![]() Two other such devices are syneresis, that operates similarly but within the word, and dieresis, that does the opposite by artificially splitting a syllable. For example, one common device that can be found in Spanish, English, and German poetry is the synalepha, which allows to join separate phonological groups (syllables belonging to different words, i.e., the last syllable of a word and the first one of the next) into one single unit of pronunciation solely for metrical purposes (see Example 1). This process might be affected by rhetorical figures and the particularities of each tradition. The scanning of a verse depends entirely on the correct assignment of stress to the syllables of the words is comprised of. Extracting metrical patterns, calculating verse lengths, identifying rhyme schemes, or inquiring about rhyme types, are all parts of the study of poetry in structural terms. The analysis of poetry usually intertwines both structural and semantic aspects, making the creation of computer-based solutions a challenge. Different poetic traditions demand slightly different approaches to their analysis, despite being mostly based on the musicality and prosody of the specific languages they are rendered in. However, one particular literary genre that has remained somewhat overlooked by the advances in natural language processing is poetry. In the last two decades, the almost coincidental emergence of the big data and distant reading paradigms increased the demand within the Humanities for bigger corpora that could be analyzed in mass and from which trends and corpus-wide characteristics otherwise invisible could be identified. Despite being initially conceived as models suitable for semantic tasks, our results suggest that transformers-based models retain enough structural information to perform reasonably well for Spanish on a monolingual setting, and outperforms both for English and German when using a model trained on the three languages, showing evidence of the benefits of cross-lingual transfer between the languages. In this paper, we compare the automated metrical pattern identification systems available for Spanish, English, and German, against fine-tuned monolingual and multilingual language models trained on the same task. This opens the door for interpretation and further complicates the creation of automated scansion algorithms useful for automatically analyzing corpora on a distant reading fashion. Some rhetorical devices shrink the metrical length, while others might extend it. Intricate language rules and their exceptions, as well as poetic licenses exerted by the authors, make calculating these patterns a nontrivial task. If the token is a not a word, it is shown as symbol.The splitting of words into stressed and unstressed syllables is the foundation for the scansion of poetry, a process that aims at determining the metrical pattern of a line of verse within a poem. If the index is negative, the syllable position is counted from the end of the word: Stress_position: Index, starting from 0, for the stressed syllable of the word. Has_synalepha or has_sinaeresis: Whether or not the syllable can be conjoined with the next one. Is_word_end: Whether the syllable is the end of a word or not. ![]() ![]() Is_stressed: Whether the syllable is stressed or not. If the token is a word, it shows a list of the syllables it is made of, with the following information: A list of tokens, and a list of “phonological groups” i.e., the phonological units that form a verse after synalephas and sinaereris are taken into account. Each stanza is then shown as two separate lists. The output of Rantanplan is a complex structure that will be broken down for clarity.įirst, Rantanplan will show a list of stanzas. ![]() Y te pareces a la palabra melancolía.""" get_scansion ( poem ) Output example Parece que los ojos se te hubieran voladoĬomo todas las cosas están llenas de mi almaĮmerges de las cosas, llena del alma mía. Y me oyes desde lejos, y mi voz no te toca. To use Rantanplan in a project: import rantanplan Usage example from re import get_scansion poem = """Me gustas cuando callas porque estás como ausente, Install Freeling rules for affixes: python -m spacy_affixes download es ![]() Install spaCy model language for Spanish: python -m spacy download es_core_news_md Installation pip install rantanplan Install required resources Rantanplan is fast and accurate as it is built using SpaCy and SpaCy-affixes.įree software: Apache Software License 2.0 It is also able to identify up to 45 different types of the most significant Spanish stanzas. Scansion is the measurement of the rhythm of verses of a poem and our tool achieves state-of-the-art results for mixed metre poems. Rantanplan is a Python library for the automated scansion of Spanish poetry. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |