Automatic inference: a probabilistic basis for natural language interpretation
Abstract: "This work proposes a probabilistic basis for natural language understanding models. It has become apparent that syntax and semantics need to be highly integrated, especially to understand constructs like nominal compounds, but inadequate modelling tools have hindered efforts to repla...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Berkeley, Calif.
Computer Science Division, (EECS)
1992
|
| Schlagworte: | |
| Zusammenfassung: | Abstract: "This work proposes a probabilistic basis for natural language understanding models. It has become apparent that syntax and semantics need to be highly integrated, especially to understand constructs like nominal compounds, but inadequate modelling tools have hindered efforts to replace the traditional parser-interpreter pipeline architecture. Qualitatively, associative frameworks like spreading activation and marker passing produce the desired interactions, but their reliance on ad hoc numeric weights make scaling them up to increasingly large domains difficult. On the other hand, statistical approaches ground numeric measures over large domains, but have thus far failed to incorporate the structural generalizations found in traditional models A major reason for this is the inability of most statistical language models to represent compositional constraints; this is related to the variable binding problem in neural networks. The proposed model attacks these issues from three directions. First, it distinguishes two fundamentally different mental processing modes: automatic and controlled inference. Automatic inference is pre-attentive, subconscious, reflexive, fairly instantaneous, associative, and highly heuristic; this delimits the domain of parallel interactive processing. Automatic inference is motivated by both resource bounds and empirical criteria, and is responsible for much if not most of parsing and semantic interpretation Second, the nature of mental representations is defined more precisely. The proposed cognitive ontology includes mental images, lexical semantics, conceptual, and lexicosyntactic modules. Automatic inference extends over all modules. The modular ontology approach accounts for a range of subtle meaning distinctions, is consistent with psycholinguistic and neural evidence, and helps reduce the complexity of the concept space. Third, probability theory provides an elegant basis for evidential interpretation, to model automatic inference in language understanding. A uniform representation for all the modules is proposed, compatible with both feature-structures and semantic networks. Probabilistic, associative extensions are then made to those frameworks |
| Beschreibung: | Zugl.: Berkeley, Calif., Univ., Diss., 1992 |
| Beschreibung: | XIII, 241 S. graph. Darst. |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV009534149 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 940415s1992 d||| m||| 00||| eng d | ||
| 035 | |a (OCoLC)26907357 | ||
| 035 | |a (DE-599)BVBBV009534149 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 050 | 0 | |a TK7885.A1 | |
| 084 | |a DAT 716d |2 stub | ||
| 084 | |a MAT 624d |2 stub | ||
| 084 | |a DAT 714d |2 stub | ||
| 084 | |a DAT 710d |2 stub | ||
| 088 | |a UCB CSD 92 692 | ||
| 100 | 1 | |a Wu, Dekai |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Automatic inference |b a probabilistic basis for natural language interpretation |c Dekai Wu |
| 246 | 1 | 3 | |a UCB CSD 92 692 |
| 264 | 1 | |a Berkeley, Calif. |b Computer Science Division, (EECS) |c 1992 | |
| 300 | |a XIII, 241 S. |b graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a Zugl.: Berkeley, Calif., Univ., Diss., 1992 | ||
| 520 | 3 | |a Abstract: "This work proposes a probabilistic basis for natural language understanding models. It has become apparent that syntax and semantics need to be highly integrated, especially to understand constructs like nominal compounds, but inadequate modelling tools have hindered efforts to replace the traditional parser-interpreter pipeline architecture. Qualitatively, associative frameworks like spreading activation and marker passing produce the desired interactions, but their reliance on ad hoc numeric weights make scaling them up to increasingly large domains difficult. On the other hand, statistical approaches ground numeric measures over large domains, but have thus far failed to incorporate the structural generalizations found in traditional models | |
| 520 | 3 | |a A major reason for this is the inability of most statistical language models to represent compositional constraints; this is related to the variable binding problem in neural networks. The proposed model attacks these issues from three directions. First, it distinguishes two fundamentally different mental processing modes: automatic and controlled inference. Automatic inference is pre-attentive, subconscious, reflexive, fairly instantaneous, associative, and highly heuristic; this delimits the domain of parallel interactive processing. Automatic inference is motivated by both resource bounds and empirical criteria, and is responsible for much if not most of parsing and semantic interpretation | |
