• Contenu principal
  • Menu
OpenEdition Books
  • Accueil
  • Catalogue de 16075 livres
  • Éditeurs
  • Auteurs
  • Facebook
  • X
  • Partager
    • Facebook

    • X

    • Accueil
    • Catalogue de 16075 livres
    • Éditeurs
    • Auteurs
  • Ressources numériques en sciences humaines et sociales

    • OpenEdition
  • Nos plateformes

    • OpenEdition Books
    • OpenEdition Journals
    • Hypothèses
    • Calenda
  • Bibliothèques

    • OpenEdition Freemium
  • Suivez-nous

  • Lettre d’information
OpenEdition Search

Redirection vers OpenEdition Search.

À quel endroit ?
  • Accademia University Press
  • ›
  • Collana dell'Associazione Italiana di Li...
  • ›
  • Proceedings of the Seventh Italian Confe...
  • ›
  • Contributed Papers
  • ›
  • Suoidne-varra-bleahkka-mála-bihkka-senet...
  • Accademia University Press
  • Accademia University Press
    Accademia University Press
    Informations sur la couverture
    Table des matières
    Liens vers le livre
    Informations sur la couverture
    Table des matières
    Formats de lecture

    Plan

    Plan détaillé Texte intégral 1. Introduction 2. Background 3. Compounds in three NLP applications 4. Evaluation 5. Conclusion Bibliographie Notes de bas de page Auteurs

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    Ce livre est recensé par

    Précédent Suivant
    Table des matières

    Suoidne-varra-bleahkka-mála-bihkka-senet-dielku ‘hay-blood-ink-paint-tar-mustard-stain’ – Should compounds be lexicalized in NLP?

    Linda Wiechetek, Chiara Argese, Tommi A. Pirinen et Trond Trosterud

    p. 464-470

    Résumés

    Lexicalizing compounds, in addition to treating them dynamically, is a key element in giving us idiomatic translations and detecting compound errors. We present and evaluate an e-dictionary (NDS) and a grammar checker (GramDivvun) for North Sámi. We achieve a coverage of 98% for NDS-queries and of 96% for compound error detection in GramDivvun.

    La lessicalizzazione delle parole composte, in aggiunta a trattarle in maniera dinamica, è un elemento chiave per ottenere traduzioni idiomatiche e rilevare errori nelle stesse. Presentiamo e valutiamo un e-dizionario (NDS) e un correttore grammaticale (GramDivvun) per il Sami del Nord. Otteniamo una copertura del 98% per le ricerche in NDS e del 96% per il rilevamento di errori nelle parole composte in GramDivvun.

    Remerciements

    Thank you to Thomas Omma for doing the error corpus mark-up and for fun linguistic discussions, and to Lene Antonsen for digging in our corpus and helping to find just the right example.

    Texte intégral Bibliographie Notes de bas de page Auteurs

    Texte intégral

    1. Introduction

    1In this paper1, we discuss the use and necessity of the lexicalization of compounds – in addition to the dynamic approach to compounding – in two rule-based Natural Language Processing (NLP) applications, a grammar checker GramDivvun and an electronic dictionary NDS (short for Neahttadigisánit). We argue for a dual approach and support this view with an evaluation of these tools. For comparison, we also look at a third application, a corpus tool (Korp) for the North Sámi corpus SIKOR. SIKOR, the Sámi International KORpus, is the collection of texts in different Sámi languages compiled by UiT The Arctic University of Norway and the Norwegian Sámi Parliament.

    2In the past, we have mostly focussed on the dynamic approach to morphological analysis. This means that we have a lexicon with lemmata and stems, which in a finite-state manner are combined with inflectional and derivational affixes and other stems and modified when morpho-phonological processes apply. In this way the linguistic processes inflection, derivation and compounding are modelled in a dynamic way, i.e. by means of concatenation and composition as opposed to listing of all forms. Lexicalization, i.e. listing compounds or inflected word forms as such, is the alternative approach to the dynamic one. In addition to these two approaches we also use guessers for certain tasks, i.e. proper name guessing in morpho-syntactic parsing. Our approach is entirely rule-based and open source. Within our 20 year experience with language tools for the Sámi languages and other languages with complex morphology, we have achieved good results and produced reliable tools.

    3There are a number of approaches to error detection of a few errortypes for morphologically complex - although less complex than North Sámi - languages like Latvian (Deksne 2019) and Russian (Rozovskaya and Roth 2019). The Latvian neural network grammar checker focusses on preposition-postposition confusion, adjective-noun agreement, mood errors in verb forms, number and case in noun forms, definiteness of adjectives and missing commata. All of these error types have a good performance with precisions between 78% and 98.5%. Judging from their regular expressions to insert artificial errors, most of their error types seem to be fairly local errors that can be resolved based on bigrams.

    4The Russian system focusses on more advanced error types - case, number agreement, gender agreement, preposition and aspect. However, the results show that the system is still in its initial phase with low precision and recall for most error types (precision is between 22% and 56%, only gender agreement reaches 68%, and recall is significantly lower, between 9% and 36%). None of these approaches deals with compound error detection.

