Networks that Learn about Phonological Feature Persistence View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1992

AUTHORS

Michael Gasser , Chan-Do Lee

ABSTRACT

Natural language phonology presents a challenge to connectionists because it is an example of apparently symbolic, rule-governed behavior. This paper describes two experiments investigating the power of simple recurrent networks (SRNs) to acquire phonological regularities that can be described in terms of the persistence of particular features. The first experiment demonstrates the ability of an SRN to learn simple harmony constraints within morphemes; that is, restrictions on the co-occurrence of particular types of segments. The second experiment shows that an SRN is capable of learning patterns of feature persistence across morpheme boundaries, in this case, the alterations occurring in the regular plural forms of English nouns. This behavior is usually characterized in terms of a derivation from a more to a less abstract level; here it takes the form of the more psychologically plausible processes of the production of a sequence of segments given a meaning or the generation of a meaning given a sequence of segments. This is accomplished by having both segmental and semantic inputs and outputs in the network. Trained on the task of auto-associating the current segment and meaning and predicting the next segment, the network learns to produce the appropriate plural suffix on nouns it has seen in only the singular and to recognize novel plural forms as plural. More... »

PAGES

349-362

Book

TITLE

Connectionist Natural Language Processing

ISBN

978-94-010-5160-6
978-94-011-2624-3

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-94-011-2624-3_16

DOI

http://dx.doi.org/10.1007/978-94-011-2624-3_16

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1018609888


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2004", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Linguistics", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/20", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Language, Communication and Culture", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Indiana University Bloomington", 
          "id": "https://www.grid.ac/institutes/grid.411377.7", 
          "name": [
            "Computer Science Department, Indiana University, 47405, Bloomington, IN, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gasser", 
        "givenName": "Michael", 
        "id": "sg:person.01212513340.93", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01212513340.93"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Indiana University Bloomington", 
          "id": "https://www.grid.ac/institutes/grid.411377.7", 
          "name": [
            "Computer Science Department, Indiana University, 47405, Bloomington, IN, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lee", 
        "givenName": "Chan-Do", 
        "id": "sg:person.010701645035.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010701645035.21"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/0010-0277(88)90032-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005609105"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0010-0277(88)90032-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005609105"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0010-0277(88)90031-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016754718"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0010-0277(88)90031-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016754718"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/09540099008915667", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017286155"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1207/s15516709cog1402_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037432371"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/09540099008915666", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050260490"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3765/bls.v15i0.1732", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1071383434"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.21236/ada225536", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091558276"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.21236/ada164453", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091744995"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1992", 
    "datePublishedReg": "1992-01-01", 
    "description": "Natural language phonology presents a challenge to connectionists because it is an example of apparently symbolic, rule-governed behavior. This paper describes two experiments investigating the power of simple recurrent networks (SRNs) to acquire phonological regularities that can be described in terms of the persistence of particular features. The first experiment demonstrates the ability of an SRN to learn simple harmony constraints within morphemes; that is, restrictions on the co-occurrence of particular types of segments. The second experiment shows that an SRN is capable of learning patterns of feature persistence across morpheme boundaries, in this case, the alterations occurring in the regular plural forms of English nouns. This behavior is usually characterized in terms of a derivation from a more to a less abstract level; here it takes the form of the more psychologically plausible processes of the production of a sequence of segments given a meaning or the generation of a meaning given a sequence of segments. This is accomplished by having both segmental and semantic inputs and outputs in the network. Trained on the task of auto-associating the current segment and meaning and predicting the next segment, the network learns to produce the appropriate plural suffix on nouns it has seen in only the singular and to recognize novel plural forms as plural.", 
    "editor": [
      {
        "familyName": "Sharkey", 
        "givenName": "Noel", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-94-011-2624-3_16", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-94-010-5160-6", 
        "978-94-011-2624-3"
      ], 
      "name": "Connectionist Natural Language Processing", 
      "type": "Book"
    }, 
    "name": "Networks that Learn about Phonological Feature Persistence", 
    "pagination": "349-362", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1018609888"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-94-011-2624-3_16"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "58ab25ab439455528c6032a8be7a3ec7818c10f4dd7af2f1b41824750f860afe"
        ]
      }
    ], 
    "publisher": {
      "location": "Dordrecht", 
      "name": "Springer Netherlands", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-94-011-2624-3_16", 
      "https://app.dimensions.ai/details/publication/pub.1018609888"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T09:39", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000374_0000000374/records_119714_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-94-011-2624-3_16"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-94-011-2624-3_16'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-94-011-2624-3_16'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-94-011-2624-3_16'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-94-011-2624-3_16'


 

This table displays all metadata directly associated to this object as RDF triples.

