User modelling in text generation:
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
London u.a.
Pinter
1993
|
| Edition: | 1. publ. |
| Series: | Communication in artificial intelligence series
|
| Subjects: | |
| Links: | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=005232862&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| Physical Description: | XX, 205 S graph. Darst. |
| ISBN: | 0861878094 |
Staff View
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV007916481 | ||
| 003 | DE-604 | ||
| 005 | 20150212 | ||
| 007 | t| | ||
| 008 | 930701s1993 xx d||| |||| 00||| eng d | ||
| 020 | |a 0861878094 |9 0-86187-809-4 | ||
| 035 | |a (OCoLC)27146854 | ||
| 035 | |a (DE-599)BVBBV007916481 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-739 | ||
| 050 | 0 | |a QA76.9.T48 | |
| 082 | 0 | |a 006.3/5 |2 20 | |
| 084 | |a ST 306 |0 (DE-625)143654: |2 rvk | ||
| 100 | 1 | |a Paris, Cécile L. |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a User modelling in text generation |c Cécile L. Paris |
| 250 | |a 1. publ. | ||
| 264 | 1 | |a London u.a. |b Pinter |c 1993 | |
| 300 | |a XX, 205 S |b graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 0 | |a Communication in artificial intelligence series | |
| 650 | 7 | |a Kennissystemen |2 gtt | |
| 650 | 7 | |a Tekstanalyse |2 gtt | |
| 650 | 4 | |a Text processing (Computer science) | |
| 650 | 0 | 7 | |a Textproduktion |0 (DE-588)4184945-0 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Benutzermodell |0 (DE-588)4343329-7 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Dialogsystem |0 (DE-588)4131632-0 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Dialogsystem |0 (DE-588)4131632-0 |D s |
| 689 | 0 | 1 | |a Benutzermodell |0 (DE-588)4343329-7 |D s |
| 689 | 0 | 2 | |a Textproduktion |0 (DE-588)4184945-0 |D s |
| 689 | 0 | |5 DE-604 | |
| 856 | 4 | 2 | |m HEBIS Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=005232862&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-005232862 | |
Record in the Search Index
| _version_ | 1819311936732397568 |
|---|---|
| adam_text | USER MODELLING
IN TEXT
GENERATION
Cecile L Paris
Pinter Publishers, London and New York
distributed in the United States and Canada
by St Martin s Press, New York
Contents
Contents vii
List of Figures xi
Foreword xvii
Preface xix
1 Introduction 1
1 1 Natural Language Generation 1
111 Language variation according to the situation 3
1 2 User modelling in generation 5
1 3 Research method and major results 6
1 4 The domain 8
1 5 System overview 10
1 6 Examples from TAILOR 12
1 7 Limitations 12
18A guide to remaining chapters 16
2 The user model in TAILOR 17
2 1 Contents and use of a user model 17
2 2 Identifying what needs to be in the user model 19
2 3 Determining the level of expertise 21
231 Usertype 22
vii
232 Obtaining information from a dialogue 22
233 Employing Inference Rules 24
234 Asking the user questions and using the previous discourse 25
2 4 Conclusions 25
3 The text analysis 27
3 1 Analyzing text 28
3 2 The texts analyzed 30
321 The textual analysis 31
322 Analyses of entries from adult encyclopedias and the car man-
ual for experts 33
323 Texts from junior encyclopedias, high school textbooks, and
the car manual for novices 37
324 Need for directives 44
325 Summary of the textual analyses 49
326 Plausibility of this hypothesis 51
3 3 Combining the strategies for users with
intermediate levels of expertise 52
3 4 Summary 52
4 The discourse strategies used in TAILOR 55
4 1 Constituency Schema 55
4 2 Process Trace 57
4 3 Requirements of the knowledge base 59
4 4 The process trace: a procedural strategy 59
441 Identifying the main path and different kinds of links 61
442 The main path 62
443 Deciding among several side links or side chains 65
4 5 Strategy representation 75
4 6 Open problems 86
4 7 Summary 86
viii
5 Combining the strategies to describe devices for a whole range of users 87
5 1 The user model contains explicit
parameters 88
5 2 Generating a description based on the user model 89
521 Choosing a strategy for the overall structure
of the description 90
522 Combining the strategies 92
5 3 Examples of texts combining the two
strategies 95
5 4 Combining strategies yields a greater
variety of texts 102
5 5 Conclusions 107
6 TAILOR system implementation 109
6 1 System overview 109
