Suchergebnisse

In our paper we present a corpus of transcribed Lithuanian parliamentary speeches. The corpus is prepared in a specific format, appropriate for different authorship identification tasks. The corpus consists of approximately 111 thousand texts (24 million words). Each text matches one parliamentary speech produced during an ordinary session from the period of 7 parliamentary terms starting on March 10, 1990 and ending on December 23, 2013. The texts are grouped into 147 categories corresponding to individual authors, therefore they can be used for authorship attribution tasks; besides, these texts are also grouped according to age, gender and political views, therefore they are also suitable for author profiling tasks. Whereas short texts complicate recognition of author speaking style and are ambiguous in relation to the style of other authors, we incorporated only texts containing not less than 100 words into the corpus. In order to make each category as comprehensive and representative as possible, we included only those authors, who produced speeches at least 200 times. All the texts are lemmatized, morphologically and syntactically annotated, tokenized into the character n-grams. The statistical information of the corpus is also available. We have also demonstrated that the created corpus can be effectively used in authorship attribution and author profiling tasks with supervised machine learning methods. The corpus structure also allows using it with unsupervised machine learning methods and can be used for creation of rule-based methods, as well as in different linguistic analyses.

In our paper we present a corpus of transcribed Lithuanian parliamentary speeches. The corpus is prepared in a specific format, appropriate for different authorship identification tasks. The corpus consists of approximately 111 thousand texts (24 million words). Each text matches one parliamentary speech produced during an ordinary session from the period of 7 parliamentary terms starting on March 10, 1990 and ending on December 23, 2013. The texts are grouped into 147 categories corresponding to individual authors, therefore they can be used for authorship attribution tasks; besides, these texts are also grouped according to age, gender and political views, therefore they are also suitable for author profiling tasks. Whereas short texts complicate recognition of author speaking style and are ambiguous in relation to the style of other authors, we incorporated only texts containing not less than 100 words into the corpus. In order to make each category as comprehensive and representative as possible, we included only those authors, who produced speeches at least 200 times. All the texts are lemmatized, morphologically and syntactically annotated, tokenized into the character n-grams. The statistical information of the corpus is also available. We have also demonstrated that the created corpus can be effectively used in authorship attribution and author profiling tasks with supervised machine learning methods. The corpus structure also allows using it with unsupervised machine learning methods and can be used for creation of rule-based methods, as well as in different linguistic analyses.

In our paper we present a corpus of transcribed Lithuanian parliamentary speeches. The corpus is prepared in a specific format, appropriate for different authorship identification tasks. The corpus consists of approximately 111 thousand texts (24 million words). Each text matches one parliamentary speech produced during an ordinary session from the period of 7 parliamentary terms starting on March 10, 1990 and ending on December 23, 2013. The texts are grouped into 147 categories corresponding to individual authors, therefore they can be used for authorship attribution tasks; besides, these texts are also grouped according to age, gender and political views, therefore they are also suitable for author profiling tasks. Whereas short texts complicate recognition of author speaking style and are ambiguous in relation to the style of other authors, we incorporated only texts containing not less than 100 words into the corpus. In order to make each category as comprehensive and representative as possible, we included only those authors, who produced speeches at least 200 times. All the texts are lemmatized, morphologically and syntactically annotated, tokenized into the character n-grams. The statistical information of the corpus is also available. We have also demonstrated that the created corpus can be effectively used in authorship attribution and author profiling tasks with supervised machine learning methods. The corpus structure also allows using it with unsupervised machine learning methods and can be used for creation of rule-based methods, as well as in different linguistic analyses.

Many studies reveal that unchangeable static variables, such as prior offending history and membership in high-risk demographic subgroups, consistently predict recidivism. Recent risk assessment research focuses on dynamic attributes — attitudes, values, and interpersonal skills that are modified by new experiences and, thus, may change during the residential stay.

Many studies reveal that unchangeable static variables, such as prior offending history and membership in high-risk demographic subgroups, consistently predict recidivism. Recent risk assessment research focuses on dynamic attributes — attitudes, values, and interpersonal skills that are modified by new experiences and, thus, may change during the residential stay.

