Adaptive parsing: self-extending natural language interfaces
The research presented advances a new, alternative approach to interface design based on a model of language acquisition through automatic adaptation. The model depends on a key observation about frequent user behavior: although individual users differ significantly in their preferred linguistic exp...
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Buch |
Sprache: | English |
Veröffentlicht: |
Pittsburgh, Pa.
1989
|
Schriftenreihe: | Carnegie-Mellon University <Pittburgh, Pa.> / Computer Science Department: CMU-CS
89,191 |
Schlagworte: | |
Zusammenfassung: | The research presented advances a new, alternative approach to interface design based on a model of language acquisition through automatic adaptation. The model depends on a key observation about frequent user behavior: although individual users differ significantly in their preferred linguistic expression, each frequent user is quite consistent in her usage over time. This self-bounded aspect of user behavior is demonstrated empirically in an initial set of experiments using a simulated system and a later set of experiments using an implementation of the model. The regularity in each frequent user's linguistic behavior is exploited in the design of a general mechanism to learn idiosyncratic grammars. The mechanism explains perceived errors in the input utterance as deviations with respect to the system's current grammar The explanation is then transformed into new grammatical components that are capable of recognizing the general structure of the deviation in future interactions. Thus, in contrast to most existing interfaces, the adaptive interface is self-extending and allows the user to employ her own natural language for accomplishing tasks. The usefulness and robustness of adaptation is demonstrated by the implementation of the model in a working interface. The interface has been evaluated both on the data from the original simulations and in on-line interactions with real users. The results of the evaluation clearly show adaptation's effectiveness; the implementation was able to capture both the regularity and the idiosyncracy in the natural grammars of eight users. |
Beschreibung: | Zugl.: Pittburgh, Univ., Diss. |
Beschreibung: | XI, 301 S. |
Internformat
MARC
LEADER | 00000nam a2200000 cb4500 | ||
---|---|---|---|
001 | BV008949104 | ||
003 | DE-604 | ||
005 | 00000000000000.0 | ||
007 | t | ||
008 | 940206s1989 m||| 00||| eng d | ||
035 | |a (OCoLC)21024535 | ||
035 | |a (DE-599)BVBBV008949104 | ||
040 | |a DE-604 |b ger |e rakddb | ||
041 | 0 | |a eng | |
049 | |a DE-29T | ||
082 | 0 | |a 510.7808 |b C28r 89-191 | |
100 | 1 | |a Lehman, Jill F. |e Verfasser |4 aut | |
245 | 1 | 0 | |a Adaptive parsing |b self-extending natural language interfaces |c Jill Fain Lehman |
264 | 1 | |a Pittsburgh, Pa. |c 1989 | |
300 | |a XI, 301 S. | ||
336 | |b txt |2 rdacontent | ||
337 | |b n |2 rdamedia | ||
338 | |b nc |2 rdacarrier | ||
490 | 1 | |a Carnegie-Mellon University <Pittburgh, Pa.> / Computer Science Department: CMU-CS |v 89,191 | |
500 | |a Zugl.: Pittburgh, Univ., Diss. | ||
520 | 3 | |a The research presented advances a new, alternative approach to interface design based on a model of language acquisition through automatic adaptation. The model depends on a key observation about frequent user behavior: although individual users differ significantly in their preferred linguistic expression, each frequent user is quite consistent in her usage over time. This self-bounded aspect of user behavior is demonstrated empirically in an initial set of experiments using a simulated system and a later set of experiments using an implementation of the model. The regularity in each frequent user's linguistic behavior is exploited in the design of a general mechanism to learn idiosyncratic grammars. The mechanism explains perceived errors in the input utterance as deviations with respect to the system's current grammar | |
520 | 3 | |a The explanation is then transformed into new grammatical components that are capable of recognizing the general structure of the deviation in future interactions. Thus, in contrast to most existing interfaces, the adaptive interface is self-extending and allows the user to employ her own natural language for accomplishing tasks. The usefulness and robustness of adaptation is demonstrated by the implementation of the model in a working interface. The interface has been evaluated both on the data from the original simulations and in on-line interactions with real users. The results of the evaluation clearly show adaptation's effectiveness; the implementation was able to capture both the regularity and the idiosyncracy in the natural grammars of eight users. | |
650 | 4 | |a Natural language processing | |
650 | 4 | |a Parsing (Computer grammar) | |
650 | 0 | 7 | |a Parser |0 (DE-588)4125056-4 |2 gnd |9 rswk-swf |
650 | 0 | 7 | |a Schnittstelle |0 (DE-588)4053059-0 |2 gnd |9 rswk-swf |
650 | 0 | 7 | |a Syntaktische Analyse |0 (DE-588)4058778-2 |2 gnd |9 rswk-swf |
650 | 0 | 7 | |a Natürliche Sprache |0 (DE-588)4041354-8 |2 gnd |9 rswk-swf |