| 520 | 3 | |a Second, the nature of mental representations is defined more precisely. The proposed cognitive ontology includes mental images, lexical semantics, conceptual, and lexicosyntactic modules. Automatic inference extends over all modules. The modular ontology approach accounts for a range of subtle meaning distinctions, is consistent with psycholinguistic and neural evidence, and helps reduce the complexity of the concept space. Third, probability theory provides an elegant basis for evidential interpretation, to model automatic inference in language understanding. A uniform representation for all the modules is proposed, compatible with both feature-structures and semantic networks. Probabilistic, associative extensions are then made to those frameworks | |
| 650 | 4 | |a Natural language processing (Computer science) | |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-006295929 | ||
Datensatz im Suchindex
| _version_ | 1804123871859703808 |
|---|---|
| any_adam_object | |
| author | Wu, Dekai |
| author_facet | Wu, Dekai |
| author_role | aut |
| author_sort | Wu, Dekai |
| author_variant | d w dw |
| building | Verbundindex |
| bvnumber | BV009534149 |
| callnumber-first | T - Technology |
| callnumber-label | TK7885 |
| callnumber-raw | TK7885.A1 |
| callnumber-search | TK7885.A1 |
| callnumber-sort | TK 47885 A1 |
| callnumber-subject | TK - Electrical and Nuclear Engineering |
| classification_tum | DAT 716d MAT 624d DAT 714d DAT 710d |
| ctrlnum | (OCoLC)26907357 (DE-599)BVBBV009534149 |
| discipline | Informatik Mathematik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03376nam a2200385 c 4500</leader><controlfield tag="001">BV009534149</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940415s1992 d||| m||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)26907357</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV009534149</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="050" ind1=" " ind2="0"><subfield code="a">TK7885.A1</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 716d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">MAT 624d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 714d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 710d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="088" ind1=" " ind2=" "><subfield code="a">UCB CSD 92 692</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wu, Dekai</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automatic inference</subfield><subfield code="b">a probabilistic basis for natural language interpretation</subfield><subfield code="c">Dekai Wu</subfield></datafield><datafield tag="246" ind1="1" ind2="3"><subfield code="a">UCB CSD 92 692</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Berkeley, Calif.</subfield><subfield code="b">Computer Science Division, (EECS)</subfield><subfield code="c">1992</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XIII, 241 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="500" ind1=" " ind2=" "><subfield code="a">Zugl.: Berkeley, Calif., Univ., Diss., 1992</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "This work proposes a probabilistic basis for natural language understanding models. It has become apparent that syntax and semantics need to be highly integrated, especially to understand constructs like nominal compounds, but inadequate modelling tools have hindered efforts to replace the traditional parser-interpreter pipeline architecture. Qualitatively, associative frameworks like spreading activation and marker passing produce the desired interactions, but their reliance on ad hoc numeric weights make scaling them up to increasingly large domains difficult. On the other hand, statistical approaches ground numeric measures over large domains, but have thus far failed to incorporate the structural generalizations found in traditional models</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">A major reason for this is the inability of most statistical language models to represent compositional constraints; this is related to the variable binding problem in neural networks. The proposed model attacks these issues from three directions. First, it distinguishes two fundamentally different mental processing modes: automatic and controlled inference. Automatic inference is pre-attentive, subconscious, reflexive, fairly instantaneous, associative, and highly heuristic; this delimits the domain of parallel interactive processing. Automatic inference is motivated by both resource bounds and empirical criteria, and is responsible for much if not most of parsing and semantic interpretation</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Second, the nature of mental representations is defined more precisely. The proposed cognitive ontology includes mental images, lexical semantics, conceptual, and lexicosyntactic modules. Automatic inference extends over all modules. The modular ontology