    5For neural network approaches, large corpora with error mark-up are necessary, which are not available for North Sámi. The error marked-up corpus contains 120 459 words, and when looking at specific error types – as in this case compound errors – the corpus is even smaller. The Russian system is based on an error-marked corpus of 200k words (deemed too small by its authors), the Latvian system works with artificial errors, an approach that can be problematic as it does not reflect real text errors.

    6In compounding, two or several words are combined to form a new word. In Sámi, Finnic and Germanic languages, compounding is a productive process and new compounds like in can be made on the fly.2 In Romance languages, these compounds typically correspond to prepositional constructions (ital. ‘la federa del cuscino del divano’).3

    (1) soffá|guoddá|olggoža (North Sámi)[sami]
    sofa|pute|trekk (Norwegian)
    ‘sofa pillow cover (English)’

    7The initial motivation for extensive lexicalization of compounds of North Sámi goes back to adapting the spellchecker to users’ needs, i.e. avoiding false alarms in Ávvir newspaper’s texts.

    8North Sámi is a Uralic language spoken in Norway, Sweden and Finland by approximately 25 700 speakers (Simons and Fennig 2018). It is a synthetic language, where the open parts of speech (PoS) – nouns, adjectives, etc. – inflect for case, person and number. The grammatical categories are expressed by a combination of suffixes and stem-internal processes affecting root vowels and consonants alike, making it perhaps the most fusional of all Uralic languages. In addition to compounding, inflection and derivation are common morphological processes in North Sámi.

    9North Sámi has seven morpho-syntactic cases, i.e. nominative (Nom.), genitive (Gen.), accusative (Acc.), illative (Ill.), locative (Loc.), comitative (Com.), and essive (Ess.). Case plays a more central role in Sámi than in preposition-based case languages, since here syntactic functions are identified based on case only. In addition, nouns can bear possessive suffixes. Verbs are inflected for person, number (singular, dual, plural), tense (present and past tense) and mood (indicative, conditional, and potential). Derivational processes (passive, causative, inchoative, diminutive, reflexive, to name only some of them) enhance the combinatory possibilities of each verb.

    10Table 1 illustrates that compounding in North Sámi is by no means restricted to noun noun combinations, but includes a number of other parts-of-speech (PoS) as well, also as heads.4

    Table 1: Compound types according to PoS; ‘|’ is used to mark word boundaries

    Type

    Example

    Gloss and translation

    N N

    láhka|rievdadusat

    law|change.pl ‘law changes’

    A.Attr N

    boahtte|áigi

    coming|time ‘future’

    Adv N

    dáppe|olmmoš

    here|person ‘person from here’

    Pron A

    iešguđet|lágan

    each|alike ‘different kinds of’

    Pron N

    eanet|lohku

    more|number ‘majority’

    Adv Pcle

    dušše|fal

    only|really ‘just’

    Adv V

    vuostái|váldojuvvo

    against|take.pass.3sg ‘received’

    PrfPrc N

    mearridan|fápmu

    decide.prfprc|power ‘authority’

    Num Num

    okta|nuppe|lohkái

    one|second|ten.ill ‘eleven’

    Num N

    1978|-láhka

    1978|-law ‘1978 law’

    Num A

    3|-ivnnat

    3|-colored ‘3-colored’

    Num A

    golmma|ivnnat

    three|colored ‘three colored’

    11In North Sámi, compounds are formed without a hyphen, except for those involving a proper noun, a digit, or an acronym like Davvi-Norgii ‘Northern Norway (Ill.)’, 3-juvllatsykkel ‘tricycle’, and ILO-álgoálbmotsoahpamuš ‘ILO-indigenous people agreement’ (Riektačállinrávvagat 2015, 46). There are a number of multiwords where a space is obligatory (albma ládje ‘properly’ and duollet dálle ‘sometimes’). Also genitive first compounds have an alternative interpretation when written apart, which makes error detection more difficult.

    2. Background

    12The North Sámi tools described in this article – NDS, Korp for SIKOR and GramDivvun (Wiechetek, n.d.) – all rely on the GiellaLT infrastructure (Moshagen, Pirinen, and Trosterud 2013), a technological framework for managing lexical data and building it into language technology applications including e-dictionaries and grammar checkers. All of them make use of a morphological analyzer, an FST (Finite-State Transducer) described in Pirinen , where word formation processes are moduled. Additionally, SIKOR and GramDivvun include a Constraint Grammar-based syntactic analysis. The full modular structure of the latter is described in Wiechetek .

    13The computational modeling of the language is done using finite-state morphology (Beesley and Karttunen 2003). The method of recognizing grammatical words as well as querying their grammatical information is based on looking up the words in an FST that contains the morphological dictionary of the language. There are two types of compounds in the language model: the ones that are stored in the lexicon as lexicalized units and the ones generated dynamically using a compounding model. Table 2 gives the statistics over the length of lexicalized compounds.5

    14Lexicalized four-element compounds are quite common in the noun lexicon, e.g. davvisámegielterminologiija ‘North Sámi language terminology’. Even six-element compounds (sáivačáhceguollevuostáiváldindilli ‘fresh water fish receive situation’) can be found.

