6027522
03
01
01
JB
John Benjamins Publishing Company
01
JB code
NLP 14 Eb
15
9789027258489
06
10.1075/nlp.14
13
2021042005
DG
002
02
01
NLP
02
1567-8202
Natural Language Processing
14
01
The Swedish FrameNet++
The
Swedish FrameNet++
Harmonization, integration, method development and practical language technology applications
01
nlp.14
01
https://benjamins.com
02
https://benjamins.com/catalog/nlp.14
1
B01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
2
B01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
3
B01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
HeppiLing AB
01
eng
347
xiv
333
LAN009000
v.2006
CFX
2
24
JB Subject Scheme
LIN.COMPUT
Computational & corpus linguistics
24
JB Subject Scheme
LIN.CORP
Corpus linguistics
24
JB Subject Scheme
LIN.GERM
Germanic linguistics
06
01
Large computational lexicons are central NLP resources. Swedish FrameNet++ aims to be a versatile full-scale lexical resource for NLP containing many kinds of linguistic information. Although focused on Swedish, this ongoing effort, which includes building a new Swedish framenet and recycling existing lexicons, has offered valuable insights into general aspects of lexical-resource building for NLP, which are discussed in this book: computational and linguistic problems of lexical semantics and lexical typology, the nature of lexical items (words and multiword expressions), achieving interoperability among heterogeneous lexical content, NLP methods for extending and interlinking existing lexicons, and deploying the new resource in practical NLP applications. This book is targeted at everyone with an interest in lexicography, computational lexicography, lexical typology, lexical semantics, linguistics, computational linguistics and related fields. We believe it should be of particular interest to those who are or have been involved in language resource creation, development and evaluation.
46
01
http://creativecommons.org/licenses/by-nc-nd/4.0/
47
Open access -- this title is available under a CC BY-NC-ND license. For full details, see: http://creativecommons.org/licenses/by-nc-nd/4.0/
04
09
01
https://benjamins.com/covers/475/nlp.14.png
04
03
01
https://benjamins.com/covers/475_jpg/9789027209900.jpg
04
03
01
https://benjamins.com/covers/475_tif/9789027209900.tif
06
09
01
https://benjamins.com/covers/1200_front/nlp.14.hb.png
07
09
01
https://benjamins.com/covers/125/nlp.14.png
25
09
01
https://benjamins.com/covers/1200_back/nlp.14.hb.png
27
09
01
https://benjamins.com/covers/3d_web/nlp.14.hb.png
10
01
JB code
nlp.14.loa
vii
viii
2
Miscellaneous
1
01
Acronyms
10
01
JB code
nlp.14.glossary
ix
x
2
Miscellaneous
2
01
Abbreviations
10
01
JB code
nlp.14.pre
xi
xiv
4
Miscellaneous
3
01
Preface
10
01
JB code
nlp.14.p1
4
65
62
Section header
4
01
Part I. Introduction and background
10
01
JB code
nlp.14.01bor
3
36
34
Chapter
5
01
Chapter 1. Introduction
Swedish FrameNet++
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
2
A01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
3
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent researcher
01
The Swedish FrameNet++ was designed to be several things. As a <i>digital artifact</i>, it is an integrated panchronic lexical macroresource, primarily for Swedish, but including several other languages, intended as a basic infrastructural component in Swedish language technology research and for developing natural language processing applications. As an <i>activity</i>, it is a long-term R&D initiative, initially aimed at bringing about this macroresource, and now at maintaining and extending it, at promoting its use in language technology research and application development, as well as ensuring that the results of this research and development in their turn are incorporated in the macroresource. As a <i>product of research</i>, it reflects both computational and linguistic approaches to lexicology, lexical semantics, and lexical typology.
10
01
JB code
nlp.14.02dan
37
66
30
Chapter
6
01
Chapter 2. Swedish FrameNet
1
A01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
2
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
3
A01
Markus Forsberg
Forsberg, Markus
Markus
Forsberg
University of Gothenburg
4
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent researcher
5
A01
Maria Toporowska Gronostaj
Gronostaj, Maria Toporowska
Maria Toporowska
Gronostaj
University of Gothenburg
01
This chapter describes the development of Swedish FrameNet. A new framenet project often follows one of two methodological approaches: (1) <i>extension</i>, through translation of a different-language – often English – framenet into the target language, and (2) <i>merging</i>, where the resource is built from scratch in the target language. Both approaches have their pros and cons, which have been extensively discussed in the literature. Swedish FrameNet is mainly developed through the extension approach, although balanced with the merging approach. Drawing on the two approaches simultaneously, we describe how integrated language resources and tools have been exploited to create and develop Swedish FrameNet: how it was constructed, what it contains, and the basic assumptions underlying the annotation of its contents.
