Document (#10982)

Author

Stede, M.

Title

Lexicalization in natural language generation : a survey

Source

Artificial intelligence review. 8(1994/95) no.4, S.309-336

Year

1994/95

Abstract

In natural language generation, a meaning representation of some kind is successively transformed into a sentence or a text. Naturally, a central subtask of this problem is the choice of words, or lexicalization. Proposes 4 major issues that determine how a generator tackles lexicalization, and surveys the contributions that research have made to them. Identifies open problems, and sketches a possible direction for research

Theme

Computerlinguistik

Similar documents (content)

1. Stede, M.: Lexicalization in natural language generation (2002) 0.29

   0.29379538 = sum of:
     0.29379538 = product of:
       0.7344884 = sum of:
         0.059525363 = weight(abstract_txt:words in 5245) [ClassicSimilarity], result of:
           0.059525363 = score(doc=5245,freq=3.0), product of:
             0.11733471 = queryWeight, product of:
               1.1113919 = boost
               5.355831 = idf(docFreq=569, maxDocs=44421)
               0.019712077 = queryNorm
             0.5073125 = fieldWeight in 5245, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.355831 = idf(docFreq=569, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.036357537 = weight(abstract_txt:central in 5245) [ClassicSimilarity], result of:
           0.036357537 = score(doc=5245,freq=1.0), product of:
             0.12182278 = queryWeight, product of:
               1.1324478 = boost
               5.4573007 = idf(docFreq=514, maxDocs=44421)
               0.019712077 = queryNorm
             0.29844612 = fieldWeight in 5245, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.4573007 = idf(docFreq=514, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.039074756 = weight(abstract_txt:meaning in 5245) [ClassicSimilarity], result of:
           0.039074756 = score(doc=5245,freq=1.0), product of:
             0.12781928 = queryWeight, product of:
               1.1599845 = boost
               5.59 = idf(docFreq=450, maxDocs=44421)
               0.019712077 = queryNorm
             0.30570313 = fieldWeight in 5245, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.59 = idf(docFreq=450, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.055195577 = weight(abstract_txt:surveys in 5245) [ClassicSimilarity], result of:
           0.055195577 = score(doc=5245,freq=1.0), product of:
             0.16091692 = queryWeight, product of:
               1.3015319 = boost
               6.272122 = idf(docFreq=227, maxDocs=44421)
               0.019712077 = queryNorm
             0.34300667 = fieldWeight in 5245, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.272122 = idf(docFreq=227, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.014111709 = weight(abstract_txt:research in 5245) [ClassicSimilarity], result of:
           0.014111709 = score(doc=5245,freq=1.0), product of:
             0.08166988 = queryWeight, product of:
               1.3112936 = boost
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.019712077 = queryNorm
             0.17278963 = fieldWeight in 5245, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.07188289 = weight(abstract_txt:sentence in 5245) [ClassicSimilarity], result of:
           0.07188289 = score(doc=5245,freq=1.0), product of:
             0.19190335 = queryWeight, product of:
               1.421331 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.019712077 = queryNorm
             0.3745786 = fieldWeight in 5245, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.072592616 = weight(abstract_txt:language in 5245) [ClassicSimilarity], result of:
           0.072592616 = score(doc=5245,freq=5.0), product of:
             0.14232478 = queryWeight, product of:
               1.7310485 = boost
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.019712077 = queryNorm
             0.51004905 = fieldWeight in 5245, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.1451292 = weight(abstract_txt:generator in 5245) [ClassicSimilarity], result of:
           0.1451292 = score(doc=5245,freq=1.0), product of:
             0.30655053 = queryWeight, product of:
               1.7964082 = boost
               8.656945 = idf(docFreq=20, maxDocs=44421)
               0.019712077 = queryNorm
             0.4734267 = fieldWeight in 5245, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.656945 = idf(docFreq=20, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.08243133 = weight(abstract_txt:natural in 5245) [ClassicSimilarity], result of:
           0.08243133 = score(doc=5245,freq=2.0), product of:
             0.21024568 = queryWeight, product of:
               2.103936 = boost
               5.0694656 = idf(docFreq=758, maxDocs=44421)
               0.019712077 = queryNorm
             0.39207146 = fieldWeight in 5245, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.0694656 = idf(docFreq=758, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
         0.15818743 = weight(abstract_txt:generation in 5245) [ClassicSimilarity], result of:
           0.15818743 = score(doc=5245,freq=4.0), product of:
             0.25769353 = queryWeight, product of:
               2.329275 = boost
               5.612423 = idf(docFreq=440, maxDocs=44421)
               0.019712077 = queryNorm
             0.61385876 = fieldWeight in 5245, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               5.612423 = idf(docFreq=440, maxDocs=44421)
               0.0546875 = fieldNorm(doc=5245)
       0.4 = coord(10/25)
   