6 2 The knowledge base and its representation 113
621 The generalization hierarchies 119
622 Limitations of the knowledge base 122
6 3 The user model 122
6 4 The textual component 124
641 Initially selecting a strategy 124
642 Finding the main path 126
643 Implementation of the Strategies 130
644 Stepping through the Constituency Schema 133
645 The ATN corresponding to the Process Trace 136
646 Choosinganarc 140
6 5 The Interface 141
6 6 The surface generator 147
661 The functional grammar and the unification process 149
6 7 Issues pertaining to domain dependency 152
6 8 TAILOR as a question answering system 152
ix
7 Related Work 153
7 1 Related work in user modelling
and generation 153
711 Using stereotypes 154
712 Modelling and exploiting the user s
domain knowledge 155
713 Using knowledge about the user s plans
and goals to generate responses 157
714 Using reasoning about mutual beliefs to plan an
utterance 158
715 Dealing with misconceptions about the domain 159
716 Exploiting the speaker s and hearer s pragmatic goals
in generation 159
7 2 Related work in psychology and reading
comprehension 160
7 3 Summary 161
8 Beyond TAILOR 163
8 1 Main points of this work 163
8 2 Feasibility and extensibility of this approach 164
8 3 Current directions 165
831 Employing the generator presented here in another domain 166
832 Building a system with dialogue capabilities 166
833 Tailoring the phrasing of a text 169
834 Bringing the whole generation process under
register control 172
835 Providing a system with adaptive capabilities 173
Appendix A 175
Appendix B 179
Bibliography 183
Index 201
List of Figures
1 1 Employing different terms in talking to different people 4
1 2 Dictionary entries for doctors and non-doctors 4
1 3 Example of a patent abstract 8
1 4 RESEARCHER and the TAILOR System 9
1 5 Two descriptions of the air filtering mechanism of a disc-drive 10
1 6 The TAILOR System 11
1 7 Short description of a telephone 13
1 8 Description of a telephone 13
1 9 Description of a receiver 14
1 10 Description of a vacuum-tube 14
1 11 Description of a pulse-telephone 15
2 1 Description of a telegraph from Collier Encyclopedia (1962) 20
3 1 Rhetorical predicates used in this analysis 32
3 2 Two descriptions of the filament lamps 33
3 3 The constituency schema 34
3 4 Description of a telephone from an adult encyclopedia 35
3 5 Description of transformers from an adult encyclopedia 37
3 6 Description of a telephone from a junior encyclopedia 39
3 7 Organization of the description of the telephone from a Junior Ency-
clopedia 40
3 8 Organization of the description of the telephone from a Junior Ency-
clopedia - Cont d 41
xi
3 9 Description of transformers from a junior encyclopedia 41
3 10 The process trace algorithm 43
3 11 Including a subpart s process explanation while explaining the object s
function 44
3 12 Including a subpart s process explanation after explaining the object s
function 45
3 13 Decomposition of the telephone example from the junior encyclopedia
text into rhetorical predicates 46
3 14 Decomposition of part of the telephone example from the junior ency-
clopedia text into coherence relations 48
3 15 Decomposition of the telephone example from the junior encyclopedia
text into nucleus/satellite schemata 50
3 16 Text from the Encyc/opedia of Chemical Technology 53
4 1 The Constituency Schema as defined by McKeown (1985) 56
4 2 The modified Constituency Schema 58
4 3 The process explanation follows the main path from the start state to
the goal state 61
4 4 The process explanation follows the main path from the goal state to
the start state 61
4 5 Subset of the knowledge base for the loudspeaker 64
4 6 An analogical side link can produce a clearer explanation 66
4 7 The side chain is related to the main path 67
4 8 Portion of the knowledge base for the dialing mechanism 69
4 9 The side chain is related to the main path: an example 70
4 10 Including a side chain whose one-before-last event is an enabling con-
dition for an event on the main path 71
4 11 There is a single side link 71
4 12 Including a causal side link does not render the explanation clearer 72
4 13 Including an enabling condition 72
4 14 There are many short links 73
4 15 There is a long side chain which is not related to the main path 73
4 16 The side chain is long and not related to the main path 74
4 17 Substeps arising because of subparts 76
