A Word Embedding Transfer Model for Robust Text Categorization View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018-10-07

AUTHORS

Yiming Zhang , Jing Wang , Weijian Deng , Yaojie Lu

ABSTRACT

It is common to fine-tune pre-trained word embeddings in text categorization. However, we find that fine-tuning does not guarantee improvement across text categorization datasets, while could introduce considerable parameters to model. In this paper, we study new transfer methods to solve the problems above, and propose “Robustness of OOVs” to provide a perspective to reduce memory consumption further. The experimental results show that the proposed method is proved to be a good alternative to fine-tuning method on large dataset. More... »

PAGES

314-323

Book

TITLE

Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data

ISBN

978-3-030-01715-6
978-3-030-01716-3

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-01716-3_26

DOI

http://dx.doi.org/10.1007/978-3-030-01716-3_26

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1107463484


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/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Institute of Information Engineering", 
          "id": "https://www.grid.ac/institutes/grid.458480.5", 
          "name": [
            "Institute of Information Engineering, CAS, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhang", 
        "givenName": "Yiming", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Beijing University of Posts and Telecommunications", 
          "id": "https://www.grid.ac/institutes/grid.31880.32", 
          "name": [
            "Beijing University of Posts and Telecommunications, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Jing", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute of Information Engineering", 
          "id": "https://www.grid.ac/institutes/grid.458480.5", 
          "name": [
            "Institute of Information Engineering, CAS, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Deng", 
        "givenName": "Weijian", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute of Software", 
          "id": "https://www.grid.ac/institutes/grid.458446.f", 
          "name": [
            "Institute of Software, CAS, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lu", 
        "givenName": "Yaojie", 
        "id": "sg:person.014543632126.85", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014543632126.85"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1109/5.726791", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061179979"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2015.123", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093828312"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/p17-1001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1096025145"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/p17-1018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1096025162"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/p17-1052", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1096025493"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/d16-1046", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098652941"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/p15-2058", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110187"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/p15-2058", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110187"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/d14-1162", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110523"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/d14-1162", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110523"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/d14-1181", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110546"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/d14-1181", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110546"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/p14-1062", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110648"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/p14-1062", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099110648"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/tacl_a_00051", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110957692"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/tacl_a_00051", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110957692"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-10-07", 
    "datePublishedReg": "2018-10-07", 
    "description": "It is common to fine-tune pre-trained word embeddings in text categorization. However, we find that fine-tuning does not guarantee improvement across text categorization datasets, while could introduce considerable parameters to model. In this paper, we study new transfer methods to solve the problems above, and propose \u201cRobustness of OOVs\u201d to provide a perspective to reduce memory consumption further. The experimental results show that the proposed method is proved to be a good alternative to fine-tuning method on large dataset.", 
    "editor": [
      {
        "familyName": "Sun", 
        "givenName": "Maosong", 
        "type": "Person"
      }, 
      {
        "familyName": "Liu", 
        "givenName": "Ting", 
        "type": "Person"
      }, 
      {
        "familyName": "Wang", 
        "givenName": "Xiaojie", 
        "type": "Person"
      }, 
      {
        "familyName": "Liu", 
        "givenName": "Zhiyuan", 
        "type": "Person"
      }, 
      {
        "familyName": "Liu", 
        "givenName": "Yang", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-01716-3_26", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-030-01715-6", 
        "978-3-030-01716-3"
      ], 
      "name": "Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data", 
      "type": "Book"
    }, 
    "name": "A Word Embedding Transfer Model for Robust Text Categorization", 
    "pagination": "314-323", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-01716-3_26"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "082d5b2de88c9cf2c294eee9531c129e9ee22cc7b39cf54a8fb62b3d7b26a2cf"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1107463484"
        ]
      }
    ], 
    "publisher": {
      "location": "Cham", 
      "name": "Springer International Publishing", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-01716-3_26", 
      "https://app.dimensions.ai/details/publication/pub.1107463484"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T04:39", 
    "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/v90/0000000321_0000000321/records_74928_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-3-030-01716-3_26"
  }
]
 

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.10.1007/978-3-030-01716-3_26'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01716-3_26'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01716-3_26'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01716-3_26'


 