10
01
JB code
nlp.14.p2
70
165
96
Section header
7
01
Part II. Harmonization and integration
10
01
JB code
nlp.14.03bor
69
96
28
Chapter
8
01
Chapter 3. Swedish FrameNet++ – lexical samsara
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
2
A01
Markus Forsberg
Forsberg, Markus
Markus
Forsberg
University of Gothenburg
3
A01
Lennart Lönngren
Lönngren, Lennart
Lennart
Lönngren
Arctic University of Norway
4
A01
Niklas Zechner
Zechner, Niklas
Niklas
Zechner
University of Gothenburg
01
One of the main goals of the Swedish FrameNet++ initiative is to recycle and include as many existing modern Swedish lexical resources as possible into one unified lexical macroresource useful for automatic language processing. In this chapter we describe the structure of Saldo, the central resource of Swedish FrameNet++, the design of the formal interlinking mechanism keeping the lexical macroresource together, and our work on Swesaurus, a Swedish wordnet, and a Swedish Roget-style thesaurus as components of Swedish FrameNet++.
10
01
JB code
nlp.14.04ade
97
122
26
Chapter
9
01
Chapter 4. A lexical resource for computational historical linguistics
1
A01
Yvonne Adesam
Adesam, Yvonne
Yvonne
Adesam
University of Gothenburg
2
A01
Peter Andersson Lilja
Lilja, Peter Andersson
Peter Andersson
Lilja
University of Gothenburg/University of Borås
3
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
4
A01
Gerlof Bouma
Bouma, Gerlof
Gerlof
Bouma
University of Gothenburg
01
In this chapter we present the diachronic dimension of Swedish FrameNet++. We describe the historical lexical resources currently available for Swedish, linked to the Contemporary Swedish lexicon Saldo. We present a case study of how interlinking the dictionaries simultaneously allows us to study lexical change. We also present a method of linking text words to lexicon entries, facilitating interactive exploration of historical texts. Diachronical language resources present both a high-variation challenge from a wider language technology perspective, and an interesting object of linguistic study. While a number of improvements of the parts of the diachronic lexical macroresource are still needed, this resource is invaluable for analysing and accessing historical texts, as well as for both synchronic historical and diachronic lexical studies.
10
01
JB code
nlp.14.05lin
123
138
16
Chapter
10
01
Chapter 5. A multilingual net of lexical resources
1
A01
Krister Lindén
Lindén, Krister
Krister
Lindén
University of Helsinki
2
A01
Jyrki Niemi
Niemi, Jyrki
Jyrki
Niemi
University of Helsinki
3
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
4
A01
Markus Forsberg
Forsberg, Markus
Markus
Forsberg
University of Gothenburg
5
A01
Bolette S. Pedersen
Pedersen, Bolette S.
Bolette S.
Pedersen
University of Copenhagen
6
A01
Sanni Nimb
Nimb, Sanni
Sanni
Nimb
The Society for Danish Language and Literature
7
A01
Heili Orav
Orav, Heili
Heili
Orav
University of Tartu
8
A01
Neeme Kahusk
Kahusk, Neeme
Neeme
Kahusk
University of Tartu
9
A01
Kadri Vider
Vider, Kadri
Kadri
Vider
University of Tartu
01
In this chapter, we explore how to develop and encode the relationship between wordnets for different languages using some Nordic and Baltic wordnets to illustrate the variety of approaches. We also briefly touch on how these wordnets have been enhanced or augmented with various types of lexical information, such as framenet frames as well as syntagmatic and sentiment information.
10
01
JB code
nlp.14.06bor
139
166
28
Chapter
11
01
Chapter 6. Swedish FrameNet++ and comparative linguistics
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
2
A01
Anju Saxena
Saxena, Anju
Anju
Saxena
Uppsala University
3
A01
Shafqat Mumtaz Virk
Virk, Shafqat Mumtaz
Shafqat Mumtaz
Virk
University of Gothenburg
4
A01
Bernard Comrie
Comrie, Bernard
Bernard
Comrie
University of California
01
In this chapter we describe a multilingual extension of Swedish FrameNet++, intended to address research questions of a broad comparative nature, in genealogical, areal and typological linguistics, focusing on the integration into Swedish FrameNet++ of so-called core vocabularies, used in several linguistic subfields in order to conduct massive comparative studies involving large numbers of languages. Specifically, we describe the inclusion of two such lexical databases covering several hundred South Asian languages, with the aim of investigating areal and genealogical connections among these languages.