xn
4 18 The Constituency Schema 77
4 19 Stepping through the Constituency Schema 79
4 20 The Process Trace 80
4 21 Process Trace for the loudspeaker 81
4 22 Process trace for the loudspeaker (Cont d) 82
4 23 English output for the trace of Figures 4 21 and 4 22 83
4 24 Process trace for the dialing mechanism 84
4 25 Process trace for the dialing mechanism - Cont d 85
4 26 Example of a feedback loop 85
5 1 Representing the user model explicitly 89
5 2 The Constituency Schema strategy and its decision points 94
5 3 The Process Trace strategy and its decision points 94
5 4 Simplified portion of the knowledge base for the telephone 96
5 5 Combining the strategies: using the constituency schema as the overall
structure of the text and switching to the process trace for one part 97
5 6 Starting with the constituency schema and switching to the process
trace for the new part 98
5 7 Switching to the process trace for the superordinate and two parts 100
5 8 Starting with the process trace and switching to the constituency
schema for one part 101
5 9 Changing the parameter that determines the overall structure of a de-
scription r 103
5 10 Description of the telephone Most is set to half of the functionally
important parts 104
5 11 Combining the strategies 106
5 12 Combining the strategies, using an entry point other than the beginning 106
6 1 RESEARCHER and the TAILOR System 110
6 2 The TAILOR System 112
6 3 The knowledge base used in TAILOR; parts hierarchies 114
6 4 The knowledge base used in TAILOR; generalization hierarchies 115
6 5 An object frame 116
xiii
6 6 Primitives used to describe static physical relations (Wasserman, 1985) 117
6 7 Example of a relation (Wasserman, 1985) 117
6 8 Representation of a microphone s function 118
6 9 Categories of dynamic relations 118
6 10 Representation of events and links between events 120
6 11 Representation of a microphone 120
6 12 Several generalization trees 121
6 13 A characterization of the User Model in TAILOR 123
6 14 More examples of user models in TAILOR 123
6 15 The decision algorithm 125
6 16 Importance scale used to find the main path 125
6 17 Links between events 127
6 18 Finding the main path for the loudspeaker 128
6 19 Subset of the knowledge base for the loudspeaker 129
6 20 Examples of propositions obtained from traversing an arc of the con-
stituency schema 132
6 21 Example of a proposition obtained from traversing an arc of the process
trace 132
6 22 Constituency Schema and its ATN 134
6 23 Including more information than strictly required by the predicates 136
6 24 Predicate semantics 137
6 25 Description using the Constituency Schema 138
6 26 ATN corresponding to the Process Trace 139
6 27 Description using the Process Trace 140
6 28 When to include a relation 142
6 29 Interface input and output 142
6 30 Translation of the various propositions 144
6 31 Constructing a sentence from the identification predicate 145
6 32 Constructing a sentence from the attributive predicate 146
6 33 Combining simple sentences into a complex sentence 148
6 34 Using the pronoun this in a process explanation 149
xiv
6 35 A simple subgrammar for noun phrases 150
6 36 Embedded clauses and their use in TAILOR 151
8 1 Examples of variations generated from the same propositional input
for different user types 171
8 2 Architecture for controlling phrasing 172
xv
|
| any_adam_object | 1 |
| author | Paris, Cécile L. |
| author_facet | Paris, Cécile L. |
| author_role | aut |
| author_sort | Paris, Cécile L. |
| author_variant | c l p cl clp |
| building | Verbundindex |
| bvnumber | BV007916481 |
| callnumber-first | Q - Science |
| callnumber-label | QA76 |
| callnumber-raw | QA76.9.T48 |
| callnumber-search | QA76.9.T48 |
| callnumber-sort | QA 276.9 T48 |
| callnumber-subject | QA - Mathematics |
| classification_rvk | ST 306 |
| ctrlnum | (OCoLC)27146854 (DE-599)BVBBV007916481 |
| dewey-full | 006.3/5 |
| dewey-hundreds | 000 - Computer science, information, general works |
| dewey-ones | 006 - Special computer methods |
| dewey-raw | 006.3/5 |
| dewey-search | 006.3/5 |
| dewey-sort | 16.3 15 |
| dewey-tens | 000 - Computer science, information, general works |
| discipline | Informatik |
