PARSEC: a connectionist learning architecture for parsing spoken language
Abstract: "A great deal of research has been done developing parsers for natural language, but adequate solutions for some of the particular problems involved in spoken language are still in their infancy. Among the unsolved problems are: difficulty in constructing task- specific grammars, lack...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Pittsburgh, Pa.
School of Computer Science, Carnegie Mellon Univ.
1991
|
| Schriftenreihe: | School of Computer Science <Pittsburgh, Pa.>: CMU-CS
1991,208 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "A great deal of research has been done developing parsers for natural language, but adequate solutions for some of the particular problems involved in spoken language are still in their infancy. Among the unsolved problems are: difficulty in constructing task- specific grammars, lack of tolerance to noisy input, and inability to effectively utilize complimentary non-symbolic information. This thesis describes PARSEC -- a system for generating connectionist parsing networks from example parses. PARSEC networks exhibit three strengths: They automatically learn to parse, and they generalize well compared to hand- coded grammars They tolerate several types of noise without any explicit noise- modeling. They can learn to use multi-modal input, e.g. a combination of intonation, syntax and semantics. The PARSEC network architecture relies on a variation of supervised back-propagation learning. The architecture differs from other connectionist approaches in that it is highly structured, both at the macroscopic level of modules, and at the microscopic level of connections. Structure is exploited to enhance system performance. Conference registration dialogs formed the primary development testbed for PARSEC. A separate simultaneous effort in speech recognition and translation for conference registration provided a useful data source for performance comparisons Presented in this thesis are the PARSEC architecture, its training algorithms, and detailed performance analyses along several dimensions that concretely demonstrate PARSEC's advantages. |
| Beschreibung: | Zugl.: Pittsburgh, Pa., Univ., Diss., 1992 |
| Beschreibung: | XVI, 164 S. graph. Darst. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV009667565 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 940623s1991 d||| m||| 00||| engod | ||
| 035 | |a (OCoLC)26274575 | ||
| 035 | |a (DE-599)BVBBV009667565 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91 | ||
| 082 | 0 | |a 510.7808 |b C28r 91-208 | |
| 084 | |a DAT 710d |2 stub | ||
| 084 | |a DAT 554d |2 stub | ||
| 084 | |a DAT 708d |2 stub | ||
| 088 | |a CMU CS 91 208 | ||
| 100 | 1 | |a Jain, Ajay N. |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a PARSEC |b a connectionist learning architecture for parsing spoken language |c Ajay N. Jain |
| 246 | 1 | 3 | |a CMU CS 91 208 |
| 264 | 1 | |a Pittsburgh, Pa. |b School of Computer Science, Carnegie Mellon Univ. |c 1991 | |
| 300 | |a XVI, 164 S. |b graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a School of Computer Science <Pittsburgh, Pa.>: CMU-CS |v 1991,208 | |
| 500 | |a Zugl.: Pittsburgh, Pa., Univ., Diss., 1992 | ||
| 520 | 3 | |a Abstract: "A great deal of research has been done developing parsers for natural language, but adequate solutions for some of the particular problems involved in spoken language are still in their infancy. Among the unsolved problems are: difficulty in constructing task- specific grammars, lack of tolerance to noisy input, and inability to effectively utilize complimentary non-symbolic information. This thesis describes PARSEC -- a system for generating connectionist parsing networks from example parses. PARSEC networks exhibit three strengths: They automatically learn to parse, and they generalize well compared to hand- coded grammars | |
| 520 | 3 | |a They tolerate several types of noise without any explicit noise- modeling. They can learn to use multi-modal input, e.g. a combination of intonation, syntax and semantics. The PARSEC network architecture relies on a variation of supervised back-propagation learning. The architecture differs from other connectionist approaches in that it is highly structured, both at the macroscopic level of modules, and at the microscopic level of connections. Structure is exploited to enhance system performance. Conference registration dialogs formed the primary development testbed for PARSEC. A separate simultaneous effort in speech recognition and translation for conference registration provided a useful data source for performance comparisons | |
| 520 | 3 | |a Presented in this thesis are the PARSEC architecture, its training algorithms, and detailed performance analyses along several dimensions that concretely demonstrate PARSEC's advantages. | |
| 650 | 4 | |a Natural language processing (Computer science) | |
| 650 | 4 | |a Neural networks (Computer science) | |
| 650 | 4 | |a Parsing (Computer grammar) | |