10
01
JB code
nlp.14.p3
170
259
90
Section header
12
01
Part III. Method development
10
01
JB code
nlp.14.07joh
169
190
22
Chapter
13
01
Chapter 7. NLP for resource building
1
A01
Richard Johansson
Johansson, Richard
Richard
Johansson
University of Gothenburg
01
We evaluate several lexicon-based and corpus-based methods to automatically induce new lexical units for Swedish FrameNet, and we see that the best-performing setup uses a combination of both types of methods. A particular challenge for Swedish is the absence of a lexical resource such as WordNet; however, we show that the semantic network Saldo, which is organized according to lexicographical principles quite different from those of WordNet, is very useful for our purposes.
10
01
JB code
nlp.14.08fri
191
220
30
Chapter
14
01
Chapter 8. Differing design decisions – comparing Swedish FrameNet to FrameNet
1
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent Researcher
01
Creation of framenets for languages other than English based on Berkeley FrameNet has tested the hypothesis that semantic frames, to a certain extent, are language independent. This working hypothesis facilitated reuse of frames for new framenets, defining language specific frame evoking lemmas and annotating language specific sentences. The caveat is the bias towards creating what is possible, rather than typical, in a language. The reuse of frames allowed developing SweFN in a relatively short period of time. However, the goal to build a typical, not a possible Swedish framenet, necessitated some frame modifications. <br />This chapter provides a comparison between the English and Swedish framenets regarding semantic annotation and representation, and socio-cultural factors, including how differences forced modification of the original structure.
10
01
JB code
nlp.14.09bor
221
260
40
Chapter
15
01
Chapter 9. Multiword expressions – a tough typological nut for Swedish FrameNet++
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
01
Multiword expressions have attracted much attention in language technology over the last two decades or so, and in general linguistics, the interest in phraseology – which includes the linguistic study of multiword expressions – goes back much further. In our work on the multilingual components of Swedish FrameNet++, we have strived to adopt a typologically informed view on multiword expressions. This raises a number of theoretical and methodological questions, some of which are discussed in this chapter.
10
01
JB code
nlp.14.p4
264
329
66
Section header
16
01
Part IV. Natural language processing applications
10
01
JB code
nlp.14.10joh
263
280
18
Chapter
17
01
Chapter 10. Semantic role labeling
1
A01
Richard Johansson
Johansson, Richard
Richard
Johansson
University of Gothenburg
2
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent researcher
3
A01
Dimitrios Kokkinakis
Kokkinakis, Dimitrios
Dimitrios
Kokkinakis
University of Gothenburg
01
We investigate the feasibility of automatic <i>semantic role labeling</i> (SRL) using Swedish FrameNet (SweFN). In the first part of the chapter, we describe a baseline system using a traditional division into segmentation and labeling steps. These subsystems are implemented as separate machine learning models, and we explore a wide range of syntactic and lexical features for these models. In the second part, we turn to the question of how the frame-to-frame relations defined in FrameNet allow us to use the annotated examples more effectively. The cross-frame generalization methods reduce the number of errors made by the labeling classifier by 27%. For previously unseen frames, the reduction is even more significant: 50%.
10
01
JB code
nlp.14.11dan
281
302
22
Chapter
18
01
Chapter 11. Computational representation of FrameNet for multilingual natural language generation
1
A01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
2
A01
Normunds Grūzītis
Grūzītis, Normunds
Normunds
Grūzītis
IMCS, University of Latvia
01
Multilingual natural language generation, the process of producing written or spoken utterances in parallel languages from either structured or unstructured representations requires large amounts of syntactic and semantic information to generate an expression that is tailored to the target audience. This information is offered by FrameNet-like resources, which have been developed for a number of languages. In this chapter, we present a computational FrameNet grammar resource for multilingual natural language generation. We compare between English and Swedish framenets to illustrate how these can be unified under a shared computational representation using Grammatical Framework. We demonstrate how the grammar was exploited in two practical multilingual natural language generation applications to facilitate tourist communication and empower museum users with coherent artwork descriptions.