| edition | 1. publ. |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01633nam a2200445 c 4500</leader><controlfield tag="001">BV007916481</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20150212 </controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">930701s1993 xx d||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">0861878094</subfield><subfield code="9">0-86187-809-4</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)27146854</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV007916481</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-739</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QA76.9.T48</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">006.3/5</subfield><subfield code="2">20</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 306</subfield><subfield code="0">(DE-625)143654:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Paris, Cécile L.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">User modelling in text generation</subfield><subfield code="c">Cécile L. Paris</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">1. publ.</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">London u.a.</subfield><subfield code="b">Pinter</subfield><subfield code="c">1993</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XX, 205 S</subfield><subfield code="b">graph. Darst.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="0" ind2=" "><subfield code="a">Communication in artificial intelligence series</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Kennissystemen</subfield><subfield code="2">gtt</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Tekstanalyse</subfield><subfield code="2">gtt</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Text processing (Computer science)</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Textproduktion</subfield><subfield code="0">(DE-588)4184945-0</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Benutzermodell</subfield><subfield code="0">(DE-588)4343329-7</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Dialogsystem</subfield><subfield code="0">(DE-588)4131632-0</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Dialogsystem</subfield><subfield code="0">(DE-588)4131632-0</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Benutzermodell</subfield><subfield code="0">(DE-588)4343329-7</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Textproduktion</subfield><subfield code="0">(DE-588)4184945-0</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">HEBIS Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=005232862&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-005232862</subfield></datafield></record></collection> |
| id | DE-604.BV007916481 |
| illustrated | Illustrated |
| indexdate | 2024-12-20T09:14:10Z |
| institution | BVB |
| isbn | 0861878094 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-005232862 |
| oclc_num | 27146854 |
| open_access_boolean | |
| owner | DE-739 |
| owner_facet | DE-739 |
| physical | XX, 205 S graph. Darst. |
| publishDate | 1993 |
| publishDateSearch | 1993 |
| publishDateSort | 1993 |
| publisher | Pinter |
| record_format | marc |
| series2 | Communication in artificial intelligence series |
| spellingShingle | Paris, Cécile L. User modelling in text generation Kennissystemen gtt Tekstanalyse gtt Text processing (Computer science) Textproduktion (DE-588)4184945-0 gnd Benutzermodell (DE-588)4343329-7 gnd Dialogsystem (DE-588)4131632-0 gnd |
| subject_GND | (DE-588)4184945-0 (DE-588)4343329-7 (DE-588)4131632-0 |
| title | User modelling in text generation |
| title_auth | User modelling in text generation |
| title_exact_search | User modelling in text generation |
| title_full | User modelling in text generation Cécile L. Paris |
| title_fullStr | User modelling in text generation Cécile L. Paris |
| title_full_unstemmed | User modelling in text generation Cécile L. Paris |
| title_short | User modelling in text generation |
| title_sort | user modelling in text generation |
| topic | Kennissystemen gtt Tekstanalyse gtt Text processing (Computer science) Textproduktion (DE-588)4184945-0 gnd Benutzermodell (DE-588)4343329-7 gnd Dialogsystem (DE-588)4131632-0 gnd |
| topic_facet | Kennissystemen Tekstanalyse Text processing (Computer science) Textproduktion Benutzermodell Dialogsystem |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=005232862&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT pariscecilel usermodellingintextgeneration |