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

142 TRIPLES      23 PREDICATES      37 URIs      19 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-01716-3_26 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author Ndce648a8d9e546bda47b2dcfec024a2a
4 schema:citation https://doi.org/10.1109/5.726791
5 https://doi.org/10.1109/iccv.2015.123
6 https://doi.org/10.1162/tacl_a_00051
7 https://doi.org/10.18653/v1/d16-1046
8 https://doi.org/10.18653/v1/p17-1001
9 https://doi.org/10.18653/v1/p17-1018
10 https://doi.org/10.18653/v1/p17-1052
11 https://doi.org/10.3115/v1/d14-1162
12 https://doi.org/10.3115/v1/d14-1181
13 https://doi.org/10.3115/v1/p14-1062
14 https://doi.org/10.3115/v1/p15-2058
15 schema:datePublished 2018-10-07
16 schema:datePublishedReg 2018-10-07
17 schema:description It is common to fine-tune pre-trained word embeddings in text categorization. However, we find that fine-tuning does not guarantee improvement across text categorization datasets, while could introduce considerable parameters to model. In this paper, we study new transfer methods to solve the problems above, and propose “Robustness of OOVs” to provide a perspective to reduce memory consumption further. The experimental results show that the proposed method is proved to be a good alternative to fine-tuning method on large dataset.
18 schema:editor Naf3e64dae38d45b1b821d8603028114c
19 schema:genre chapter
20 schema:inLanguage en
21 schema:isAccessibleForFree false
22 schema:isPartOf N9fcabd38b20341709680ce084bd8baae
23 schema:name A Word Embedding Transfer Model for Robust Text Categorization
24 schema:pagination 314-323
25 schema:productId N00ce6aefb0724576b6dcfb5993219b93
26 N677d18ba649444fe8167d0b9f37c061b
27 Nceaea1cd867345cf8d46e3bf7d378951
28 schema:publisher Nff9a43c0dd6945c9a3b478a727d46a16
29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107463484
30 https://doi.org/10.1007/978-3-030-01716-3_26
31 schema:sdDatePublished 2019-04-16T04:39
32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
33 schema:sdPublisher N4ab886d7f25e4ca78c6e10a02024d3ba
34 schema:url https://link.springer.com/10.1007%2F978-3-030-01716-3_26
35 sgo:license sg:explorer/license/
36 sgo:sdDataset chapters
37 rdf:type schema:Chapter
38 N00ce6aefb0724576b6dcfb5993219b93 schema:name dimensions_id
39 schema:value pub.1107463484
40 rdf:type schema:PropertyValue
41 N02ae4bfba07d46e9964fe9b8e61e8df0 schema:familyName Liu
42 schema:givenName Zhiyuan
43 rdf:type schema:Person
44 N050cab75c4184f03a1a98028f65c4497 rdf:first N02ae4bfba07d46e9964fe9b8e61e8df0
45 rdf:rest Ne7c2f44968bf4f07a86dc57b9087d1a8
46 N0db5c6a12d4545c0a400850f2985e29c schema:familyName Liu
47 schema:givenName Ting
48 rdf:type schema:Person
49 N32ab9c52b9b3473f88569531570a9efc rdf:first N3ed64fc398224558bfa559272ba5e3d7
50 rdf:rest N050cab75c4184f03a1a98028f65c4497
51 N3d6ff670db6d4918892a3e484266ca0f schema:affiliation https://www.grid.ac/institutes/grid.31880.32
52 schema:familyName Wang
53 schema:givenName Jing
54 rdf:type schema:Person
55 N3ed64fc398224558bfa559272ba5e3d7 schema:familyName Wang
56 schema:givenName Xiaojie
57 rdf:type schema:Person
58 N482c35fd081744dab5ad63c5d0b5f8c9 schema:familyName Liu
59 schema:givenName Yang
60 rdf:type schema:Person
61 N4ab886d7f25e4ca78c6e10a02024d3ba schema:name Springer Nature - SN SciGraph project
62 rdf:type schema:Organization
63 N4ffecf5ae02f4247b80b83511b012e66 rdf:first N7ba6a9f231a244bebb787c6a858bdddf
64 rdf:rest Nc6239ef97ea6448f8a0757945a2041bc
65 N677d18ba649444fe8167d0b9f37c061b schema:name doi
66 schema:value 10.1007/978-3-030-01716-3_26
67 rdf:type schema:PropertyValue
68 N6a42113393ed4f29beea566f5184472b schema:familyName Sun
69 schema:givenName Maosong
70 rdf:type schema:Person
71 N7ba6a9f231a244bebb787c6a858bdddf schema:affiliation https://www.grid.ac/institutes/grid.458480.5
72 schema:familyName Deng
73 schema:givenName Weijian
74 rdf:type schema:Person
75 N9fcabd38b20341709680ce084bd8baae schema:isbn 978-3-030-01715-6
