.5568279 = boost
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.017115707 = queryNorm
             0.6434909 = fieldWeight in 657, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
         0.06926848 = weight(abstract_txt:events in 657) [ClassicSimilarity], result of:
           0.06926848 = score(doc=657,freq=1.0), product of:
             0.17658277 = queryWeight, product of:
               1.6437893 = boost
               6.2763524 = idf(docFreq=225, maxDocs=44218)
               0.017115707 = queryNorm
             0.39227203 = fieldWeight in 657, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.2763524 = idf(docFreq=225, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
         0.12706377 = weight(abstract_txt:sentence in 657) [ClassicSimilarity], result of:
           0.12706377 = score(doc=657,freq=2.0), product of:
             0.21002083 = queryWeight, product of:
               1.7926817 = boost
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.017115707 = queryNorm
             0.60500556 = fieldWeight in 657, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
         0.38227743 = weight(abstract_txt:event in 657) [ClassicSimilarity], result of:
           0.38227743 = score(doc=657,freq=7.0), product of:
             0.32999554 = queryWeight, product of:
               2.7521472 = boost
               7.0055394 = idf(docFreq=108, maxDocs=44218)
               0.017115707 = queryNorm
             1.1584321 = fieldWeight in 657, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               7.0055394 = idf(docFreq=108, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
         0.21565145 = weight(abstract_txt:summarization in 657) [ClassicSimilarity], result of:
           0.21565145 = score(doc=657,freq=2.0), product of:
             0.3420686 = queryWeight, product of:
               2.8020394 = boost
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.017115707 = queryNorm
             0.6304333 = fieldWeight in 657, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.0625 = fieldNorm(doc=657)
       0.32 = coord(8/25)
   

2. Zajic, D.; Dorr, B.J.; Lin, J.; Schwartz, R.: Multi-candidate reduction : sentence compression as a tool for document summarization tasks (2007) 0.24

   0.24241218 = sum of:
     0.24241218 = product of:
       1.0100508 = sum of:
         0.06648117 = weight(abstract_txt:document in 944) [ClassicSimilarity], result of:
           0.06648117 = score(doc=944,freq=4.0), product of:
             0.08259926 = queryWeight, product of:
               1.1242427 = boost
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.017115707 = queryNorm
             0.80486405 = fieldWeight in 944, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.09375 = fieldNorm(doc=944)
         0.056016065 = weight(abstract_txt:framework in 944) [ClassicSimilarity], result of:
           0.056016065 = score(doc=944,freq=2.0), product of:
             0.09283864 = queryWeight, product of:
               1.1918906 = boost
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.017115707 = queryNorm
             0.6033702 = fieldWeight in 944, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.09375 = fieldNorm(doc=944)
         0.08140677 = weight(abstract_txt:combination in 944) [ClassicSimilarity], result of:
           0.08140677 = score(doc=944,freq=1.0), product of:
             0.15007351 = queryWeight, product of:
               1.5153886 = boost
               5.7860904 = idf(docFreq=368, maxDocs=44218)
               0.017115707 = queryNorm
             0.54244596 = fieldWeight in 944, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7860904 = idf(docFreq=368, maxDocs=44218)
               0.09375 = fieldNorm(doc=944)
         0.17653883 = weight(abstract_txt:multi in 944) [ClassicSimilarity], result of:
           0.17653883 = score(doc=944,freq=4.0), product of:
             0.15839344 = queryWeight, product of:
               1.5568279 = boost
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.017115707 = queryNorm
             1.1145589 = fieldWeight in 944, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.09375 = fieldNorm(doc=944)
         0.23343104 = weight(abstract_txt:sentence in 944) [ClassicSimilarity], result of:
           0.23343104 = score(doc=944,freq=3.0), product of:
             0.21002083 = queryWeight, product of:
               1.7926817 = boost
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.017115707 = queryNorm
             1.1114662 = fieldWeight in 944, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.09375 = fieldNorm(doc=944)
         0.396177 = weight(abstract_txt:summarization in 944) [ClassicSimilarity], result of:
           0.396177 = score(doc=944,freq=3.0), product of:
             0.3420686 = queryWeight, product of:
               2.8020394 = boost
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.017115707 = queryNorm
             1.1581799 = fieldWeight in 944, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.09375 = fieldNorm(doc=944)
       0.24 = coord(6/25)
   