In our paper we present a corpus of transcribed Lithuanian parliamentary speeches. The corpus is prepared in a specific format, appropriate for different authorship identification tasks. The corpus consists of approximately 111 thousand texts (24 million words). Each text matches one parliamentary speech produced during an ordinary session from the period of 7 parliamentary terms starting on March 10, 1990 and ending on December 23, 2013. The texts are grouped into 147 categories corresponding to individual authors, therefore they can be used for authorship attribution tasks; besides, these texts are also grouped according to age, gender and political views, therefore they are also suitable for author profiling tasks. Whereas short texts complicate recognition of author speaking style and are ambiguous in relation to the style of other authors, we incorporated only texts containing not less than 100 words into the corpus. In order to make each category as comprehensive and representative as possible, we included only those authors, who produced speeches at least 200 times. All the texts are lemmatized, morphologically and syntactically annotated, tokenized into the character n-grams. The statistical information of the corpus is also available. We have also demonstrated that the created corpus can be effectively used in authorship attribution and author profiling tasks with supervised machine learning methods. The corpus structure also allows using it with unsupervised machine learning methods and can be used for creation of rule-based methods, as well as in different linguistic analyses. ; Straipsnyje pristatome Seimo posėdžių stenogramų tekstyną, parengtą specialiu formatu, tinkančiu įvairiems autorystės nustatymo tyrimams. Tekstyną sudaro apie 111 tūkstančių tekstų (24 milijonai žodžių), kurių kiekvienas atitinka vieną parlamentaro pasisakymą eilinės sesijos posėdžio metu bei apima 7 Lietuvos Respublikos Seimo kadencijas: nuo 1990 metų kovo 10 dienos iki 2013 metų gruodžio 23 dienos. Pasisakymų tekstai sugrupuoti pagal autorius į 147 grupes, todėl tinka individualių autorių autorystės nustatymo tyrimams; jie suskirstyti pagal autorių amžiaus grupes, lytį ar politines pažiūras, todėl tinka autorių profilio sudarymo tyrimams. Trumpas tekstas neatskleidžia jo autoriaus kalbėjimo stiliaus, yra daugiaprasmiškas kitų autorių atžvilgiu, todėl į tekstyną įtraukti ne trumpesni nei 100 žodžių tekstai. Kiekvieną autorių atitinkantis tekstų rinkinys turi būti išsamus ir reprezentatyvus, todėl įtraukti autoriai, pasisakę ne mažiau kaip 200 kartų. Visi tekstai automatiškai lemuoti, morfologiškai bei sintaksiškai anotuoti, suskaidyti simbolių n-gramomis, surinkta statistinė informacija. Straipsnyje pademonstruota, kaip sukurtas tekstynas gali būti panaudotas individualių autorių autorystės nustatymo bei autorių profilio sudarymo tyrimams, naudojant prižiūrimo mašininio mokymo metodus. Tekstyno struktūra taip pat leidžia taikyti neprižiūrimo Ligita Šarkutė Viešosios politikos ir administravimo institutas Kauno technologijos universitetas K. Donelaičio g. 20-217 LT-44239 Kaunas, Lietuva El. paštas: ligita.sarkute@ktu.lt 28 mašininio mokymo metodus, patogi taisyklinių-loginių metodų kūrimui bei įvairioms lingvistinėms analizėms.

Historical cabinet protocols are a useful resource which enable historians to identify the opinions expressed by politicians on different subjects and at different points of time. While cabinet protocols are often available in digitized form, so far the only method to access their information content is by keyword-based search, which often returns sub-optimal results. We present a method for enriching German cabinet protocols with information about the originators of statements. This requires automatic speaker attribution. In order to avoid costly manual annotation of training data, we design a rule-based system which exploits morpho-syntactic cues. Unlike many other approaches, our method can also deal with cases in which the speaker is not explicitly identified in the sentence itself. This is an important capability as 45% of all sentences in the data constitute reported speech whose speakers are not explicitly marked. Our system is able to detect implicit speakers by taking into account signals of speaker continuity. We show that such a system obtains good results, especially with respect to recall which is particularly important for information access.