2. Hazrina, S.; Sharef, N.M.; Ibrahim, H.; Murad, M.A.A.; Noah, S.A.M.: Review on the advancements of disambiguation in semantic question answering system (2017) 0.13

   0.12687272 = sum of:
     0.12687272 = product of:
       0.39647725 = sum of:
         0.035404198 = weight(abstract_txt:open in 4292) [ClassicSimilarity], result of:
           0.035404198 = score(doc=4292,freq=2.0), product of:
             0.0949931 = queryWeight, product of:
               4.8190303 = idf(docFreq=974, maxDocs=44421)
               0.019712077 = queryNorm
             0.37270284 = fieldWeight in 4292, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.8190303 = idf(docFreq=974, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
         0.048602257 = weight(abstract_txt:words in 4292) [ClassicSimilarity], result of:
           0.048602257 = score(doc=4292,freq=2.0), product of:
             0.11733471 = queryWeight, product of:
               1.1113919 = boost
               5.355831 = idf(docFreq=569, maxDocs=44421)
               0.019712077 = queryNorm
             0.41421893 = fieldWeight in 4292, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.355831 = idf(docFreq=569, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
         0.06767946 = weight(abstract_txt:meaning in 4292) [ClassicSimilarity], result of:
           0.06767946 = score(doc=4292,freq=3.0), product of:
             0.12781928 = queryWeight, product of:
               1.1599845 = boost
               5.59 = idf(docFreq=450, maxDocs=44421)
               0.019712077 = queryNorm
             0.52949333 = fieldWeight in 4292, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.59 = idf(docFreq=450, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
         0.04875208 = weight(abstract_txt:contributions in 4292) [ClassicSimilarity], result of:
           0.04875208 = score(doc=4292,freq=1.0), product of:
             0.14813612 = queryWeight, product of:
               1.2487757 = boost
               6.017888 = idf(docFreq=293, maxDocs=44421)
               0.019712077 = queryNorm
             0.32910326 = fieldWeight in 4292, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.017888 = idf(docFreq=293, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
         0.019956972 = weight(abstract_txt:research in 4292) [ClassicSimilarity], result of:
           0.019956972 = score(doc=4292,freq=2.0), product of:
             0.08166988 = queryWeight, product of:
               1.3112936 = boost
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.019712077 = queryNorm
             0.24436146 = fieldWeight in 4292, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
         0.07188289 = weight(abstract_txt:sentence in 4292) [ClassicSimilarity], result of:
           0.07188289 = score(doc=4292,freq=1.0), product of:
             0.19190335 = queryWeight, product of:
               1.421331 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.019712077 = queryNorm
             0.3745786 = fieldWeight in 4292, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
         0.045911606 = weight(abstract_txt:language in 4292) [ClassicSimilarity], result of:
           0.045911606 = score(doc=4292,freq=2.0), product of:
             0.14232478 = queryWeight, product of:
               1.7310485 = boost
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.019712077 = queryNorm
             0.32258338 = fieldWeight in 4292, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
         0.05828776 = weight(abstract_txt:natural in 4292) [ClassicSimilarity], result of:
           0.05828776 = score(doc=4292,freq=1.0), product of:
             0.21024568 = queryWeight, product of:
               2.103936 = boost
               5.0694656 = idf(docFreq=758, maxDocs=44421)
               0.019712077 = queryNorm
             0.2772364 = fieldWeight in 4292, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.0694656 = idf(docFreq=758, maxDocs=44421)
               0.0546875 = fieldNorm(doc=4292)
       0.32 = coord(8/25)
   