3. Zajic, D.M.; Dorr, B.J.; Lin, J.: Single-document and multi-document summarization techniques for email threads using sentence compression (2008) 0.21

   0.21025404 = sum of:
     0.21025404 = product of:
       0.8760585 = sum of:
         0.039174408 = weight(abstract_txt:document in 2105) [ClassicSimilarity], result of:
           0.039174408 = score(doc=2105,freq=2.0), product of:
             0.08259926 = queryWeight, product of:
               1.1242427 = boost
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.017115707 = queryNorm
             0.4742707 = fieldWeight in 2105, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.078125 = fieldNorm(doc=2105)
         0.033007782 = weight(abstract_txt:framework in 2105) [ClassicSimilarity], result of:
           0.033007782 = score(doc=2105,freq=1.0), product of:
             0.09283864 = queryWeight, product of:
               1.1918906 = boost
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.017115707 = queryNorm
             0.3555393 = fieldWeight in 2105, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.078125 = fieldNorm(doc=2105)
         0.06718014 = weight(abstract_txt:implemented in 2105) [ClassicSimilarity], result of:
           0.06718014 = score(doc=2105,freq=1.0), product of:
             0.14910029 = queryWeight, product of:
               1.5104669 = boost
               5.767298 = idf(docFreq=375, maxDocs=44218)
               0.017115707 = queryNorm
             0.45057017 = fieldWeight in 2105, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.767298 = idf(docFreq=375, maxDocs=44218)
               0.078125 = fieldNorm(doc=2105)
         0.073557846 = weight(abstract_txt:multi in 2105) [ClassicSimilarity], result of:
           0.073557846 = score(doc=2105,freq=1.0), product of:
             0.15839344 = queryWeight, product of:
               1.5568279 = boost
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.017115707 = queryNorm
             0.46439958 = fieldWeight in 2105, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.078125 = fieldNorm(doc=2105)
         0.1588297 = weight(abstract_txt:sentence in 2105) [ClassicSimilarity], result of:
           0.1588297 = score(doc=2105,freq=2.0), product of:
             0.21002083 = queryWeight, product of:
               1.7926817 = boost
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.017115707 = queryNorm
             0.75625694 = fieldWeight in 2105, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.078125 = fieldNorm(doc=2105)
         0.50430864 = weight(abstract_txt:summarization in 2105) [ClassicSimilarity], result of:
           0.50430864 = score(doc=2105,freq=7.0), product of:
             0.3420686 = queryWeight, product of:
               2.8020394 = boost
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.017115707 = queryNorm
             1.474291 = fieldWeight in 2105, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.078125 = fieldNorm(doc=2105)
       0.24 = coord(6/25)
   

4. Kar, M.; Nunes, S.; Ribeiro, C.: Summarization of changes in dynamic text collections using Latent Dirichlet Allocation model (2015) 0.14