    15The different types of North Sámi compounds in Table 1 are not treated equally in the morphological analyzer. Only the compounds in the first two lines can be derived dynamically. All others need to be lexicalized, i.e. listed in the lexicon, to receive a compound analysis. Numeral compounding is not treated dynamically in the FST. The dynamic compounds are generated from the dictionary by concatenating word forms (such as a genitive or nominative noun followed by other noun) and adding a compound tag +Cmp. The main dynamic compounds are (derived and non-derived) noun + noun pairs. One feature of the underlying technology is that the compounding mechanism is capable of modeling infinitely long compounds: for example nouns of any magnitude are compounds and modeled by the finite-state automaton. Since the compounding mechanism of an FST is very powerful, it also leads to ambiguity. When we allow arbitrary lexemes to combine to form compounds, some will overlap other existing lexemes, cf. ex. (2).

    (2) Davvi regiuvdna[regivudna]
    North region;direction.oven
    ‘The northern region’

    16Here, regiuvdna ‘region’ has a typical spelling error, o>u. The FST analyzes it as a misspelling of regiovdna ‘region’, but also as a compound with the elements regi, a common wrong form of regiija ‘direction’, and uvdna ‘oven’. While this example has only two possible analyses, twenty or more different analyses are not uncommon.

    Table 2 : Lexical compounds in the lexicon by the PoS of their head and the number of their roots

    Roots

    2

    3

    4

    5

    6+

    Pos

    N

    16 603

    1 048

    1 665

    86

    15

    Num

    408

    1 048

    42

    0

    4

    Prop

    11 680

    3 005

    115

    9

    1

    A

    3 854

    333

    13

    0

    0

    V

    478

    4

    0

    0

    9

    Adv

    896

    109

    1

    0

    0

    Adp

    152

    49

    0

    0

    0

    Conj

    3

    0

    0

    0

    0

    3. Compounds in three NLP applications

    17We present three applications, an e-dictionary, a corpus tool, and a grammar checker tool.

    3.1 An e-dictionary (NDS)

    18The North Sámi – Norwegian dictionary contains 25 000 lemmata and uses an FST. The e-dictionary was first implemented in 2013 with no use of relational databases (all linguistic resources are contained within static files and external command-line tools) (Ryan Johnson 2013). It is an intelligent dictionary in the sense that is able to look up North Sámi word forms and find lemmas via the FST. It also allows a tolerant mode, which accepts the letters acdnstz for áčđŋšt-ž in addition to their usual values. The e-dictionary can split compounds to provide the user with its elements as well as the whole compound if a translation is available. The lexicalization of compounds is important since the translation of the compound cannot necessarily be derived from the translation of its parts (Antonsen 2018, 54).

    19In the FST 90% of the 100 000 nouns, and in the dictionary 75% of the 25 000 nouns are compounds.

    3.2 A corpus tool

    20The web application and corpus search tool Korp (Borin, Forsberg, and Roxendal 2012) does not show the internal structure of compounds in SIKOR. Neither lexicalized, nor dynamic compounds are searchable as either the lexicalized analysis is picked instead of the dynamic one or – in the case of compounds that are not listed in the lexicon – a lexicalized compound is made by the preprocessor. This is a problem inherent in the implementation of the tool. However, when searching for the compound tag used in the FST (+Cmp), there are 94 658 results. The reason for that is that the first element in split compounds in coordination receives a specific compound tag (+Cmp/SplitR) as well.

    21Table 3 shows the statistics for compounds in SIKOR.6 The results are obtained using the scripts that can be found in GiellaLT.7 According to our analyses 8.6% of the tokens in corpus are compounds, and 86% are lexicalized. The rest is mainly composed of 2-elements compounds (13.4%) and a very small part of 4-7 elements (0.5%).

    22Many of the longer compounds in SIKOR are quite creative and are hyphenated as the one in ex. (3).

    (3) suoidne-varra-bleahkka-mála-bihkka-senet-dielku mu báiddis lei dušše lihkohisvuohta.[productivecompoundsikor]
    hay-blood-ink-paint-tar-mustard-stain my shirt.loc was only mishap
    ‘The hay-blood-ink-paint-tar-mustard-stain on my shirt was only a mishap.’

    Table 3: Compound types in SIKOR by the PoS of their head and the number of their root (amounts given in percentage

    Roots

    2

    3

    4

    5

    6/7

    Pos

    N

    96.2

    98.9

    89.2

    80

    66.7

    Prop

    3.8

    1.1

    10.8

    20

    33.3

    23The current public version of the Sámi corpus SIKOR (SIKOR 2018) (in Korp) consists of 32.2 million words. It was analyzed with a preprocessor that does not distinguish between lexicalized and dynamic compounds. The (non-public) version of SIKOR used in this article makes this distinction, though, as will future versions in Korp.

    24A search for compound tags only returns split compounds, i.e. the first coordinated hyphenated nominal element, cf. in ex. , i.e. riddo- ‘coast-’.

    (4) riddo- ja vuotnaguovlluin[split]
    coast- and fjordregion.loc.pl
    ‘in coastal and fjord regions’

    25GiellaLT has already produced a solution, i.e. a tag for cohorts with a dynamic compound (<with-dynamic-compound>) added by a Constraint Grammar module. However, this tag does not provide any information about the number of elements and the beginning and ending of each element.