3. Altinel, B.; Ganiz, M.C.: Semantic text classification : a survey of past and recent advances (2018) 0.11

   0.11056176 = sum of:
     0.11056176 = product of:
       0.39486343 = sum of:
         0.03857 = weight(abstract_txt:survey in 51) [ClassicSimilarity], result of:
           0.03857 = score(doc=51,freq=2.0), product of:
             0.10057467 = queryWeight, product of:
               1.0289595 = boost
               4.958587 = idf(docFreq=847, maxDocs=44421)
               0.019712077 = queryNorm
             0.38349617 = fieldWeight in 51, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.958587 = idf(docFreq=847, maxDocs=44421)
               0.0546875 = fieldNorm(doc=51)
         0.09092649 = weight(abstract_txt:words in 51) [ClassicSimilarity], result of:
           0.09092649 = score(doc=51,freq=7.0), product of:
             0.11733471 = queryWeight, product of:
               1.1113919 = boost
               5.355831 = idf(docFreq=569, maxDocs=44421)
               0.019712077 = queryNorm
             0.7749326 = fieldWeight in 51, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               5.355831 = idf(docFreq=569, maxDocs=44421)
               0.0546875 = fieldNorm(doc=51)
         0.039074756 = weight(abstract_txt:meaning in 51) [ClassicSimilarity], result of:
           0.039074756 = score(doc=51,freq=1.0), product of:
             0.12781928 = queryWeight, product of:
               1.1599845 = boost
               5.59 = idf(docFreq=450, maxDocs=44421)
               0.019712077 = queryNorm
             0.30570313 = fieldWeight in 51, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.59 = idf(docFreq=450, maxDocs=44421)
               0.0546875 = fieldNorm(doc=51)
         0.07805833 = weight(abstract_txt:surveys in 51) [ClassicSimilarity], result of:
           0.07805833 = score(doc=51,freq=2.0), product of:
             0.16091692 = queryWeight, product of:
               1.3015319 = boost
               6.272122 = idf(docFreq=227, maxDocs=44421)
               0.019712077 = queryNorm
             0.48508468 = fieldWeight in 51, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.272122 = idf(docFreq=227, maxDocs=44421)
               0.0546875 = fieldNorm(doc=51)
         0.014111709 = weight(abstract_txt:research in 51) [ClassicSimilarity], result of:
           0.014111709 = score(doc=51,freq=1.0), product of:
             0.08166988 = queryWeight, product of:
               1.3112936 = boost
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.019712077 = queryNorm
             0.17278963 = fieldWeight in 51, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.0546875 = fieldNorm(doc=51)
         0.101657756 = weight(abstract_txt:sentence in 51) [ClassicSimilarity], result of:
           0.101657756 = score(doc=51,freq=2.0), product of:
             0.19190335 = queryWeight, product of:
               1.421331 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.019712077 = queryNorm
             0.52973413 = fieldWeight in 51, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.0546875 = fieldNorm(doc=51)
         0.032464407 = weight(abstract_txt:language in 51) [ClassicSimilarity], result of:
           0.032464407 = score(doc=51,freq=1.0), product of:
             0.14232478 = queryWeight, product of:
               1.7310485 = boost
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.019712077 = queryNorm
             0.22810088 = fieldWeight in 51, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.0546875 = fieldNorm(doc=51)
       0.28 = coord(7/25)
   

