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.
Social media platforms have revolutionized communication and society over the past decade, becoming essential in our daily lives by enabling effortless interaction and content sharing. They play a crucial role in opinion analysis, allowing companies to enhance their products based on reviews posted on platforms like Facebook and YouTube. This paper presents a method for constructing a data warehouse from social media data using document-oriented NoSQL databases and linguistic resources from the NooJ platform. The proposed method involves four steps: Data Extraction, Data Classification, Multidimensional Modeling, and Data Loading. To assess and validate our process, we built a corpus containing over 100 comments related to the technology domain. The obtained results are satisfactory and encouraging.
This article explores the challenges of action research on well-being at work in the context of a corporate merger, focusing on the water sector in Lyon. Using NooJ to analyze reception data from employee discourse, we highlight the impact of digital technology on the water professions and the difficulties of adaptation linked to the merger. NooJ enables us to examine employees' professional postures and feelings by analyzing feeling verbs, revealing the tensions between their expectations and the growing demands of customers andmanagement. Using participatorymethods and discourse analysis, we identify employees' professional values and analyze the points of support and irritants in their professional environment. By integrating these approaches (linguistics, discourse analysis, reception studies), this research proposes innovative solutions for preserving well-being at work and fostering fulfilling collaboration in companies transforming while accompanying change.
The CETEHIPL focuses on developing pedagogical applications of the NooJ linguistic platform. Using the Argentinian Spanish Module, we have developed various linguistic resources to help learners of Spanish, whether native speakers or not, improve their proficiency in reading and producing texts. In this paper, we study the opposition between two types of syntactic constructions in mainly northwestern Argentinian Spanish: concessive and conditional clauses. Our corpus comprises the lyrics of Atahualpa Yupanqui's folk songs. In the first descriptive stage, we located the connectors introducing these subordinate clauses in the corpus. In a second productive stage, we used NooJ to recognize and generate the corresponding syntactic structures. We have adapted our dictionaries to process the expressions of Gaucho Spanish, and we have constructed new syntactic grammars that recognize conditional and concessive clauses, seeking to bring together the variety in both prototypical formats and emphasizing the notion of nucleus phrases.
The article presents a parallel Russian-Belarusian corpus compiled from the Republic of Belarus law codes. We have analyzed a sub-corpus of almost sixty thousand words in detail and studied grammatical ambiguity occurring in it. We have developed rule-based and statistical methods to clear up ambiguity in Belarusian, including nineteen local grammars which solve homonymy for the twenty most frequent words and for several grammatical categories. These local grammars are used to select the correct tag among variants (nominative or accusative case, plural or singular, numeral or verb, etc.) and determine the proper case form after prepositions governing several cases.
This study explores the identification of diminutive and pejorative verbs in Croatian using NooJ. It focuses on suffixal verb formation, a prevalent method in Croatian word-formation, particularly for verbs expressing diminutiveness or pejorativeness. These verbs typically feature an additional suffix within their structure, distinguishing them from regular verbs. The paper outlines the creation of a morphological grammar in NooJ designed to detect verbs with these specific suffixes and the verb stems from which they are derived. The research applies this grammar to a large corpus, extracting occurrences for analysis and dictionary enhancement. The findings aim to enrich Croatian linguistic resources on the NooJ platform and provide a foundation for further morphological studies. The results also contribute to the development of a more sophisticated morphological parser for Croatian and could also benefit several research areas, including computational linguistics, lexicography, language education, cognitive science, and artificial intelligence.
Most question answering systems have been designed to answer short questions (straight answers such as dates, locations), but there are only a few pieces of research about complex questions. In this paper, we present a method for analyzing complex questions at the syntactic and the morphological levels with a pattern-based structure. These linguistic patterns allow us to annotate the question and its semantic features for extracting the focus and topic. We start with the implementation of the rules which identify and annotate the various medical named entities. Our Named Entity Recognizer (NER) is able to sift through references to people, places and organizations, diseases, viruses, as targets to extract the correct answer from the user. The NER is embedded in our question answering system. The task of our system is divided in four phases each of which plays a critical role in the general performance: question analysis, segmentation and passage retrieval, answer validation and, finally, answer extraction. We use the NooJ platform which represents a valuable linguistic development environment. The first evaluations show that the actual results are encouraging and could be deployed for further question types.
SANTI-morf is a new morphological annotation system for Indonesian, implemented using Nooj [1, 2]. SANTI-morf is designed using multi-module pipeline architecture. The modules are the Annotator, the Improver, the Disambiguator, and the Guesser. The Guesser, as its name suggests, provides best guesses for words the Annotator fails to analyze. Due to the complexities of Indonesian morphology, multiple layers of rules are created to guess the morphological structures of unknown polymorphemic and monomorphemic words. These rules are incorporated into five morphological grammars, which are applied in a pipeline based on their priorities. In each grammar, there are two layers of rules. The first layer rules are prioritized, thus ending with a +UNAMB operator. The second layer rules only apply when the first layer rules fail to find any match. Thus, the rules are constructed without a +UNAMB operator. Reflecting on the complexity of this experiment, I therefore suggest an alternative to set priorities, whose method I simulate in this paper. I argue that using the proposed alternative, NooJ users can organize rules with multiple priorities in just one grammar file.