| 650 | 0 | 7 | |a Natürliche Sprache |0 (DE-588)4041354-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Parser |0 (DE-588)4125056-4 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Natürliche Sprache |0 (DE-588)4041354-8 |D s |
| 689 | 0 | 1 | |a Parser |0 (DE-588)4125056-4 |D s |
| 689 | 0 | 2 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | |5 DE-604 | |
| 830 | 0 | |a School of Computer Science <Pittsburgh, Pa.>: CMU-CS |v 1991,208 |w (DE-604)BV006187264 |9 1991,208 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-006393335 | ||
Datensatz im Suchindex
| _version_ | 1804124012317507584 |
|---|---|
| any_adam_object | |
| author | Jain, Ajay N. |
| author_facet | Jain, Ajay N. |
| author_role | aut |
| author_sort | Jain, Ajay N. |
| author_variant | a n j an anj |
| building | Verbundindex |
| bvnumber | BV009667565 |
| classification_tum | DAT 710d DAT 554d DAT 708d |
| ctrlnum | (OCoLC)26274575 (DE-599)BVBBV009667565 |
| 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 | Informatik Mathematik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03401nam a2200517 cb4500</leader><controlfield tag="001">BV009667565</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940623s1991 d||| m||| 00||| engod</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)26274575</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV009667565</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-91</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">510.7808</subfield><subfield code="b">C28r 91-208</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 710d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 554d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 708d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="088" ind1=" " ind2=" "><subfield code="a">CMU CS 91 208</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jain, Ajay N.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">PARSEC</subfield><subfield code="b">a connectionist learning architecture for parsing spoken language</subfield><subfield code="c">Ajay N. Jain</subfield></datafield><datafield tag="246" ind1="1" ind2="3"><subfield code="a">CMU CS 91 208</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Pittsburgh, Pa.</subfield><subfield code="b">School of Computer Science, Carnegie Mellon Univ.</subfield><subfield code="c">1991</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XVI, 164 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="1" ind2=" "><subfield code="a">School of Computer Science <Pittsburgh, Pa.>: CMU-CS</subfield><subfield code="v">1991,208</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Zugl.: Pittsburgh, Pa., Univ., Diss., 1992</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "A great deal of research has been done developing parsers for natural language, but adequate solutions for some of the particular problems involved in spoken language are still in their infancy. Among the unsolved problems are: difficulty in constructing task- specific grammars, lack of tolerance to noisy input, and inability to effectively utilize complimentary non-symbolic information. This thesis describes PARSEC -- a system for generating connectionist parsing networks from example parses. PARSEC networks exhibit three strengths: They automatically learn to parse, and they generalize well compared to hand- coded grammars</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">They tolerate several types of noise without any explicit noise- modeling. They can learn to use multi-modal input, e.g. a combination of intonation, syntax and semantics. The PARSEC network architecture relies on a variation of supervised back-propagation learning. The architecture differs from other connectionist approaches in that it is highly structured, both at the macroscopic level of modules, and at the microscopic level of connections. Structure is exploited to enhance system performance. Conference registration dialogs formed the primary development testbed for PARSEC. A separate simultaneous effort in speech recognition and translation for conference registration provided a useful data source for performance comparisons</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Presented in this thesis are the PARSEC architecture, its training algorithms, and detailed performance analyses along several dimensions that concretely demonstrate PARSEC's advantages.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Natural language processing (Computer science)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Neural networks (Computer science)</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">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="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">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</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">Natürliche Sprache</subfield><subfield code="0">(DE-588)4041354-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><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="2"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">School of Computer Science <Pittsburgh, Pa.>: CMU-CS</subfield><subfield code="v">1991,208</subfield><subfield code="w">(DE-604)BV006187264</subfield><subfield code="9">1991,208</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-006393335</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV009667565 |