10
01
JB code
nlp.14.12pre
303
330
28
Chapter
19
01
Chapter 12. Language learning and teaching with Swedish FrameNet++
Two examples
1
A01
Julia Prentice
Prentice, Julia
Julia
Prentice
University of Gothenburg
2
A01
Camilla Håkansson
Håkansson, Camilla
Camilla
Håkansson
University of Gothenburg
3
A01
Therese Lindström Tiedemann
Lindström Tiedemann, Therese
Therese
Lindström Tiedemann
University of Helsinki
4
A01
Ildikó Pilán
Pilán, Ildikó
Ildikó
Pilán
Norwegian Computing Center
5
A01
Elena Volodina
Volodina, Elena
Elena
Volodina
University of Gothenburg
01
This chapter describes and discusses the use of resources connected to Swedish FrameNet++ (SweFN++) in the context of the teaching and learning of language proficiency and grammatical analysis in Swedish. We illustrate the way in which different resources in the SweFN++ context can be useful for language pedagogy, by employing two examples, the Swedish Constructicon and a semantic role exercise on the intelligent computer assisted language learning (ICALL) platform Lärka. These resources make use of the infrastructure developed within SweFN++ in fundamentally different ways, which are discussed and compared. In addition, we discuss the possibilities for further development of the language pedagogical potential of SweFN++, both in relation to ICALL and to other types of resources and descriptive databases, like corpora, constructicons and framenets.
10
01
JB code
nlp.14.ind
331
333
3
Miscellaneous
20
01
Index
02
JBENJAMINS
John Benjamins Publishing Company
01
John Benjamins Publishing Company
Amsterdam/Philadelphia
NL
04
20211126
2021
John Benjamins B.V.
02
WORLD
13
15
9789027209900
01
JB
3
John Benjamins e-Platform
03
jbe-platform.com
09
WORLD
40
01
738027521
03
01
01
JB
John Benjamins Publishing Company
01
JB code
NLP 14 Hb
15
9789027209900
13
2021042004
BB
01
NLP
02
1567-8202
Natural Language Processing
14
01
The Swedish FrameNet++
The
Swedish FrameNet++
Harmonization, integration, method development and practical language technology applications
01
nlp.14
01
https://benjamins.com
02
https://benjamins.com/catalog/nlp.14
1
B01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
2
B01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
3
B01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
HeppiLing AB
01
eng
347
xiv
333
LAN009000
v.2006
CFX
2
24
JB Subject Scheme
LIN.COMPUT
Computational & corpus linguistics
24
JB Subject Scheme
LIN.CORP
Corpus linguistics
24
JB Subject Scheme
LIN.GERM
Germanic linguistics
06
01
Large computational lexicons are central NLP resources. Swedish FrameNet++ aims to be a versatile full-scale lexical resource for NLP containing many kinds of linguistic information. Although focused on Swedish, this ongoing effort, which includes building a new Swedish framenet and recycling existing lexicons, has offered valuable insights into general aspects of lexical-resource building for NLP, which are discussed in this book: computational and linguistic problems of lexical semantics and lexical typology, the nature of lexical items (words and multiword expressions), achieving interoperability among heterogeneous lexical content, NLP methods for extending and interlinking existing lexicons, and deploying the new resource in practical NLP applications. This book is targeted at everyone with an interest in lexicography, computational lexicography, lexical typology, lexical semantics, linguistics, computational linguistics and related fields. We believe it should be of particular interest to those who are or have been involved in language resource creation, development and evaluation.