    3.3 A grammar checker (GramDivvun)

    26GramDivvun, the North Sámi grammar checker (Wiechetek et al. 2019) takes input from the FST to a number of other modules, the core of which are several Constraint Grammar modules. Constraint Grammar is a rule-based formalism for writing disambiguation and syntactic annotation grammars (Karlsson 1990; Karlsson et al. 1995). In our work, we use the free open source implementation VISLCG-3 (Bick and Didriksen 2015). All components are compiled and built using the GiellaLT infrastructure (Moshagen, Pirinen, and Trosterud 2013).

    27Lexicalization of compounds is relevant for grammar checking within compound error detection. One common error that cannot be resolved by a spellchecker is the spelling of compounds as two or more words. GramDivvun performs this type of error detection as part of the tokenization. The tokenization is done in two steps. In the first step potential compounds are tokenized ambiguously (either as one or as two words, the first of which is accompanied by an errortag). In the second step, a Constraint Grammar module8 selects or removes the error reading. Two conditions need to be met to find the compound error: 1. the compound needs to be lexicalized, and 2. the syntactic context needs to support the compound reading.

    28The syntactic context is specified in hand-written Constraint Grammar rules. The REMOVE-rule below removes the compound error reading (identified by the tag Err/SpaceCmp) if the head is a 3rd person singular verb (cf. l.2) and the first element of the potential compound is a noun in nominative case (cf. l.3). The context condition further specifies that there should be a finite verb (VFIN) somewhere in the sentence (cf. l.4) for the rule to apply.

    REMOVE (Err/SpaceCmp)
    (0/0 (V Sg3))
    (0/1 (N Sg Nom))
    (*0 VFIN);

    29All possible compounds written apart are considered to be errors by default, unless the lexicon specifies a two or several word compound or a syntactic rule removes the error reading. There are numerous syntactic contexts where the potential parts of compounds make perfectly sense. In the case of noun-noun compounds, the second element can for example be a simple adverbial, as in ex. (5). The second element can be homonymous with another PoS, it can be a finite verb or an infinitive.

    (5) son lea boarráseamus mánná joavkkus.[manna]
    s/he is oldest child group.loc
    ‘s/he is the oldest child in the group.’

    4. Evaluation

    30We evaluate the e-dictionary (coverage) and the grammar checker (precision, recall) for compounding (errors). The corpus search tool does not exhibit compounding information and is therefore not evaluated.

    4.1 An e-dictionary (NDS)

    31We analyzed the logs for NDS (Neahttadigisánit) for 2019, and found that 12.6% of the types in the user queries are compounds. The results are obtained using the scripts that can be found in GiellaLT. The amount of lexicalized compounds in the logs (72.1%) is approximately the same as in the dictionary, where it is 75% (cf. Section 3.1 above). As much as 98% of the compound queries get a translation, either a lexicalized one or of its parts. Thus dynamic compounding contributes with a substantial improvement to dictionary coverage. If the alternatives are “getting no help from the dictionary” and “getting help to translate the parts” then the latter is to be preferred, even though the correct translation would be different from just joining the parts. For example, the compound word ruhtahearrá ‘rich man’ is not lexicalized in NDS but it does get a translation of its parts ruhta ‘money’ and hearrá ‘man’, which can help the user to understand the meaning of the compound word itself.

    32Most of the non lexicalized compounds are composed of 2 elements (96% in the logs and 93% in the entries). When analyzing the entries in the dictionary, we found that 24.8% are compounds and of those 97.6% are lexicalized. Table 4 shows PoS for compounds in NDS logs and entries.

    Table 4: Compounds according to the number of their parts and PoS in NDS logs and entries (L=lexicalized)

    Logs

    Entries

    Roots

    L

    2

    3

    4

    L

    2

    3

    4

    Pos

    N

    90

    87

    85

    100

    86

    87

    82

    0

    A

    3

    0

    0

    0

    2

    0

    0

    0

    Prop

    3

    0

    0

    0

    12

    4

    0

    0

    V

    2

    13

    14

    0

    0

    8

    18

    0

    Adv

    1

    0

    0

    0

    0

    0

    0

    0

    4.2 A grammar checker (GramDivvun)

    33We evaluate error detection for syntactic compound errors (i.e. words that are written apart and should be a compound) in GramDivvun in two ways. Firstly, we compare last year’s results in Wiechetek  with a newer version of GramDivvun, from now on referred to as the Nodalida-corpus. Last year’s results are based on version r183544 (Wiechetek, Brubeck Unhammer, and Nørstebø Moshagen 2019)9. The new results are based on version r2851010 of GramDivvun.

    34However, as the focus in the last analysis was a different one, i.e. we evaluated other error types as well, we ran a second evaluation on a 2 363 word-corpus11 specifically made to test compound error detection, i.e. every sentence contains a potential compound. These sentences are hand-selected from SIKOR.

    35The results of the evaluation are presented in Table 5. We can see that precision has gone significantly up, i.e. the average precision is 95.5%. However, the recall has gone down to average 46%. We are investigating the reasons for that. But in general, a high precision is desirable in grammar checking, even at the cost of a lower recall.