4. Wanner, L.: Lexical choice in text generation and machine translation (1996) 0.10

   0.10186231 = sum of:
     0.10186231 = product of:
       0.6366395 = sum of:
         0.08786174 = weight(abstract_txt:identifies in 135) [ClassicSimilarity], result of:
           0.08786174 = score(doc=135,freq=1.0), product of:
             0.13820128 = queryWeight, product of:
               1.2061741 = boost
               5.8125896 = idf(docFreq=360, maxDocs=44421)
               0.019712077 = queryNorm
             0.63575196 = fieldWeight in 135, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8125896 = idf(docFreq=360, maxDocs=44421)
               0.109375 = fieldNorm(doc=135)
         0.23487508 = weight(abstract_txt:choice in 135) [ClassicSimilarity], result of:
           0.23487508 = score(doc=135,freq=6.0), product of:
             0.14649397 = queryWeight, product of:
               1.2418349 = boost
               5.98444 = idf(docFreq=303, maxDocs=44421)
               0.019712077 = queryNorm
             1.6033089 = fieldWeight in 135, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               5.98444 = idf(docFreq=303, maxDocs=44421)
               0.109375 = fieldNorm(doc=135)
         0.039913945 = weight(abstract_txt:research in 135) [ClassicSimilarity], result of:
           0.039913945 = score(doc=135,freq=2.0), product of:
             0.08166988 = queryWeight, product of:
               1.3112936 = boost
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.019712077 = queryNorm
             0.48872292 = fieldWeight in 135, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.159582 = idf(docFreq=5124, maxDocs=44421)
               0.109375 = fieldNorm(doc=135)
         0.27398866 = weight(abstract_txt:generation in 135) [ClassicSimilarity], result of:
           0.27398866 = score(doc=135,freq=3.0), product of:
             0.25769353 = queryWeight, product of:
               2.329275 = boost
               5.612423 = idf(docFreq=440, maxDocs=44421)
               0.019712077 = queryNorm
             1.0632346 = fieldWeight in 135, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.612423 = idf(docFreq=440, maxDocs=44421)
               0.109375 = fieldNorm(doc=135)
       0.16 = coord(4/25)
   

5. Helbig, H.: Knowledge representation and the semantics of natural language (2014) 0.10

   0.10070106 = sum of:
     0.10070106 = product of:
       0.5035053 = sum of:
         0.05293263 = weight(abstract_txt:representation in 3396) [ClassicSimilarity], result of:
           0.05293263 = score(doc=3396,freq=3.0), product of:
             0.099261194 = queryWeight, product of:
               1.0222185 = boost
               4.9261017 = idf(docFreq=875, maxDocs=44421)
               0.019712077 = queryNorm
             0.5332661 = fieldWeight in 3396, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.9261017 = idf(docFreq=875, maxDocs=44421)
               0.0625 = fieldNorm(doc=3396)
         0.04155147 = weight(abstract_txt:central in 3396) [ClassicSimilarity], result of:
           0.04155147 = score(doc=3396,freq=1.0), product of:
             0.12182278 = queryWeight, product of:
               1.1324478 = boost
               5.4573007 = idf(docFreq=514, maxDocs=44421)
               0.019712077 = queryNorm
             0.3410813 = fieldWeight in 3396, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.4573007 = idf(docFreq=514, maxDocs=44421)
               0.0625 = fieldNorm(doc=3396)
         0.10494081 = weight(abstract_txt:language in 3396) [ClassicSimilarity], result of:
           0.10494081 = score(doc=3396,freq=8.0), product of:
             0.14232478 = queryWeight, product of:
               1.7310485 = boost
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.019712077 = queryNorm
             0.7373334 = fieldWeight in 3396, product of:
               2.828427 = tf(freq=8.0), with freq of:
                 8.0 = termFreq=8.0
               4.1709876 = idf(docFreq=1863, maxDocs=44421)
               0.0625 = fieldNorm(doc=3396)
         0.17624561 = weight(abstract_txt:natural in 3396) [ClassicSimilarity], result of:
           0.17624561 = score(doc=3396,freq=7.0), product of:
             0.21024568 = queryWeight, product of:
               2.103936 = boost
               5.0694656 = idf(docFreq=758, maxDocs=44421)
               0.019712077 = queryNorm
             0.8382841 = fieldWeight in 3396, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               5.0694656 = idf(docFreq=758, maxDocs=44421)
               0.0625 = fieldNorm(doc=3396)
         0.12783474 = weight(abstract_txt:generation in 3396) [ClassicSimilarity], result of:
           0.12783474 = score(doc=3396,freq=2.0), product of:
             0.25769353 = queryWeight, product of:
               2.329275 = boost
               5.612423 = idf(docFreq=440, maxDocs=44421)
               0.019712077 = queryNorm
             0.49607277 = fieldWeight in 3396, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.612423 = idf(docFreq=440, maxDocs=44421)
               0.0625 = fieldNorm(doc=3396)
       0.2 = coord(5/25)