   0.13633662 = sum of:
     0.13633662 = product of:
       0.6816831 = sum of:
         0.037164107 = weight(abstract_txt:document in 2676) [ClassicSimilarity], result of:
           0.037164107 = score(doc=2676,freq=5.0), product of:
             0.08259926 = queryWeight, product of:
               1.1242427 = boost
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.017115707 = queryNorm
             0.4499327 = fieldWeight in 2676, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.046875 = fieldNorm(doc=2676)
         0.13392307 = weight(abstract_txt:intervals in 2676) [ClassicSimilarity], result of:
           0.13392307 = score(doc=2676,freq=1.0), product of:
             0.33198667 = queryWeight, product of:
               2.253888 = boost
               8.6058445 = idf(docFreq=21, maxDocs=44218)
               0.017115707 = queryNorm
             0.40339896 = fieldWeight in 2676, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.6058445 = idf(docFreq=21, maxDocs=44218)
               0.046875 = fieldNorm(doc=2676)
         0.1464993 = weight(abstract_txt:temporal in 2676) [ClassicSimilarity], result of:
           0.1464993 = score(doc=2676,freq=2.0), product of:
             0.32022938 = queryWeight, product of:
               2.7111168 = boost
               6.901097 = idf(docFreq=120, maxDocs=44218)
               0.017115707 = queryNorm
             0.4574824 = fieldWeight in 2676, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.901097 = idf(docFreq=120, maxDocs=44218)
               0.046875 = fieldNorm(doc=2676)
         0.108365476 = weight(abstract_txt:event in 2676) [ClassicSimilarity], result of:
           0.108365476 = score(doc=2676,freq=1.0), product of:
             0.32999554 = queryWeight, product of:
               2.7521472 = boost
               7.0055394 = idf(docFreq=108, maxDocs=44218)
               0.017115707 = queryNorm
             0.32838467 = fieldWeight in 2676, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.0055394 = idf(docFreq=108, maxDocs=44218)
               0.046875 = fieldNorm(doc=2676)
         0.25573117 = weight(abstract_txt:summarization in 2676) [ClassicSimilarity], result of:
           0.25573117 = score(doc=2676,freq=5.0), product of:
             0.3420686 = queryWeight, product of:
               2.8020394 = boost
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.017115707 = queryNorm
             0.747602 = fieldWeight in 2676, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.046875 = fieldNorm(doc=2676)
       0.2 = coord(5/25)
   

5. Xiong, S.; Ji, D.: Query-focused multi-document summarization using hypergraph-based ranking (2016) 0.12

   0.11644919 = sum of:
     0.11644919 = product of:
       0.58224595 = sum of:
         0.039174408 = weight(abstract_txt:document in 2972) [ClassicSimilarity], result of:
           0.039174408 = score(doc=2972,freq=2.0), product of:
             0.08259926 = queryWeight, product of:
               1.1242427 = boost
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.017115707 = queryNorm
             0.4742707 = fieldWeight in 2972, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.2926083 = idf(docFreq=1642, maxDocs=44218)
               0.078125 = fieldNorm(doc=2972)
         0.057171155 = weight(abstract_txt:framework in 2972) [ClassicSimilarity], result of:
           0.057171155 = score(doc=2972,freq=3.0), product of:
             0.09283864 = queryWeight, product of:
               1.1918906 = boost
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.017115707 = queryNorm
             0.61581206 = fieldWeight in 2972, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.550903 = idf(docFreq=1268, maxDocs=44218)
               0.078125 = fieldNorm(doc=2972)
         0.10402651 = weight(abstract_txt:multi in 2972) [ClassicSimilarity], result of:
           0.10402651 = score(doc=2972,freq=2.0), product of:
             0.15839344 = queryWeight, product of:
               1.5568279 = boost
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.017115707 = queryNorm
             0.6567602 = fieldWeight in 2972, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.9443145 = idf(docFreq=314, maxDocs=44218)
               0.078125 = fieldNorm(doc=2972)
         0.112309575 = weight(abstract_txt:sentence in 2972) [ClassicSimilarity], result of:
           0.112309575 = score(doc=2972,freq=1.0), product of:
             0.21002083 = queryWeight, product of:
               1.7926817 = boost
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.017115707 = queryNorm
             0.53475446 = fieldWeight in 2972, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.8448567 = idf(docFreq=127, maxDocs=44218)
               0.078125 = fieldNorm(doc=2972)
         0.2695643 = weight(abstract_txt:summarization in 2972) [ClassicSimilarity], result of:
           0.2695643 = score(doc=2972,freq=2.0), product of:
             0.3420686 = queryWeight, product of:
               2.8020394 = boost
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.017115707 = queryNorm
             0.78804165 = fieldWeight in 2972, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.078125 = fieldNorm(doc=2972)
       0.2 = coord(5/25)