    36The results of the evaluation of GramDivvun compound grammar checking are shown in Table 5.

    Table 5: Measures for GramDivvun (TP/FP= true/false positives, FN=false negatives)

    Measure

    (2019)

    (2020)

    Nodalida Corpus

    Compound

    corpus

    Precision

    75.0%

    93.1%

    98.0%

    Recall

    72.9%

    43.2%

    48.5%

    F1-Score

    73.9

    59.0

    64.9

    TP

    51

    54

    50

    FP

    17

    4

    1

    FN

    19

    67

    53

    37False negatives are typically due to the lack of lexicalization. Many of those are proper noun combinations which are very productive, e.g. Murmánska-aviisa ‘Murmansk newspaper’, Várggát-festiválas ‘at the Várggát festival’, km-galba ‘km sign’ and Divttasvuotna-regiovnna ‘Divttasvuotna region’.

    38Other reasons are certain (unlikely) analyses of especially the first element, e.g. that generally suggest a syntactic construction rather than a compound as in ex. (6). Here the first element duorastat ‘Thursday’ has a finite verb reading as well.

    (6) dán duorastat veaiggi.[duorastat]
    this.gen Thursday twilight.gen
    ‘this Thursday evening’

    39The false positive is due to an error in the recognition of the span of the target. In ex. (7), lulli sámi guvlui is concatenated, but it should only be lulli sámi.

    (7) dohko lulli sámi guvlui.[lullisami]
    thither South Sámi area.ill
    ‘thither towards the South Sámi area.’

    5. Conclusion

    40We have shown that the lexicalization of compounds – in addition to their dynamic treatment – is useful and necessary for two language applications for North Sámi, an e-dictionary (NDS) and a grammar checker (GramDivvun). The evaluation of NDS shows that we get a good coverage: 98% of the compounds logged do get a translation and 72% are lexicalized in the FST. The evaluation of GramDivvun has shown that we manage to identify compound errors with a precision of 98% and a recall of 49% utilising a combination of information from the lexicon and syntax.

    41We conclude that there are perfectly good reasons for lexicalizing compounds, i.e. providing idiomatic translations for when it cannot be derived from the parts, and to support compound grammar checking. At the same time, lexicalization can dissimulate word formation information in corpus tools. This can be resolved and we have already implemented a solution in Constraint Grammar to make the information available in a future version of the corpus tool. As dynamic compounding is limited to few PoS at the moment, in the future we want to investigate and model compounding of other PoS (in the FST). Also experiments with neural network approaches and a comparison of the results to our rule-based grammar checker could be an interesting future project.

    Bibliographie

    Des DOI sont automatiquement ajoutés aux références bibliographiques par Bilbo, l’outil d’annotation bibliographique d’OpenEdition. Ces références bibliographiques peuvent être téléchargées dans les formats APA, Chicago et MLA.

    Format

    • APA
    • Chicago
    • MLA
    Deksne, D. (2019). Bidirectional LSTM Tagger for Latvian Grammatical Error Detection. Springer International Publishing. https://doi.org/10.1007/978-3-030-27947-9_5
    Proceedings of the 13th conference on Computational linguistics -. (1990). Presented at the the 13th conference. https://doi.org/10.3115/991146
    Deksne, Daiga. “Bidirectional LSTM Tagger for Latvian Grammatical Error Detection”. Text, Speech, and Dialogue. Springer International Publishing, 2019. doi:10.1007/978-3-030-27947-9_5.
    “Proceedings of the 13th Conference on Computational Linguistics -”. []. Association for Computational Linguistics, 1990. doi:10.3115/991146.
    Deksne, Daiga. “Bidirectional LSTM Tagger for Latvian Grammatical Error Detection”. Text, Speech, and Dialogue, Springer International Publishing, 2019, pp. 58-68. Crossref, https://doi.org/10.1007/978-3-030-27947-9_5.
    Proceedings of the 13th Conference on Computational Linguistics -. [], Association for Computational Linguistics, 1990. Crossref, https://doi.org/10.3115/991146.

    Cette bibliographie a été enrichie de toutes les références bibliographiques automatiquement générées par Bilbo en utilisant Crossref.

    Lene Antonsen. 2018. “Sámegielaid Modelleren – Huksen Ja Heiveheapmi Duohta Giellamáilbmái. [Modeling Saami Languages. Construction and Adaptation to Real-World Linguistic Issues].” PhD thesis, Tromsø: UiT The Arctic University of Norway. https://hdl.handle.net/10037/12884.

    Kenneth R.Beesley and Lauri Karttunen. 2003. Finite State Morphology. CSLI Studies in Computational Linguistics. Stanford: CSLI Publications.

    Eckhard Bick and Tino Didriksen. 2015. “CG-3 – Beyond Classical Constraint Grammar.” In Proceedings of the 20th Nordic Conference of Computational Linguistics (Nodalida 2015), edited by Beáta Megyesi, 31–39. Linköping University Electronic Press, Linköpings universitet.