76 978-3-030-01716-3
77 schema:name Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data
78 rdf:type schema:Book
79 Na8d3fdb31308433a88bf5410dcfacd44 rdf:first N0db5c6a12d4545c0a400850f2985e29c
80 rdf:rest N32ab9c52b9b3473f88569531570a9efc
81 Naf3e64dae38d45b1b821d8603028114c rdf:first N6a42113393ed4f29beea566f5184472b
82 rdf:rest Na8d3fdb31308433a88bf5410dcfacd44
83 Nc6239ef97ea6448f8a0757945a2041bc rdf:first sg:person.014543632126.85
84 rdf:rest rdf:nil
85 Nccd86c5be702431688d61130ebd3240a schema:affiliation https://www.grid.ac/institutes/grid.458480.5
86 schema:familyName Zhang
87 schema:givenName Yiming
88 rdf:type schema:Person
89 Nceaea1cd867345cf8d46e3bf7d378951 schema:name readcube_id
90 schema:value 082d5b2de88c9cf2c294eee9531c129e9ee22cc7b39cf54a8fb62b3d7b26a2cf
91 rdf:type schema:PropertyValue
92 Ndce648a8d9e546bda47b2dcfec024a2a rdf:first Nccd86c5be702431688d61130ebd3240a
93 rdf:rest Ndf0e0385d7be45dabe58e2240c8fae4e
94 Ndf0e0385d7be45dabe58e2240c8fae4e rdf:first N3d6ff670db6d4918892a3e484266ca0f
95 rdf:rest N4ffecf5ae02f4247b80b83511b012e66
96 Ne7c2f44968bf4f07a86dc57b9087d1a8 rdf:first N482c35fd081744dab5ad63c5d0b5f8c9
97 rdf:rest rdf:nil
98 Nff9a43c0dd6945c9a3b478a727d46a16 schema:location Cham
99 schema:name Springer International Publishing
100 rdf:type schema:Organisation
101 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
102 schema:name Mathematical Sciences
103 rdf:type schema:DefinedTerm
104 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
105 schema:name Statistics
106 rdf:type schema:DefinedTerm
107 sg:person.014543632126.85 schema:affiliation https://www.grid.ac/institutes/grid.458446.f
108 schema:familyName Lu
109 schema:givenName Yaojie
110 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014543632126.85
111 rdf:type schema:Person
112 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
113 rdf:type schema:CreativeWork
114 https://doi.org/10.1109/iccv.2015.123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093828312
115 rdf:type schema:CreativeWork
116 https://doi.org/10.1162/tacl_a_00051 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110957692
117 rdf:type schema:CreativeWork
118 https://doi.org/10.18653/v1/d16-1046 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098652941
119 rdf:type schema:CreativeWork
120 https://doi.org/10.18653/v1/p17-1001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096025145
121 rdf:type schema:CreativeWork
122 https://doi.org/10.18653/v1/p17-1018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096025162
123 rdf:type schema:CreativeWork
124 https://doi.org/10.18653/v1/p17-1052 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096025493
125 rdf:type schema:CreativeWork
126 https://doi.org/10.3115/v1/d14-1162 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110523
127 rdf:type schema:CreativeWork
128 https://doi.org/10.3115/v1/d14-1181 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110546
129 rdf:type schema:CreativeWork
130 https://doi.org/10.3115/v1/p14-1062 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110648
131 rdf:type schema:CreativeWork
132 https://doi.org/10.3115/v1/p15-2058 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110187
133 rdf:type schema:CreativeWork
134 https://www.grid.ac/institutes/grid.31880.32 schema:alternateName Beijing University of Posts and Telecommunications
135 schema:name Beijing University of Posts and Telecommunications, Beijing, China
136 rdf:type schema:Organization
137 https://www.grid.ac/institutes/grid.458446.f schema:alternateName Institute of Software
138 schema:name Institute of Software, CAS, Beijing, China
139 rdf:type schema:Organization
140 https://www.grid.ac/institutes/grid.458480.5 schema:alternateName Institute of Information Engineering
141 schema:name Institute of Information Engineering, CAS, Beijing, China
142 rdf:type schema:Organization
 




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


...