This paper deals with the analysis of political discourse in Croatia, more precisely, it aims to determine how dissatisfaction is expressed with the attitudes represented by political rivals. We focus on the detection of linguistic means used to show disagreement with decisions or actions taken by parties or individuals considered political and/or ideological opponents. We are particularly interested in the means used by speakers to indicate that someone has failed to do something that is under his/her responsibility and is, therefore, guilty of this omission. In other words, we want to determine how the concept of responsibility is lexicalized, how it is signaled that there is a failure in someone’s responsibility, and, finally, that someone is therefore to be blamed for that omission or even transgression. For this purpose, we use a large corpus of texts, with over 127 million tokens, consisting of transcripts of plenary debates from the Croatian Parliament since 2003. We use NooJ for the construction of a set of rules that aim to detect the usage of the Croatian lexemes odgovornost [responsibility] and krivnja [guilt] in this corpus. Since Croatian is rich in terms of word formation, a set of rules is designed to capture the usage of derived words morphologically related to these nouns. In data analysis, we take into account the political orientation of MPs, i.e. their affiliation with left, right, or centrist parties, the usage of various linguistic constructions/frames related to responsibility and guilt as well as periods in which they were used.
The CETEHIPL (Centro de Estudios de Tecnología Educativa y Herramientas Informáticas de Procesamiento del Lenguaje) has been working on the pedagogical application of computer tools to language teaching [8]. Today we took a small turn towards discourse analysis and chose to analyze a recurring topic in post-pandemic Argentina: insecurity. Here we intended to record what impact insecurity had and still has on the linguistic domain. We built a corpus of journalistic texts published in December 2021 in the main newspapers in Rosario, Santa Fe, Argentina. We drew our attention to expressions referring to the victim, to the role of the State and to the perpetrator. We created tags to account for terms referring to the discourse of insecurity and included some lexical items provided by lunfardo, a Rioplatense slang originally created by immigrants, but which later became a colloquial and informal language variety still in use in our country. We tackled this issue of insecurity with the Rioplatense Spanish resources developed by the IES_UNR team with NooJ. To complete our analysis, we developed grammars to show how the impact of insecurity is made visible from a syntactic viewpoint.
The machine translation of nominal predicates from Arabic into French requires a judicious and analytical description in both the source language (SL) and target language (TL). The main interest of the present research work is to define the nominal predicates and support verbs. To do so, we firstly translated from Arabic into French two types of nominal predicates, namely the category <نُصْحٌ> “advice” and the category <نظرة> “look”, whose linguistic characteristics were then studied. Next, we downloaded these linguistic data on the NooJ platform to show the efficiency of machine translation and its limits.
This paper represents the procedure of creating medical and social domains corpora in NooJ. It illustrates a primary analysis of the corpora. Based on the research, the Belarusian NooJ module has been supplemented and thematic dictionaries of medical and social areas in NooJ format have been prepared. Automatic text processing emphasized words’ linguistic peculiarities (mainly morphological) that the main module of Belarusian language for NooJ did not recognize. In addition, the article shows how the corpora help to improve the quality of translation, to identify heterogeneous translation options.
This paper represents the procedure of creating a legal domain corpus in NooJ. It illustrates a primary analysis of the corpus including automatic text processing, emphasizing its main linguistic peculiarities, and analyzing prosodic characteristics of legal texts which is necessary for syntagmatic delimitation. It also depicts the compilation composition of three dictionaries in NooJ format: general, legal, and Belarusian-English-Russian dictionaries.
The article describes the syntactic grammar for automatic text segmentation into syntagms in Belarusian by means of NooJ. It is based on the principle of defining sequences of linguistic elements associated with certain semantic relationships and aimed at searching structural and semantic components of utterances and delimiting them into accentual units. Its implementation is essential for improving the synthetic speech generated by Belarusian text-to-speech systems using prepared syntactic grammars in NooJ.
In 1954, with his article entitled Transfer Grammar (published in “The International Journal of American Linguistics”, Vol. 20, No. 4, pp. 259–270, University of Chicago Press), Zellig S. Harris was the first linguist to approach the nascent Automatic Translation (AT) from the point of view of structuralist and formal linguistics. This article, written in the pivotal period for the first AT attempts in the US, outlines a translation method that wants to: At the time, the purposes of Harris’s article were therefore extremely innovative, since they considered translation as a process in which meaning transfers could only be achieved based on morphosyntactic analyses and evaluations. Moreover, it is worth stressing that at the time the first AT experiments performed word-for-word translations, without taking into account (not even statistically) the contexts in which the words co-occurred. As is known, this method proved to be unsuccessful, as regards the quality, time and costs of the translations made automatically. In 1966, this led ALPAC [1] to end AT research in the US, and cut off the flow of funding to it.
Learning through play is a concept used in educational science and psychology. It defends the idea that child acquires skills through the activity of play, making sense of the world around him. It can keep kids motivated and more engaged. Indeed, the game would give them social and cognitive skills and self-confidence that would allow him to live new experiences and evolve in unfamiliar environments. It also encourages them to verbalize their thoughts, to argue their choices and, therefore, helps them to improve their language skills and learn from their mistakes. The aim of this paper is to propose a serious game based on dictionaries and local grammars. This game is developed with the NooJ platform. It improves the player's level in languages. This is done by mastering the conjugation of Arabic, English and French Verbs on the one hand and the inflection of French Nouns and adjectives on the other hand. The obtained results are satisfactory and the developed game can be used as a teaching tool.