    Lars Borin, Markus Forsberg, and Johan Roxendal. 2012. “Korp – the Corpus Infrastructure of Språkbanken.” In Proceedings of the 8th International Conference on Language Resources and Evaluation (Lrec 2012), edited by Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Mehmet Uğur Doğan, Bente Maegaard, Joseph Mariani, Jan Odijk, and Stelios Piperidis. European Language Resources Association (ELRA).

    Daiga Deksne. 2019. “Bidirectional Lstm Tagger for Latvian Grammatical Error Detection.” In Ekštein K. (Eds) Text, Speech, and Dialogue. TSD 2019. Lecture Notes in Computer Science, Vol 11697. Springer. https://doi.org/10.1007/978-3-030-27947-9_5.

    10.1007/978-3-030-27947-9_5 :

    Fred Karlsson. 1990. “Constraint Grammar as a Framework for Parsing Running Text.” In Proceedings of the 13th Conference on Computational Linguistics (Coling 1990), edited by Hans Karlgren, 3:168–73. Helsinki, Finland: Association for Computational Linguistics.

    10.3115/991146 :

    Fred Karlsson, Atro Voutilainen, Juha Heikkilä, and Arto Anttila. 1995. Constraint Grammar: A Language-Independent System for Parsing Unrestricted Text. Berlin: Mouton de Gruyter.

    Sjur N. Moshagen, Tommi A. Pirinen, and Trond Trosterud. 2013. “Building an Open-Source Development Infrastructure for Language Technology Projects.” In NODALIDA.

    Riektačállinrávvagat. 2015. “Riektačállinrávvagat.” Sámedikki giellaossodat/Sámedikki oahpahusossodat, Guovdageaidnu. https://www.sametinget.no/content/download/870/13825 (Accessed 2017-11-3).

    Alla Rozovskaya and Dan Roth. 2019. “Grammar Error Correction in Morphologically Rich Languages: The Case of Russian.” In Transactions of the Association for Computational Linguistics, Vol. 7, Pp. 1–17, 2019. https://www.aclweb.org/anthology/Q19-1001.pdf.

    Ryan Johnson, Trond Trosterud, Lene Antonsen. 2013. “Using Finite State Transducers for Making Efficient Reading Comprehension Dictionaries.” In Proceedings of the 19th Nordic Conference of Computational Linguistics (Nodalida 2013). Proceedings Series 16: 59–71.

    SIKOR. 2018. “SIKOR Uit Norgga árktalaš Universitehta Ja Norgga Sámedikki Sámi Teakstačoakkáldat, Veršuvdna 06.11.2018.” http://gtweb.uit.no/korp.

    Gary F. Simons and Charles D. Fennig, eds. 2018. Ethnologue: Languages of the World. Twenty-first. Dallas, Texas: SIL International. http://www.ethnologue.com (Accessed 2018-10-09).

    Linda Wiechetek. n.d. “Constraint Grammar Based Correction of Grammatical Errors for North Sámi.” In Proceedings of the Workshop on Language Technology for Normalisation of Less-Resourced Languages (Saltmil 8/Aflat 2012), edited by G. De Pauw, G-M de Schryver, M. L. Forcada, K. Sarasola, F. M. Tyers, and P. W. Wagacha, 35–40. Istanbul, Turkey: European Language Resources Association (ELRA).

    Linda Wiechetek, Kevin Brubeck Unhammer, and Sjur Nørstebø Moshagen. 2019. “Seeing more than whitespace – Tokenisation and disambiguation in a North Sámi grammar checker.” In Proceedings of the Third Workshop on the Use of Computational Methods in the Study of Endangered Languages, 46–55. https://www.aclweb.org/anthology/W19-6007.

    Linda Wiechetek, Sjur Nørstebø Moshagen, Børre Gaup, and Thomas Omma. 2019. “Many Shades of Grammar Checking – Launching a Constraint Grammar Tool for North Sámi.” In Proceedings of the Nodalida 2019 Workshop on Constraint Grammar - Methods, Tools and Applications, 35–44. NEALT Proceedings Series 33:8.

    Notes de bas de page

    1 Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

    2 To avoid confusion with hyphenated compounds, “|” is used to mark word boundaries in compounds

    3 Although there are a number of real compounds in Italian, such as fruttivendolo, as well.

    4 The following abbreviations are used: N=noun, V=verb, A=adjective, Attr=attributive, Adv=adverb, Pron=pronoun, Pcle=particle, PrfPrc=past participle, Num=numeral, Prop=propernoun.

    5 The table is based on the dictionary size at the time of the writing (September 2020); it is actively developed daily. Further abbreviations are Adp=adposition, Conj=conjunction.