96 TRIPLES      23 PREDICATES      35 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-94-011-2624-3_16 schema:about anzsrc-for:20
2 anzsrc-for:2004
3 schema:author N4e4f8bd39bee4cfe91e9b9c9ef0b165a
4 schema:citation https://doi.org/10.1016/0010-0277(88)90031-5
5 https://doi.org/10.1016/0010-0277(88)90032-7
6 https://doi.org/10.1080/09540099008915666
7 https://doi.org/10.1080/09540099008915667
8 https://doi.org/10.1207/s15516709cog1402_1
9 https://doi.org/10.21236/ada164453
10 https://doi.org/10.21236/ada225536
11 https://doi.org/10.3765/bls.v15i0.1732
12 schema:datePublished 1992
13 schema:datePublishedReg 1992-01-01
14 schema:description Natural language phonology presents a challenge to connectionists because it is an example of apparently symbolic, rule-governed behavior. This paper describes two experiments investigating the power of simple recurrent networks (SRNs) to acquire phonological regularities that can be described in terms of the persistence of particular features. The first experiment demonstrates the ability of an SRN to learn simple harmony constraints within morphemes; that is, restrictions on the co-occurrence of particular types of segments. The second experiment shows that an SRN is capable of learning patterns of feature persistence across morpheme boundaries, in this case, the alterations occurring in the regular plural forms of English nouns. This behavior is usually characterized in terms of a derivation from a more to a less abstract level; here it takes the form of the more psychologically plausible processes of the production of a sequence of segments given a meaning or the generation of a meaning given a sequence of segments. This is accomplished by having both segmental and semantic inputs and outputs in the network. Trained on the task of auto-associating the current segment and meaning and predicting the next segment, the network learns to produce the appropriate plural suffix on nouns it has seen in only the singular and to recognize novel plural forms as plural.
15 schema:editor N903e6cf97da446e9b258f65f7b22e1fa
16 schema:genre chapter
17 schema:inLanguage en
18 schema:isAccessibleForFree false
19 schema:isPartOf N0f0884c91c214f92b20fd7c7da1df640
20 schema:name Networks that Learn about Phonological Feature Persistence
21 schema:pagination 349-362
22 schema:productId N0f0cbd046e444de6a0fe87532553a10e
23 N8d0f8fe374a54c40bf8032b650d3b860
24 N8efcb2ec40e345798dcac7ada8ed4447
25 schema:publisher Nd6cc5d24e9e84d8dac88a1085e9d43c7
26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018609888
27 https://doi.org/10.1007/978-94-011-2624-3_16
28 schema:sdDatePublished 2019-04-16T09:39
29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
30 schema:sdPublisher Ndf3e7839c4de4799bae9b66f95ce12fb
31 schema:url https://link.springer.com/10.1007%2F978-94-011-2624-3_16
32 sgo:license sg:explorer/license/
33 sgo:sdDataset chapters
34 rdf:type schema:Chapter
35 N0f0884c91c214f92b20fd7c7da1df640 schema:isbn 978-94-010-5160-6
36 978-94-011-2624-3
37 schema:name Connectionist Natural Language Processing
38 rdf:type schema:Book
39 N0f0cbd046e444de6a0fe87532553a10e schema:name dimensions_id
40 schema:value pub.1018609888
41 rdf:type schema:PropertyValue
42 N1acc112b555546b9ad8bf58be2c44739 rdf:first sg:person.010701645035.21
43 rdf:rest rdf:nil
44 N4e4f8bd39bee4cfe91e9b9c9ef0b165a rdf:first sg:person.01212513340.93
45 rdf:rest N1acc112b555546b9ad8bf58be2c44739
46 N8612da64fdfd474682dd7a191deeffab schema:familyName Sharkey
47 schema:givenName Noel
48 rdf:type schema:Person
49 N8d0f8fe374a54c40bf8032b650d3b860 schema:name readcube_id
50 schema:value 58ab25ab439455528c6032a8be7a3ec7818c10f4dd7af2f1b41824750f860afe
51 rdf:type schema:PropertyValue
52 N8efcb2ec40e345798dcac7ada8ed4447 schema:name doi
53 schema:value 10.1007/978-94-011-2624-3_16
54 rdf:type schema:PropertyValue
55 N903e6cf97da446e9b258f65f7b22e1fa rdf:first N8612da64fdfd474682dd7a191deeffab
56 rdf:rest rdf:nil
57 Nd6cc5d24e9e84d8dac88a1085e9d43c7 schema:location Dordrecht
58 schema:name Springer Netherlands
59 rdf:type schema:Organisation
60 Ndf3e7839c4de4799bae9b66f95ce12fb schema:name Springer Nature - SN SciGraph project
61 rdf:type schema:Organization
62 anzsrc-for:20 schema:inDefinedTermSet anzsrc-for:
63 schema:name Language, Communication and Culture
64 rdf:type schema:DefinedTerm
65 anzsrc-for:2004 schema:inDefinedTermSet anzsrc-for:
66 schema:name Linguistics
67 rdf:type schema:DefinedTerm
68 sg:person.010701645035.21 schema:affiliation https://www.grid.ac/institutes/grid.411377.7
69 schema:familyName Lee
70 schema:givenName Chan-Do
71 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010701645035.21
72 rdf:type schema:Person
73 sg:person.01212513340.93 schema:affiliation https://www.grid.ac/institutes/grid.411377.7
74 schema:familyName Gasser
75 schema:givenName Michael
76 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01212513340.93
77 rdf:type schema:Person
78 https://doi.org/10.1016/0010-0277(88)90031-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016754718
79 rdf:type schema:CreativeWork
80 https://doi.org/10.1016/0010-0277(88)90032-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005609105
81 rdf:type schema:CreativeWork
82 https://doi.org/10.1080/09540099008915666 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050260490
83 rdf:type schema:CreativeWork
84 https://doi.org/10.1080/09540099008915667 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017286155
85 rdf:type schema:CreativeWork
86 https://doi.org/10.1207/s15516709cog1402_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037432371
87 rdf:type schema:CreativeWork
88 https://doi.org/10.21236/ada164453 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091744995
89 rdf:type schema:CreativeWork
90 https://doi.org/10.21236/ada225536 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091558276
91 rdf:type schema:CreativeWork
92 https://doi.org/10.3765/bls.v15i0.1732 schema:sameAs https://app.dimensions.ai/details/publication/pub.1071383434
93 rdf:type schema:CreativeWork
94 https://www.grid.ac/institutes/grid.411377.7 schema:alternateName Indiana University Bloomington
95 schema:name Computer Science Department, Indiana University, 47405, Bloomington, IN, USA
96 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...