Machine Learning for Natural Language Processing (and Vice Versa?) View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2005

AUTHORS

Claire Cardie

ABSTRACT

Over the past 10-15 years, the influence of methods from machine learning has transformed the way that research is done in the field of natural language processing. This talk will begin by covering the history of this transformation. In particular, learning methods have proved successful in producing stand-alone text-processing components to handle a number of linguistic tasks. Moreover, these components can be combined to produce systems that exhibit shallow text-understanding capabilities: they can, for example, extract key facts from unrestricted documents in limited domains or find answers to general-purpose questions from open-domain document collections. I will briefly describe the state of the art for these practical text-processing applications, focusing on the important role that machine learning methods have played in their development. The second part of the talk will explore the role that natural language processing might play in machine learning research. Here, I will explain the kinds of text-based features that are relatively easy to incorporate into machine learning data sets. In addition, I’ll outline some problems from natural language processing that require, or could at least benefit from, new machine learning algorithms. More... »

PAGES

2-2

Book

TITLE

Knowledge Discovery in Databases: PKDD 2005

ISBN

978-3-540-29244-9
978-3-540-31665-7

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11564126_2

DOI

http://dx.doi.org/10.1007/11564126_2

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1010539687


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Cornell University", 
          "id": "https://www.grid.ac/institutes/grid.5386.8", 
          "name": [
            "Department of Computer Science, Cornell University, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cardie", 
        "givenName": "Claire", 
        "id": "sg:person.0742614604.95", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0742614604.95"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2005", 
    "datePublishedReg": "2005-01-01", 
    "description": "Over the past 10-15 years, the influence of methods from machine learning has transformed the way that research is done in the field of natural language processing. This talk will begin by covering the history of this transformation. In particular, learning methods have proved successful in producing stand-alone text-processing components to handle a number of linguistic tasks. Moreover, these components can be combined to produce systems that exhibit shallow text-understanding capabilities: they can, for example, extract key facts from unrestricted documents in limited domains or find answers to general-purpose questions from open-domain document collections. I will briefly describe the state of the art for these practical text-processing applications, focusing on the important role that machine learning methods have played in their development. The second part of the talk will explore the role that natural language processing might play in machine learning research. Here, I will explain the kinds of text-based features that are relatively easy to incorporate into machine learning data sets. In addition, I\u2019ll outline some problems from natural language processing that require, or could at least benefit from, new machine learning algorithms.", 
    "editor": [
      {
        "familyName": "Jorge", 
        "givenName": "Al\u00edpio M\u00e1rio", 
        "type": "Person"
      }, 
      {
        "familyName": "Torgo", 
        "givenName": "Lu\u00eds", 
        "type": "Person"
      }, 
      {
        "familyName": "Brazdil", 
        "givenName": "Pavel", 
        "type": "Person"
      }, 
      {
        "familyName": "Camacho", 
        "givenName": "Rui", 
        "type": "Person"
      }, 
      {
        "familyName": "Gama", 
        "givenName": "Jo\u00e3o", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/11564126_2", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-29244-9", 
        "978-3-540-31665-7"
      ], 
      "name": "Knowledge Discovery in Databases: PKDD 2005", 
      "type": "Book"
    }, 
    "name": "Machine Learning for Natural Language Processing (and Vice Versa?)", 
    "pagination": "2-2", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11564126_2"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "32360539a000402576e4ce36b2586e61c2c3ba8c0af96a3d1db5c20b60ba4fe4"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1010539687"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11564126_2", 
      "https://app.dimensions.ai/details/publication/pub.1010539687"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T00:33", 
    "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/v90/0000000001_0000000264/records_8700_00000018.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/11564126_2"
  }
]
 

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.10.1007/11564126_2'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11564126_2'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11564126_2'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11564126_2'


 