    6 The search was done on 2020-09-07.

    7 [footnote_scripts]https://github.com/giellalt/conf-clicit2021

    8 https://github.com/giellalt/lang-sme/blob/3a43911929458fd39da309ed23178bf5dbd04bcd/tools/tokenisers/mwe-dis.cg3

    9 https://github.com/giellalt/lang-sme/releases/tag/nodalida-2018 on 2019-09-26

    10 https://github.com/giellalt/lang-sme/releases/tag/clicit on 2020-09-07

    11 http://gtsvn.uit.no/freecorpus/orig/sme/odda_mahppa/compounds.correct.txt

    Auteurs

    • Linda Wiechetek

      Divvun & Giellatekno, UiT Norgga árktalaš universitehta – linda.wiechetek@uit.no

    • Chiara Argese

      Divvun & Giellatekno, UiT Norgga árktalaš universitehta – chiara.argese@uit.no

    • Tommi A. Pirinen

      Divvun & Giellatekno, UiT Norgga árktalaš universitehta – tommi.pirinen@uit.no

    • Trond Trosterud

      Divvun & Giellatekno, UiT Norgga árktalaš universitehta – trond.trosterud@uit.no

    Précédent Suivant
    Table des matières

    Le texte seul est utilisable sous licence Licence OpenEdition Books. Les autres éléments (illustrations, fichiers annexes importés) sont « Tous droits réservés », sauf mention contraire.

    Voir plus de livres
    Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015

    Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015

    3-4 December 2015, Trento

    Cristina Bosco, Sara Tonelli et Fabio Massimo Zanzotto (dir.)

    2015

    Proceedings of the Third Italian Conference on Computational Linguistics CLiC-it 2016

    Proceedings of the Third Italian Conference on Computational Linguistics CLiC-it 2016

    5-6 December 2016, Napoli

    Anna Corazza, Simonetta Montemagni et Giovanni Semeraro (dir.)

    2016

    EVALITA. Evaluation of NLP and Speech Tools for Italian

    EVALITA. Evaluation of NLP and Speech Tools for Italian

    Proceedings of the Final Workshop 7 December 2016, Naples

    Pierpaolo Basile, Franco Cutugno, Malvina Nissim et al. (dir.)

    2016

    Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017

    Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017

    11-12 December 2017, Rome

    Roberto Basili, Malvina Nissim et Giorgio Satta (dir.)

    2017

    Proceedings of the Fifth Italian Conference on Computational Linguistics CLiC-it 2018

    Proceedings of the Fifth Italian Conference on Computational Linguistics CLiC-it 2018

    10-12 December 2018, Torino

    Elena Cabrio, Alessandro Mazzei et Fabio Tamburini (dir.)

    2018

    EVALITA Evaluation of NLP and Speech Tools for Italian

    EVALITA Evaluation of NLP and Speech Tools for Italian

    Proceedings of the Final Workshop 12-13 December 2018, Naples

    Tommaso Caselli, Nicole Novielli, Viviana Patti et al. (dir.)

    2018

    EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020

    EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020

    Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian Final Workshop

    Valerio Basile, Danilo Croce, Maria Maro et al. (dir.)

    2020

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    Bologna, Italy, March 1-3, 2021

    Felice Dell'Orletta, Johanna Monti et Fabio Tamburini (dir.)

    2020

    Proceedings of the Eighth Italian Conference on Computational Linguistics CliC-it 2021

    Proceedings of the Eighth Italian Conference on Computational Linguistics CliC-it 2021

    Milan, Italy, 26-28 January, 2022

    Elisabetta Fersini, Marco Passarotti et Viviana Patti (dir.)

    2022

    Voir plus de livres
    1 / 9
    Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015

    Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015

    3-4 December 2015, Trento

    Cristina Bosco, Sara Tonelli et Fabio Massimo Zanzotto (dir.)

    2015

    Proceedings of the Third Italian Conference on Computational Linguistics CLiC-it 2016

    Proceedings of the Third Italian Conference on Computational Linguistics CLiC-it 2016

    5-6 December 2016, Napoli

    Anna Corazza, Simonetta Montemagni et Giovanni Semeraro (dir.)

    2016

    EVALITA. Evaluation of NLP and Speech Tools for Italian

    EVALITA. Evaluation of NLP and Speech Tools for Italian

    Proceedings of the Final Workshop 7 December 2016, Naples

    Pierpaolo Basile, Franco Cutugno, Malvina Nissim et al. (dir.)

    2016

    Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017

    Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017

    11-12 December 2017, Rome

    Roberto Basili, Malvina Nissim et Giorgio Satta (dir.)

    2017

    Proceedings of the Fifth Italian Conference on Computational Linguistics CLiC-it 2018

    Proceedings of the Fifth Italian Conference on Computational Linguistics CLiC-it 2018

    10-12 December 2018, Torino

    Elena Cabrio, Alessandro Mazzei et Fabio Tamburini (dir.)

    2018

    EVALITA Evaluation of NLP and Speech Tools for Italian

    EVALITA Evaluation of NLP and Speech Tools for Italian

    Proceedings of the Final Workshop 12-13 December 2018, Naples

    Tommaso Caselli, Nicole Novielli, Viviana Patti et al. (dir.)

    2018

    EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020

    EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020

    Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian Final Workshop

    Valerio Basile, Danilo Croce, Maria Maro et al. (dir.)

    2020

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    Bologna, Italy, March 1-3, 2021

    Felice Dell'Orletta, Johanna Monti et Fabio Tamburini (dir.)

    2020

    Proceedings of the Eighth Italian Conference on Computational Linguistics CliC-it 2021

    Proceedings of the Eighth Italian Conference on Computational Linguistics CliC-it 2021

    Milan, Italy, 26-28 January, 2022

    Elisabetta Fersini, Marco Passarotti et Viviana Patti (dir.)