approach accounts for a range of subtle meaning distinctions, is consistent with psycholinguistic and neural evidence, and helps reduce the complexity of the concept space. Third, probability theory provides an elegant basis for evidential interpretation, to model automatic inference in language understanding. A uniform representation for all the modules is proposed, compatible with both feature-structures and semantic networks. Probabilistic, associative extensions are then made to those frameworks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Natural language processing (Computer science)</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="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-006295929</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV009534149 |
| illustrated | Illustrated |
| indexdate | 2024-07-09T17:36:40Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-006295929 |
| oclc_num | 26907357 |
| open_access_boolean | |
| physical | XIII, 241 S. graph. Darst. |
| publishDate | 1992 |
| publishDateSearch | 1992 |
| publishDateSort | 1992 |
| publisher | Computer Science Division, (EECS) |
| record_format | marc |
| spelling | Wu, Dekai Verfasser aut Automatic inference a probabilistic basis for natural language interpretation Dekai Wu UCB CSD 92 692 Berkeley, Calif. Computer Science Division, (EECS) 1992 XIII, 241 S. graph. Darst. txt rdacontent n rdamedia nc rdacarrier Zugl.: Berkeley, Calif., Univ., Diss., 1992 Abstract: "This work proposes a probabilistic basis for natural language understanding models. It has become apparent that syntax and semantics need to be highly integrated, especially to understand constructs like nominal compounds, but inadequate modelling tools have hindered efforts to replace the traditional parser-interpreter pipeline architecture. Qualitatively, associative frameworks like spreading activation and marker passing produce the desired interactions, but their reliance on ad hoc numeric weights make scaling them up to increasingly large domains difficult. On the other hand, statistical approaches ground numeric measures over large domains, but have thus far failed to incorporate the structural generalizations found in traditional models A major reason for this is the inability of most statistical language models to represent compositional constraints; this is related to the variable binding problem in neural networks. The proposed model attacks these issues from three directions. First, it distinguishes two fundamentally different mental processing modes: automatic and controlled inference. Automatic inference is pre-attentive, subconscious, reflexive, fairly instantaneous, associative, and highly heuristic; this delimits the domain of parallel interactive processing. Automatic inference is motivated by both resource bounds and empirical criteria, and is responsible for much if not most of parsing and semantic interpretation Second, the nature of mental representations is defined more precisely. The proposed cognitive ontology includes mental images, lexical semantics, conceptual, and lexicosyntactic modules. Automatic inference extends over all modules. The modular ontology approach accounts for a range of subtle meaning distinctions, is consistent with psycholinguistic and neural evidence, and helps reduce the complexity of the concept space. Third, probability theory provides an elegant basis for evidential interpretation, to model automatic inference in language understanding. A uniform representation for all the modules is proposed, compatible with both feature-structures and semantic networks. Probabilistic, associative extensions are then made to those frameworks Natural language processing (Computer science) (DE-588)4113937-9 Hochschulschrift gnd-content |
| spellingShingle | Wu, Dekai Automatic inference a probabilistic basis for natural language interpretation Natural language processing (Computer science) |
| subject_GND | (DE-588)4113937-9 |
| title | Automatic inference a probabilistic basis for natural language interpretation |
| title_alt | UCB CSD 92 692 |
| title_auth | Automatic inference a probabilistic basis for natural language interpretation |
| title_exact_search | Automatic inference a probabilistic basis for natural language interpretation |
| title_full | Automatic inference a probabilistic basis for natural language interpretation Dekai Wu |
| title_fullStr | Automatic inference a probabilistic basis for natural language interpretation Dekai Wu |
| title_full_unstemmed | Automatic inference a probabilistic basis for natural language interpretation Dekai Wu |
| title_short | Automatic inference |
| title_sort | automatic inference a probabilistic basis for natural language interpretation |
| title_sub | a probabilistic basis for natural language interpretation |
| topic | Natural language processing (Computer science) |
| topic_facet | Natural language processing (Computer science) Hochschulschrift |
| work_keys_str_mv | AT wudekai automaticinferenceaprobabilisticbasisfornaturallanguageinterpretation AT wudekai ucbcsd92692 |