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

85 TRIPLES      22 PREDICATES      27 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11564126_2 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ndfd522c711dc4657bd850e6b98dd2a95
4 schema:datePublished 2005
5 schema:datePublishedReg 2005-01-01
6 schema:description Over the past 10-15 years, the influence of methods from machine learning has transformed the way that research is done in the field of natural language processing. This talk will begin by covering the history of this transformation. In particular, learning methods have proved successful in producing stand-alone text-processing components to handle a number of linguistic tasks. Moreover, these components can be combined to produce systems that exhibit shallow text-understanding capabilities: they can, for example, extract key facts from unrestricted documents in limited domains or find answers to general-purpose questions from open-domain document collections. I will briefly describe the state of the art for these practical text-processing applications, focusing on the important role that machine learning methods have played in their development. The second part of the talk will explore the role that natural language processing might play in machine learning research. Here, I will explain the kinds of text-based features that are relatively easy to incorporate into machine learning data sets. In addition, I’ll outline some problems from natural language processing that require, or could at least benefit from, new machine learning algorithms.
7 schema:editor N6a039f94a63f4c72a4cbc28ae3afd69c
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf Ncd61fc60dbc74c6b9e72d63e3ce444a4
12 schema:name Machine Learning for Natural Language Processing (and Vice Versa?)
13 schema:pagination 2-2
14 schema:productId N2cd03658505b406a8cb4eb058154ebb8
15 Na448904283c74950a34180566f48fa61
16 Na63bfd8361294d4f88b3977da635f36b
17 schema:publisher Na9ec671ac0bb43f0931f7d47c284fa12
18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010539687
19 https://doi.org/10.1007/11564126_2
20 schema:sdDatePublished 2019-04-16T00:33
21 schema:sdLicense https://scigraph.springernature.com/explorer/license/
22 schema:sdPublisher N1337b0be02f042578c3c680a4dc1bbc5
23 schema:url http://link.springer.com/10.1007/11564126_2
24 sgo:license sg:explorer/license/
25 sgo:sdDataset chapters
26 rdf:type schema:Chapter
27 N1337b0be02f042578c3c680a4dc1bbc5 schema:name Springer Nature - SN SciGraph project
28 rdf:type schema:Organization
29 N2cd03658505b406a8cb4eb058154ebb8 schema:name readcube_id
30 schema:value 32360539a000402576e4ce36b2586e61c2c3ba8c0af96a3d1db5c20b60ba4fe4
31 rdf:type schema:PropertyValue
32 N305ae734ea724774a75b449105a63c07 rdf:first N357c9a4d8d0f4420b176c06d36b8fa75
33 rdf:rest N7d871d396d7d45c4aa88ff078bf6d91a
34 N357c9a4d8d0f4420b176c06d36b8fa75 schema:familyName Torgo
35 schema:givenName Luís
36 rdf:type schema:Person
37 N4377900a332c4f66b60c43adb4f5164f rdf:first N9a0c6b100bd4483cbc71180493c1ad3b
38 rdf:rest rdf:nil
39 N6a039f94a63f4c72a4cbc28ae3afd69c rdf:first Nf93a99b133144c9997058bd251e028c2
40 rdf:rest N305ae734ea724774a75b449105a63c07
41 N7d871d396d7d45c4aa88ff078bf6d91a rdf:first Na67855f1ed8b4be1a134e28c9e5644e1
42 rdf:rest Nc31ba8e48ae04a14b6e7db0add4f2a71
43 N9a0c6b100bd4483cbc71180493c1ad3b schema:familyName Gama
44 schema:givenName João
45 rdf:type schema:Person
46 Na448904283c74950a34180566f48fa61 schema:name doi
47 schema:value 10.1007/11564126_2
48 rdf:type schema:PropertyValue
49 Na63bfd8361294d4f88b3977da635f36b schema:name dimensions_id
50 schema:value pub.1010539687
51 rdf:type schema:PropertyValue
52 Na67855f1ed8b4be1a134e28c9e5644e1 schema:familyName Brazdil
53 schema:givenName Pavel
54 rdf:type schema:Person
55 Na9ec671ac0bb43f0931f7d47c284fa12 schema:location Berlin, Heidelberg
56 schema:name Springer Berlin Heidelberg
57 rdf:type schema:Organisation
58 Nc31ba8e48ae04a14b6e7db0add4f2a71 rdf:first Nd81fc53babc64617ad2c4883c432715c
59 rdf:rest N4377900a332c4f66b60c43adb4f5164f
60 Ncd61fc60dbc74c6b9e72d63e3ce444a4 schema:isbn 978-3-540-29244-9
61 978-3-540-31665-7
62 schema:name Knowledge Discovery in Databases: PKDD 2005
63 rdf:type schema:Book
64 Nd81fc53babc64617ad2c4883c432715c schema:familyName Camacho
65 schema:givenName Rui
66 rdf:type schema:Person
67 Ndfd522c711dc4657bd850e6b98dd2a95 rdf:first sg:person.0742614604.95
68 rdf:rest rdf:nil
69 Nf93a99b133144c9997058bd251e028c2 schema:familyName Jorge
70 schema:givenName Alípio Mário
71 rdf:type schema:Person
72 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
73 schema:name Information and Computing Sciences
74 rdf:type schema:DefinedTerm
75 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
76 schema:name Artificial Intelligence and Image Processing
77 rdf:type schema:DefinedTerm
78 sg:person.0742614604.95 schema:affiliation https://www.grid.ac/institutes/grid.5386.8
79 schema:familyName Cardie
80 schema:givenName Claire
81 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0742614604.95
82 rdf:type schema:Person
83 https://www.grid.ac/institutes/grid.5386.8 schema:alternateName Cornell University
84 schema:name Department of Computer Science, Cornell University, USA
85 rdf:type schema:Organization
 




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


...