Search results

1

Combined Machine-Learning Approach to PoS-Tagging of Middle English Corpora

100%

Karimov R.

Crossroads. A Journal of English Studies

|

2018

|

vol. 21

EN

This paper considers the problem of part-of-speech tagging in Middle English corpora (as well as historical corpora in general). Whereas PoS-tagging in general is now considered a solved problem for Modern English and is mainly achieved via hidden Markov models (HMM) and matrix-based word-to-vector conversions with every word in the dictionary being embedded into a single dimension, this approach relies on recurrent syntactic structures and context-free generative grammars and is therefore not applicable to older iterations of the English language due to irregular word order. As such, we believe that Middle English could be better handled by a morphographemic encoding and instance-based machine learning algorithms like SVM, random forests, kNN, etc. Using a moving-average method to generate multidimensional vectors giving a reliable numeric representation of character composition and sequences, we have achieved a precision and recall of 87.5% in classifying Middle English words by their part of speech while using a simplistic combined voting-based binary classifier. This result could be deemed satisfactory and encourages further research in the area.

2

Benamingen van dieren in de Nederlandse en in de Tsjechische vaste adjectivische vergelijkingen in de spiegel van de geschreven corpora

86%

Křížová K.

Neerlandica Wratislaviensia

|

2017

|

vol. 27

37-46

EN

nimal names or zooappellatives constitute an important part of the idioms and proverbs in the majority of natural languages. The Dutch idioms with an animal element were described from various perspectives by Kowalska-Szubert (1996). The Czech idioms with animal names were the subject of various studies carried out e.g. by Mrhačová (Mrhačová et al. 2000, Mrhačová-Kouptsevitch 2004). In this article we compare by the means of corpus research the use of animal names in the adjective-based similes in the current written Dutch and in the current written Czech. This research is based on the excerpta of the largest written corpora available for the Dutch and the Czech, namely the Corpus Contemporary Dutch and the Corpus Contemporary Czech SYN version 5.

3

The concept of violence and its immediate linguistic vicinity

58%

Dłutek A.

Społeczeństwo. Edukacja. Język

|

2016

|

vol. 4

243 - 254

PL

Przemoc stała się (lub raczej zawsze była) wszechobecnym zjawiskiem w niemal każdym obszarze współczesnego życia. Niniejszy artykuł jest próbą analizy bezpośredniego językowego otoczenia pojęcia violence / przemoc oraz umiejscowienia wyżej wspomnianego zjawiska w angielskim i polskim systemie językowym. Celem niniejszego badania jest zaprezentowanie jakie rodzaje domen źródłowych są wykorzystywane do konceptualizacji przemocy; jakie obrazy mentalne pomagają ludziom postrzegać, rozumieć (?), wyrażać, a nawet poskramiać przemoc. Poniższa analiza jest oparta na wybranych danych językowych z korpusów języka angielskiego i języka polskiego

EN

Violence has become (or possibly has always been) an omnipresent phenomenon in almost every area of the modern era life. This paper is an attempt to analyse the immediate linguistic vicinity of the notion of violence/przemoc to search for the location of the aforementioned phenomenon within the English and Polish linguistic systems. The aim of this research is to present what types of source domains are employed to conceptualise violence; what mental images help humans to perceive, understand (?), express, or even tame violence. The analysis is to be based on the selected corpus data of English and Polish

Refine search results

1 Crossroads. A Journal of English Studies

1 Neerlandica Wratislaviensia

1 Społeczeństwo. Edukacja. Język

1 2018

1 2017

1 2016

1 Dłutek A.

1 Karimov R.

1 Křížová K.

Combined Machine-Learning Approach to PoS-Tagging of Middle English Corpora

Benamingen van dieren in de Nederlandse en in de Tsjechische vaste adjectivische vergelijkingen in de spiegel van de geschreven corpora

The concept of violence and its immediate linguistic vicinity