    2022

    Accès ouvert

    Accès ouvert

    ePub

    PDF

    PDF du chapitre

    1 Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

    2 To avoid confusion with hyphenated compounds, “|” is used to mark word boundaries in compounds

    3 Although there are a number of real compounds in Italian, such as fruttivendolo, as well.

    4 The following abbreviations are used: N=noun, V=verb, A=adjective, Attr=attributive, Adv=adverb, Pron=pronoun, Pcle=particle, PrfPrc=past participle, Num=numeral, Prop=propernoun.

    5 The table is based on the dictionary size at the time of the writing (September 2020); it is actively developed daily. Further abbreviations are Adp=adposition, Conj=conjunction.

    6 The search was done on 2020-09-07.

    7 [footnote_scripts]https://github.com/giellalt/conf-clicit2021

    8 https://github.com/giellalt/lang-sme/blob/3a43911929458fd39da309ed23178bf5dbd04bcd/tools/tokenisers/mwe-dis.cg3

    9 https://github.com/giellalt/lang-sme/releases/tag/nodalida-2018 on 2019-09-26

    10 https://github.com/giellalt/lang-sme/releases/tag/clicit on 2020-09-07

    11 http://gtsvn.uit.no/freecorpus/orig/sme/odda_mahppa/compounds.correct.txt

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    X Facebook Email

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    Vous pouvez vous connecter à votre bibliothèque à l’adresse suivante : https://freemium.openedition.org/oebooks

    Suggérer l’acquisition à votre bibliothèque

    Si vous avez des questions, vous pouvez nous écrire à access[at]openedition.org

    Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020

    Vérifiez si votre bibliothèque a déjà acquis ce livre : authentifiez-vous à OpenEdition Freemium for Books.

    Vous pouvez suggérer à votre bibliothèque d’acquérir un ou plusieurs livres publiés sur OpenEdition Books. N’hésitez pas à lui indiquer nos coordonnées : access[at]openedition.org

    Vous pouvez également nous indiquer, à l’aide du formulaire suivant, les coordonnées de votre bibliothèque afin que nous la contactions pour lui suggérer l’achat de ce livre. Les champs suivis de (*) sont obligatoires.

    Veuillez, s’il vous plaît, remplir tous les champs.

    La syntaxe de l’email est incorrecte.

    Référence numérique du chapitre

    Format

    Wiechetek, L., Argese, C., Pirinen, T. A., & Trosterud, T. (2020). Suoidne-varra-bleahkka-mála-bihkka-senet-dielku ‘hay-blood-ink-paint-tar-mustard-stain’ – Should compounds be lexicalized in NLP?. In F. Dell’Orletta, J. Monti, & F. Tamburini (éds.), Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020. Torino: Accademia University Press. https://doi.org/10.4000/books.aaccademia.8979
    Wiechetek, Linda, Chiara Argese, Tommi A. Pirinen, et Trond Trosterud. « Suoidne-Varra-Bleahkka-mála-Bihkka-Senet-Dielku ‘hay-Blood-Ink-Paint-Tar-Mustard-stain’ – Should Compounds Be Lexicalized in NLP? ». In Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-It 2020, édité par Felice Dell’Orletta, Johanna Monti, et Fabio Tamburini. Torino: Accademia University Press, 2020. doi:10.4000/books.aaccademia.8979.
    Wiechetek, Linda, et al. « Suoidne-Varra-Bleahkka-mála-Bihkka-Senet-Dielku ‘hay-Blood-Ink-Paint-Tar-Mustard-stain’ – Should Compounds Be Lexicalized in NLP? ». Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-It 2020, édité par Felice Dell’Orletta et al., Accademia University Press, 2020, https://doi.org/10.4000/books.aaccademia.8979.

    Référence numérique du livre

    Format

    Dell’Orletta, F., Monti, J., & Tamburini, F. (éds.). (2020). Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020. Torino: Accademia University Press. https://doi.org/10.4000/books.aaccademia.8203
    Dell’Orletta, Felice, Johanna Monti, et Fabio Tamburini, éd. Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-It 2020. Torino: Accademia University Press, 2020. doi:10.4000/books.aaccademia.8203.
    Dell’Orletta, Felice, et al., éditeurs. Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-It 2020. Accademia University Press, 2020, https://doi.org/10.4000/books.aaccademia.8203.
    Compatible avec Zotero Zotero

    1 / 3

    Accademia University Press

    Accademia University Press

    • Plan du site
    • Se connecter

    Suivez-nous

    • Facebook
    • Flux RSS

    URL : http://www.aaccademia.it/

    Email : info@aaccademia.it

    Adresse :

    Accademia University Press

    Via Carlo Alberto 55

    I‐10123

    Torino

    Italia

    OpenEdition
    • Candidater à OpenEdition Books
    • Connaître le programme OpenEdition Freemium
    • Commander des livres
    • S’abonner à la lettre d’OpenEdition
    • CGU d’OpenEdition Books
    • Accessibilité : partiellement conforme
    • Données personnelles
    • Gestion des cookies
    • Système de signalement