| illustrated | Illustrated |
| indexdate | 2024-07-09T17:38:54Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-006393335 |
| oclc_num | 26274575 |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM |
| owner_facet | DE-91 DE-BY-TUM |
| physical | XVI, 164 S. graph. Darst. |
| publishDate | 1991 |
| publishDateSearch | 1991 |
| publishDateSort | 1991 |
| publisher | School of Computer Science, Carnegie Mellon Univ. |
| record_format | marc |
| series | School of Computer Science <Pittsburgh, Pa.>: CMU-CS |
| series2 | School of Computer Science <Pittsburgh, Pa.>: CMU-CS |
| spelling | Jain, Ajay N. Verfasser aut PARSEC a connectionist learning architecture for parsing spoken language Ajay N. Jain CMU CS 91 208 Pittsburgh, Pa. School of Computer Science, Carnegie Mellon Univ. 1991 XVI, 164 S. graph. Darst. txt rdacontent n rdamedia nc rdacarrier School of Computer Science <Pittsburgh, Pa.>: CMU-CS 1991,208 Zugl.: Pittsburgh, Pa., Univ., Diss., 1992 Abstract: "A great deal of research has been done developing parsers for natural language, but adequate solutions for some of the particular problems involved in spoken language are still in their infancy. Among the unsolved problems are: difficulty in constructing task- specific grammars, lack of tolerance to noisy input, and inability to effectively utilize complimentary non-symbolic information. This thesis describes PARSEC -- a system for generating connectionist parsing networks from example parses. PARSEC networks exhibit three strengths: They automatically learn to parse, and they generalize well compared to hand- coded grammars They tolerate several types of noise without any explicit noise- modeling. They can learn to use multi-modal input, e.g. a combination of intonation, syntax and semantics. The PARSEC network architecture relies on a variation of supervised back-propagation learning. The architecture differs from other connectionist approaches in that it is highly structured, both at the macroscopic level of modules, and at the microscopic level of connections. Structure is exploited to enhance system performance. Conference registration dialogs formed the primary development testbed for PARSEC. A separate simultaneous effort in speech recognition and translation for conference registration provided a useful data source for performance comparisons Presented in this thesis are the PARSEC architecture, its training algorithms, and detailed performance analyses along several dimensions that concretely demonstrate PARSEC's advantages. Natural language processing (Computer science) Neural networks (Computer science) Parsing (Computer grammar) Natürliche Sprache (DE-588)4041354-8 gnd rswk-swf Parser (DE-588)4125056-4 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Natürliche Sprache (DE-588)4041354-8 s Parser (DE-588)4125056-4 s Maschinelles Lernen (DE-588)4193754-5 s DE-604 School of Computer Science <Pittsburgh, Pa.>: CMU-CS 1991,208 (DE-604)BV006187264 1991,208 |
| spellingShingle | Jain, Ajay N. PARSEC a connectionist learning architecture for parsing spoken language School of Computer Science <Pittsburgh, Pa.>: CMU-CS Natural language processing (Computer science) Neural networks (Computer science) Parsing (Computer grammar) Natürliche Sprache (DE-588)4041354-8 gnd Parser (DE-588)4125056-4 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)4041354-8 (DE-588)4125056-4 (DE-588)4193754-5 (DE-588)4113937-9 |
| title | PARSEC a connectionist learning architecture for parsing spoken language |
| title_alt | CMU CS 91 208 |
| title_auth | PARSEC a connectionist learning architecture for parsing spoken language |
| title_exact_search | PARSEC a connectionist learning architecture for parsing spoken language |
| title_full | PARSEC a connectionist learning architecture for parsing spoken language Ajay N. Jain |
| title_fullStr | PARSEC a connectionist learning architecture for parsing spoken language Ajay N. Jain |
| title_full_unstemmed | PARSEC a connectionist learning architecture for parsing spoken language Ajay N. Jain |
| title_short | PARSEC |
| title_sort | parsec a connectionist learning architecture for parsing spoken language |
| title_sub | a connectionist learning architecture for parsing spoken language |
| topic | Natural language processing (Computer science) Neural networks (Computer science) Parsing (Computer grammar) Natürliche Sprache (DE-588)4041354-8 gnd Parser (DE-588)4125056-4 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | Natural language processing (Computer science) Neural networks (Computer science) Parsing (Computer grammar) Natürliche Sprache Parser Maschinelles Lernen Hochschulschrift |
| volume_link | (DE-604)BV006187264 |
| work_keys_str_mv | AT jainajayn parsecaconnectionistlearningarchitectureforparsingspokenlanguage AT jainajayn cmucs91208 |