04
09
01
https://benjamins.com/covers/475/nlp.14.png
04
03
01
https://benjamins.com/covers/475_jpg/9789027209900.jpg
04
03
01
https://benjamins.com/covers/475_tif/9789027209900.tif
06
09
01
https://benjamins.com/covers/1200_front/nlp.14.hb.png
07
09
01
https://benjamins.com/covers/125/nlp.14.png
25
09
01
https://benjamins.com/covers/1200_back/nlp.14.hb.png
27
09
01
https://benjamins.com/covers/3d_web/nlp.14.hb.png
10
01
JB code
nlp.14.loa
vii
viii
2
Miscellaneous
1
01
Acronyms
10
01
JB code
nlp.14.glossary
ix
x
2
Miscellaneous
2
01
Abbreviations
10
01
JB code
nlp.14.pre
xi
xiv
4
Miscellaneous
3
01
Preface
10
01
JB code
nlp.14.p1
4
65
62
Section header
4
01
Part I. Introduction and background
10
01
JB code
nlp.14.01bor
3
36
34
Chapter
5
01
Chapter 1. Introduction
Swedish FrameNet++
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
2
A01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
3
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent researcher
01
The Swedish FrameNet++ was designed to be several things. As a <i>digital artifact</i>, it is an integrated panchronic lexical macroresource, primarily for Swedish, but including several other languages, intended as a basic infrastructural component in Swedish language technology research and for developing natural language processing applications. As an <i>activity</i>, it is a long-term R&D initiative, initially aimed at bringing about this macroresource, and now at maintaining and extending it, at promoting its use in language technology research and application development, as well as ensuring that the results of this research and development in their turn are incorporated in the macroresource. As a <i>product of research</i>, it reflects both computational and linguistic approaches to lexicology, lexical semantics, and lexical typology.
10
01
JB code
nlp.14.02dan
37
66
30
Chapter
6
01
Chapter 2. Swedish FrameNet
1
A01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
2
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
3
A01
Markus Forsberg
Forsberg, Markus
Markus
Forsberg
University of Gothenburg
4
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent researcher
5
A01
Maria Toporowska Gronostaj
Gronostaj, Maria Toporowska
Maria Toporowska
Gronostaj
University of Gothenburg
01
This chapter describes the development of Swedish FrameNet. A new framenet project often follows one of two methodological approaches: (1) <i>extension</i>, through translation of a different-language – often English – framenet into the target language, and (2) <i>merging</i>, where the resource is built from scratch in the target language. Both approaches have their pros and cons, which have been extensively discussed in the literature. Swedish FrameNet is mainly developed through the extension approach, although balanced with the merging approach. Drawing on the two approaches simultaneously, we describe how integrated language resources and tools have been exploited to create and develop Swedish FrameNet: how it was constructed, what it contains, and the basic assumptions underlying the annotation of its contents.
10
01
JB code
nlp.14.p2
70
165
96
Section header
7
01
Part II. Harmonization and integration
10
01
JB code
nlp.14.03bor
69
96
28
Chapter
8
01
Chapter 3. Swedish FrameNet++ – lexical samsara
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
2
A01
Markus Forsberg
Forsberg, Markus
Markus
Forsberg
University of Gothenburg
3
A01
Lennart Lönngren
Lönngren, Lennart
Lennart
Lönngren
Arctic University of Norway
4
A01
Niklas Zechner
Zechner, Niklas
Niklas
Zechner
University of Gothenburg
01
One of the main goals of the Swedish FrameNet++ initiative is to recycle and include as many existing modern Swedish lexical resources as possible into one unified lexical macroresource useful for automatic language processing. In this chapter we describe the structure of Saldo, the central resource of Swedish FrameNet++, the design of the formal interlinking mechanism keeping the lexical macroresource together, and our work on Swesaurus, a Swedish wordnet, and a Swedish Roget-style thesaurus as components of Swedish FrameNet++.
10
01
JB code
nlp.14.04ade
97
122
26
Chapter
9
01
Chapter 4. A lexical resource for computational historical linguistics
1
A01
Yvonne Adesam
Adesam, Yvonne
Yvonne
Adesam
University of Gothenburg
2
A01
Peter Andersson Lilja
Lilja, Peter Andersson
Peter Andersson
Lilja
University of Gothenburg/University of Borås
3
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
4
A01
Gerlof Bouma
Bouma, Gerlof
Gerlof
Bouma
University of Gothenburg
01
In this chapter we present the diachronic dimension of Swedish FrameNet++. We describe the historical lexical resources currently available for Swedish, linked to the Contemporary Swedish lexicon Saldo. We present a case study of how interlinking the dictionaries simultaneously allows us to study lexical change. We also present a method of linking text words to lexicon entries, facilitating interactive exploration of historical texts. Diachronical language resources present both a high-variation challenge from a wider language technology perspective, and an interesting object of linguistic study. While a number of improvements of the parts of the diachronic lexical macroresource are still needed, this resource is invaluable for analysing and accessing historical texts, as well as for both synchronic historical and diachronic lexical studies.