655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
689 | 0 | 0 | |a Parser |0 (DE-588)4125056-4 |D s |
689 | 0 | 1 | |a Schnittstelle |0 (DE-588)4053059-0 |D s |
689 | 0 | 2 | |a Natürliche Sprache |0 (DE-588)4041354-8 |D s |
689 | 0 | |5 DE-604 | |
689 | 1 | 0 | |a Natürliche Sprache |0 (DE-588)4041354-8 |D s |
689 | 1 | 1 | |a Syntaktische Analyse |0 (DE-588)4058778-2 |D s |
689 | 1 | |5 DE-604 | |
810 | 2 | |a Computer Science Department: CMU-CS |t Carnegie-Mellon University <Pittburgh, Pa.> |v 89,191 |w (DE-604)BV006187264 |9 89,191 | |
999 | |a oai:aleph.bib-bvb.de:BVB01-005904816 |
Datensatz im Suchindex
_version_ | 1804123282161532928 |
---|---|
any_adam_object | |
author | Lehman, Jill F. |
author_facet | Lehman, Jill F. |
author_role | aut |
author_sort | Lehman, Jill F. |
author_variant | j f l jf jfl |
building | Verbundindex |
bvnumber | BV008949104 |
ctrlnum | (OCoLC)21024535 (DE-599)BVBBV008949104 |
dewey-full | 510.7808 |
dewey-hundreds | 500 - Natural sciences and mathematics |
dewey-ones | 510 - Mathematics |
dewey-raw | 510.7808 |
dewey-search | 510.7808 |
dewey-sort | 3510.7808 |
dewey-tens | 510 - Mathematics |
discipline | Mathematik |
format | Book |
fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03355nam a2200481 cb4500</leader><controlfield tag="001">BV008949104</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940206s1989 m||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)21024535</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV008949104</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-29T</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">510.7808</subfield><subfield code="b">C28r 89-191</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lehman, Jill F.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Adaptive parsing</subfield><subfield code="b">self-extending natural language interfaces</subfield><subfield code="c">Jill Fain Lehman</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Pittsburgh, Pa.</subfield><subfield code="c">1989</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XI, 301 S.</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="1" ind2=" "><subfield code="a">Carnegie-Mellon University <Pittburgh, Pa.> / Computer Science Department: CMU-CS</subfield><subfield code="v">89,191</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Zugl.: Pittburgh, Univ., Diss.</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The research presented advances a new, alternative approach to interface design based on a model of language acquisition through automatic adaptation. The model depends on a key observation about frequent user behavior: although individual users differ significantly in their preferred linguistic expression, each frequent user is quite consistent in her usage over time. This self-bounded aspect of user behavior is demonstrated empirically in an initial set of experiments using a simulated system and a later set of experiments using an implementation of the model. The regularity in each frequent user's linguistic behavior is exploited in the design of a general mechanism to learn idiosyncratic grammars. The mechanism explains perceived errors in the input utterance as deviations with respect to the system's current grammar</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The explanation is then transformed into new grammatical components that are capable of recognizing the general structure of the deviation in future interactions. Thus, in contrast to most existing interfaces, the adaptive interface is self-extending and allows the user to employ her own natural language for accomplishing tasks. The usefulness and robustness of adaptation is demonstrated by the implementation of the model in a working interface. The interface has been evaluated both on the data from the original simulations and in on-line interactions with real users. The results of the evaluation clearly show adaptation's effectiveness; the implementation was able to capture both the regularity and the idiosyncracy in the natural grammars of eight users.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Natural language processing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Parsing (Computer grammar)</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Parser</subfield><subfield code="0">(DE-588)4125056-4</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Schnittstelle</subfield><subfield code="0">(DE-588)4053059-0</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Syntaktische Analyse</subfield><subfield code="0">(DE-588)4058778-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Natürliche Sprache</subfield><subfield code="0">(DE-588)4041354-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Parser</subfield><subfield code="0">(DE-588)4125056-4</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Schnittstelle</subfield><subfield code="0">(DE-588)4053059-0</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Natürliche Sprache</subfield><subfield code="0">(DE-588)4041354-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="689" ind1="1" ind2="0"><subfield code="a">Natürliche Sprache</subfield><subfield code="0">(DE-588)4041354-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2="1"><subfield code="a">Syntaktische Analyse</subfield><subfield code="0">(DE-588)4058778-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Computer Science Department: CMU-CS</subfield><subfield code="t">Carnegie-Mellon University <Pittburgh, Pa.></subfield><subfield code="v">89,191</subfield><subfield code="w">(DE-604)BV006187264</subfield><subfield code="9">89,191</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-005904816</subfield></datafield></record></collection> |
genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
genre_facet | Hochschulschrift |
id | DE-604.BV008949104 |
illustrated | Not Illustrated |
indexdate | 2024-07-09T17:27:17Z |
institution | BVB |
language | English |
oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-005904816 |
oclc_num | 21024535 |
open_access_boolean | |
owner | DE-29T |
owner_facet | DE-29T |
physical | XI, 301 S. |
publishDate | 1989 |
publishDateSearch | 1989 |
publishDateSort | 1989 |
record_format | marc |
series2 | Carnegie-Mellon University <Pittburgh, Pa.> / Computer Science Department: CMU-CS |
spelling | Lehman, Jill F. Verfasser aut Adaptive parsing self-extending natural language interfaces Jill Fain Lehman Pittsburgh, Pa. 1989 XI, 301 S. txt rdacontent n rdamedia nc rdacarrier Carnegie-Mellon University <Pittburgh, Pa.> / Computer Science Department: CMU-CS 89,191 Zugl.: Pittburgh, Univ., Diss. The research presented advances a new, alternative approach to interface design based on a model of language acquisition through automatic adaptation. The model depends on a key observation about frequent user behavior: although individual users differ significantly in their preferred linguistic expression, each frequent user is quite consistent in her usage over time. This self-bounded aspect of user behavior is demonstrated empirically in an initial set of experiments using a simulated system and a later set of experiments using an implementation of the model. The regularity in each frequent user's linguistic behavior is exploited in the design of a general mechanism to learn idiosyncratic grammars. The mechanism explains perceived errors in the input utterance as deviations with respect to the system's current grammar The explanation is then transformed into new grammatical components that are capable of recognizing the general structure of the deviation in future interactions. Thus, in contrast to most existing interfaces, the adaptive interface is self-extending and allows the user to employ her own natural language for accomplishing tasks. The usefulness and robustness of adaptation is demonstrated by the implementation of the model in a working interface. The interface has been evaluated both on the data from the original simulations and in on-line interactions with real users. The results of the evaluation clearly show adaptation's effectiveness; the implementation was able to capture both the regularity and the idiosyncracy in the natural grammars of eight users. Natural language processing Parsing (Computer grammar) Parser (DE-588)4125056-4 gnd rswk-swf Schnittstelle (DE-588)4053059-0 gnd rswk-swf Syntaktische Analyse (DE-588)4058778-2 gnd rswk-swf Natürliche Sprache (DE-588)4041354-8 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Parser (DE-588)4125056-4 s Schnittstelle (DE-588)4053059-0 s Natürliche Sprache (DE-588)4041354-8 s DE-604 Syntaktische Analyse (DE-588)4058778-2 s Computer Science Department: CMU-CS Carnegie-Mellon University <Pittburgh, Pa.> 89,191 (DE-604)BV006187264 89,191 |
spellingShingle | Lehman, Jill F. Adaptive parsing self-extending natural language interfaces Natural language processing Parsing (Computer grammar) Parser (DE-588)4125056-4 gnd Schnittstelle (DE-588)4053059-0 gnd Syntaktische Analyse (DE-588)4058778-2 gnd Natürliche Sprache (DE-588)4041354-8 gnd |
subject_GND | (DE-588)4125056-4 (DE-588)4053059-0 (DE-588)4058778-2 (DE-588)4041354-8 (DE-588)4113937-9 |
title | Adaptive parsing self-extending natural language interfaces |
title_auth | Adaptive parsing self-extending natural language interfaces |
title_exact_search | Adaptive parsing self-extending natural language interfaces |
title_full | Adaptive parsing self-extending natural language interfaces Jill Fain Lehman |
title_fullStr | Adaptive parsing self-extending natural language interfaces Jill Fain Lehman |
title_full_unstemmed | Adaptive parsing self-extending natural language interfaces Jill Fain Lehman |
title_short | Adaptive parsing |
title_sort | adaptive parsing self extending natural language interfaces |
title_sub | self-extending natural language interfaces |
topic | Natural language processing Parsing (Computer grammar) Parser (DE-588)4125056-4 gnd Schnittstelle (DE-588)4053059-0 gnd Syntaktische Analyse (DE-588)4058778-2 gnd Natürliche Sprache (DE-588)4041354-8 gnd |
topic_facet | Natural language processing Parsing (Computer grammar) Parser Schnittstelle Syntaktische Analyse Natürliche Sprache Hochschulschrift |
volume_link | (DE-604)BV006187264 |
work_keys_str_mv | AT lehmanjillf adaptiveparsingselfextendingnaturallanguageinterfaces |