In this paper, we present NooJ dictionaries and inflectional grammars designed to recognize various types of Latin verbs, including regular, irregular, defective, deponent, semideponent, and impersonal verbs. Additionally, we have developed morphological grammars to identify compound verbs. The primary aim of this paper is for NooJ to recognize all forms of a verb and link each verb to its corresponding inflectional paradigm. Furthermore, we aim to investigate the recognition of compound verbs using NooJ grammars such as verbs derived by prefix de- such as decedo 'to go away' (< de + cedo 'to go'), deficio 'to withdray' (< de + facio 'to make'), dimitto 'to send down' (< de + mitto 'to send'), etc. To validate our work, we applied these resources to a corpus of last wills and testaments written in medieval Latin in the Zadar commune (MedText). Although MedText contains only one type of legal document and a limited number of verbs, our grammars demonstrated high complexity even in this sample. These resources complete the work on NooJ morphological resources for medieval Latin.
Compared to other corpus tools, such as CQPweb, Sketch Engine, and AntConc, NooJ is rarely used for collocation analysis. This might be due to the absence of an automatic collocation extraction function in NooJ. In this paper, I demonstrate that NooJ can be used for collocation analysis using a semi-automatic method. The target corpus is the Indonesian version of the Holy Quran, whose translation is approved by the Ministry of Religions of Indonesia. The target node words are all word forms derived from the lemma with ambiguous meanings. I aim to identify the senses of node words and their collocates. The target corpus is annotated using SANTI-morf, a NooJ-based Indonesian morpheme tagger, which includes a lemmatizer. Two senses of the nodes are found: literal (SENSE_1) and metaphorical meanings (SENSE_2). Collocates are extracted semi-automatically from concordances. Thirty-one collocates are observed and lexicogrammatically categorized. The implications for disambiguation of the senses are also discussed. The results may contribute to developing SANTI-network, a NooJ-based multi-level tagger for Indonesian that combines morpheme, POS, and syntactic annotation.
This paper focuses on normalizing quantitative expressions, a crucial step for enhancing natural language processing tasks in the Belarusian language. They present a NooJ syntactic grammar designed to identify and standardize different quantitative expressions in Belarusian texts. Beyond explaining the grammar, they provide practical techniques for searching for and analyzing dates, Cyrillic and Roman numbers, years, and quantitative expressions with measurement units, whose processing poses significant problems to automatic processing and usage in various technologies, including speech synthesis and recognition systems. This work contributes significantly to Belarusian NLP, laying the foundation for effectively unifying different syntactic grammars compiled in NooJ that determine intonation boundaries in electronic texts.
In Italy, the conversation around misogynistic gender-based violence received mainstream attention in the last decade. Recent data tells of 120 femicides in 2023, Italy alone, with romantic/marital partners recognized as aggressors in more than half of the cases. Using the NooJ platform, we have analyzed reporting surrounding seven high-profile criminal cases that occurred from 2005 to 2023. We constructed six grammars to compute statistics around potentially misogynistic tropes occurring in the corpus, such as pseudo-apologetic attitudes displayed towards the aggressors, infantilization of the victims, emphasis placed on women's role as mothers, wives, and daughters, and recurrence of secondary victimization. We consider the way modern tech and social media influence both feminist advocacy campaigns and dynamics surrounding gender-based violence. The reconstruction of chronological events emerging from the corpus also highlighted a pattern of legal complaints and warning signs ultimately ignored by authorities.
This paper focuses on the automatic annotation of linguistic readability features in institutional Italian texts. Specifically, our research deals with qualitative linguistic features identified by other researchers as elements of complexity. Italian administrative texts often exhibit an excessive complexity that interferes with citizens' right to access information. Many authors identified the features responsible for low readability and proposed rewriting rules. We will focus our research on complex prepositions and conjunctions, passive voice, nominalizations, support verb constructions, and double negation. Specifically, we developed an automatic readability assessment tool that identifies these readability issues in sentences, through NooJ dictionaries and grammars. Finally, we applied it to a corpus of institutional texts.