10
01
JB code
nlp.14.05lin
123
138
16
Chapter
10
01
Chapter 5. A multilingual net of lexical resources
1
A01
Krister Lindén
Lindén, Krister
Krister
Lindén
University of Helsinki
2
A01
Jyrki Niemi
Niemi, Jyrki
Jyrki
Niemi
University of Helsinki
3
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
4
A01
Markus Forsberg
Forsberg, Markus
Markus
Forsberg
University of Gothenburg
5
A01
Bolette S. Pedersen
Pedersen, Bolette S.
Bolette S.
Pedersen
University of Copenhagen
6
A01
Sanni Nimb
Nimb, Sanni
Sanni
Nimb
The Society for Danish Language and Literature
7
A01
Heili Orav
Orav, Heili
Heili
Orav
University of Tartu
8
A01
Neeme Kahusk
Kahusk, Neeme
Neeme
Kahusk
University of Tartu
9
A01
Kadri Vider
Vider, Kadri
Kadri
Vider
University of Tartu
01
In this chapter, we explore how to develop and encode the relationship between wordnets for different languages using some Nordic and Baltic wordnets to illustrate the variety of approaches. We also briefly touch on how these wordnets have been enhanced or augmented with various types of lexical information, such as framenet frames as well as syntagmatic and sentiment information.
10
01
JB code
nlp.14.06bor
139
166
28
Chapter
11
01
Chapter 6. Swedish FrameNet++ and comparative linguistics
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
2
A01
Anju Saxena
Saxena, Anju
Anju
Saxena
Uppsala University
3
A01
Shafqat Mumtaz Virk
Virk, Shafqat Mumtaz
Shafqat Mumtaz
Virk
University of Gothenburg
4
A01
Bernard Comrie
Comrie, Bernard
Bernard
Comrie
University of California
01
In this chapter we describe a multilingual extension of Swedish FrameNet++, intended to address research questions of a broad comparative nature, in genealogical, areal and typological linguistics, focusing on the integration into Swedish FrameNet++ of so-called core vocabularies, used in several linguistic subfields in order to conduct massive comparative studies involving large numbers of languages. Specifically, we describe the inclusion of two such lexical databases covering several hundred South Asian languages, with the aim of investigating areal and genealogical connections among these languages.
10
01
JB code
nlp.14.p3
170
259
90
Section header
12
01
Part III. Method development
10
01
JB code
nlp.14.07joh
169
190
22
Chapter
13
01
Chapter 7. NLP for resource building
1
A01
Richard Johansson
Johansson, Richard
Richard
Johansson
University of Gothenburg
01
We evaluate several lexicon-based and corpus-based methods to automatically induce new lexical units for Swedish FrameNet, and we see that the best-performing setup uses a combination of both types of methods. A particular challenge for Swedish is the absence of a lexical resource such as WordNet; however, we show that the semantic network Saldo, which is organized according to lexicographical principles quite different from those of WordNet, is very useful for our purposes.
10
01
JB code
nlp.14.08fri
191
220
30
Chapter
14
01
Chapter 8. Differing design decisions – comparing Swedish FrameNet to FrameNet
1
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent Researcher
01
Creation of framenets for languages other than English based on Berkeley FrameNet has tested the hypothesis that semantic frames, to a certain extent, are language independent. This working hypothesis facilitated reuse of frames for new framenets, defining language specific frame evoking lemmas and annotating language specific sentences. The caveat is the bias towards creating what is possible, rather than typical, in a language. The reuse of frames allowed developing SweFN in a relatively short period of time. However, the goal to build a typical, not a possible Swedish framenet, necessitated some frame modifications. <br />This chapter provides a comparison between the English and Swedish framenets regarding semantic annotation and representation, and socio-cultural factors, including how differences forced modification of the original structure.
10
01
JB code
nlp.14.09bor
221
260
40
Chapter
15
01
Chapter 9. Multiword expressions – a tough typological nut for Swedish FrameNet++
1
A01
Lars Borin
Borin, Lars
Lars
Borin
University of Gothenburg
01
Multiword expressions have attracted much attention in language technology over the last two decades or so, and in general linguistics, the interest in phraseology – which includes the linguistic study of multiword expressions – goes back much further. In our work on the multilingual components of Swedish FrameNet++, we have strived to adopt a typologically informed view on multiword expressions. This raises a number of theoretical and methodological questions, some of which are discussed in this chapter.
10
01
JB code
nlp.14.p4
264
329
66
Section header
16
01
Part IV. Natural language processing applications
10
01
JB code
nlp.14.10joh
263
280
18
Chapter
17
01
Chapter 10. Semantic role labeling
1
A01
Richard Johansson
Johansson, Richard
Richard
Johansson
University of Gothenburg
2
A01
Karin Friberg Heppin
Friberg Heppin, Karin
Karin
Friberg Heppin
Independent researcher
3
A01
Dimitrios Kokkinakis
Kokkinakis, Dimitrios
Dimitrios
Kokkinakis
University of Gothenburg
01
We investigate the feasibility of automatic <i>semantic role labeling</i> (SRL) using Swedish FrameNet (SweFN). In the first part of the chapter, we describe a baseline system using a traditional division into segmentation and labeling steps. These subsystems are implemented as separate machine learning models, and we explore a wide range of syntactic and lexical features for these models. In the second part, we turn to the question of how the frame-to-frame relations defined in FrameNet allow us to use the annotated examples more effectively. The cross-frame generalization methods reduce the number of errors made by the labeling classifier by 27%. For previously unseen frames, the reduction is even more significant: 50%.
10
01
JB code
nlp.14.11dan
281
302
22
Chapter
18
01
Chapter 11. Computational representation of FrameNet for multilingual natural language generation
1
A01
Dana Dannélls
Dannélls, Dana
Dana
Dannélls
University of Gothenburg
2
A01
Normunds Grūzītis
Grūzītis, Normunds
Normunds
Grūzītis
IMCS, University of Latvia
01
Multilingual natural language generation, the process of producing written or spoken utterances in parallel languages from either structured or unstructured representations requires large amounts of syntactic and semantic information to generate an expression that is tailored to the target audience. This information is offered by FrameNet-like resources, which have been developed for a number of languages. In this chapter, we present a computational FrameNet grammar resource for multilingual natural language generation. We compare between English and Swedish framenets to illustrate how these can be unified under a shared computational representation using Grammatical Framework. We demonstrate how the grammar was exploited in two practical multilingual natural language generation applications to facilitate tourist communication and empower museum users with coherent artwork descriptions.
10
01
JB code
nlp.14.12pre
303
330
28
Chapter
19
01
Chapter 12. Language learning and teaching with Swedish FrameNet++
Two examples
1
A01
Julia Prentice
Prentice, Julia
Julia
Prentice
University of Gothenburg
2
A01
Camilla Håkansson
Håkansson, Camilla
Camilla
Håkansson
University of Gothenburg
3
A01
Therese Lindström Tiedemann
Lindström Tiedemann, Therese
Therese
Lindström Tiedemann
University of Helsinki
4
A01
Ildikó Pilán
Pilán, Ildikó
Ildikó
Pilán
Norwegian Computing Center
5
A01
Elena Volodina
Volodina, Elena
Elena
Volodina
University of Gothenburg
01
This chapter describes and discusses the use of resources connected to Swedish FrameNet++ (SweFN++) in the context of the teaching and learning of language proficiency and grammatical analysis in Swedish. We illustrate the way in which different resources in the SweFN++ context can be useful for language pedagogy, by employing two examples, the Swedish Constructicon and a semantic role exercise on the intelligent computer assisted language learning (ICALL) platform Lärka. These resources make use of the infrastructure developed within SweFN++ in fundamentally different ways, which are discussed and compared. In addition, we discuss the possibilities for further development of the language pedagogical potential of SweFN++, both in relation to ICALL and to other types of resources and descriptive databases, like corpora, constructicons and framenets.
10
01
JB code
nlp.14.ind
331
333
3
Miscellaneous
20
01
Index
02
JBENJAMINS
John Benjamins Publishing Company
01
John Benjamins Publishing Company
Amsterdam/Philadelphia
NL
04
20211126
2021
John Benjamins B.V.
02
WORLD
08
765
gr
01
JB
1
John Benjamins Publishing Company
+31 20 6304747
+31 20 6739773
bookorder@benjamins.nl
01
https://benjamins.com
01
WORLD
US CA MX
21
77
18
01
02
JB
1
00
99.00
EUR
R
02
02
JB
1
00
104.94
EUR
R
01
JB
10
bebc
+44 1202 712 934
+44 1202 712 913
sales@bebc.co.uk
03
GB
21
18
02
02
JB
1
00
83.00
GBP
Z
01
JB
2
John Benjamins North America
+1 800 562-5666
+1 703 661-1501
benjamins@presswarehouse.com
01
https://benjamins.com
01
US CA MX
21
5
18
01
gen
02
JB
1
00
149.00
USD