Factual Question Generation for the Portuguese Language

Leite, Bernardo; Cardoso, Henrique Lopes; Reis, Luís Paulo; Soares, Carlos

doi:10.1109/inista49547.2020.9194631

Cited by 7 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SRL is regarded as a powerful method for text semantic analysis because it can assign a semantic role to each word in a sentence. After using nlpnet to find semantic role labels in Portuguese sentences, question generation can be generated [63].…”

Section: Newsmentioning

confidence: 99%

A Systematic Review on Semantic Role Labeling for Information Extraction in Low-Resource Data

Ariyanto,

Purwitasari,

Fatichah

2024

IEEE Access

View full text Add to dashboard Cite

Challenges in the big data phenomenon arise due to the existence of unstructured text data, which is very large, comes from various sources, has various formats, and contains much noise. The complexity of unstructured text data makes it difficult to extract useful information. Therefore, a process is needed to transform it into structured data to be processed further. The information Extraction (IE) process helps to extract relationships, entities, semantic roles, and events from unstructured text data by converting them into structured output. One of IE's tasks is Semantic Role Labeling (SRL), which has a crucial function in identifying semantic roles in a sentence so that it can enrich the understanding of the text. However, much of SRL development focuses on high-resource data, especially in English. The limited development of SRL in specific low-resource languages or domains is a complex challenge. This research aims to conduct a systematic study on the development of SRL for low-resource data, both in low-resource language or domainspecific contexts. The review process was carried out systematically using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) model, and 54 quality papers were obtained from the filtering process (from 2018 to 2023). We review several essential points, including (1) datasets that are often used for SRL tasks and their labeling strategies for low-resource data, (2) methods that have currently been developed for SRL tasks and learning scenarios when dealing with low-resource data, (4) evaluation metrics, (5) application of SRL tasks. This review is complemented by a discussion of issues and potential solutions for developing SRL on low-resource data to help researchers develop SRL more effectively in dealing with the challenges faced with low-resource data.

show abstract

Section: Newsmentioning

confidence: 99%

A Systematic Review on Semantic Role Labeling for Information Extraction in Low-Resource Data

Ariyanto,

Purwitasari,

Fatichah

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The entity can be a person's name, an organization's name, a date, or a time etc. Named entities [27,28,42] and SRL [43] have been utilized to generate factoid questions. Figure 2 shows the types of proper nouns and possible factoid questions that can be generated from each type of proper noun.…”

Section: 14nermentioning

confidence: 99%

“…Hence, a scientific study of the linguistic and grammatical aspects of Marathi has been conducted, and a set of rules and patterns has been crafted that facilitate AQG in a linguistically correct manner. While substantial research has been conducted in the area of AQG for foreign languages such as English [18, 2225], Bahasa [26], Chinese [27], and Portuguese [28], there is a notable gap in AQG focusing on Indian regional languages. Addressing this gap, current research presents a novel working model for AQG crafted specifically for the Marathi language.…”

Section: Introductionmentioning

confidence: 99%

Bloom’s Taxonomy based automatic Marathi question generation

2024

IJATEE

View full text Add to dashboard Cite

In the current era of automation, various fields, including education, are undergoing transformations to enhance their existing processes. One crucial aspect in the field of education is examination management. Automatic question generation (AQG) for creating evaluation systems and question papers represents a significant transformation that schools, colleges, and universities are experiencing. Although significant research has been conducted in AQG for foreign languages, there is a scarcity of such work in Indian regional languages. Considering this, a novel working model for AQG for Marathi language texts was presented. The proposed research generates a diverse set of questions automatically through various natural language processing (NLP) pipeline activities, including tokenization, parts of speech (POS) tagging, stemming, named entity recognition (NER), shallow parsing, and dependency parsing. The generated questions fall into the categories of context-based and grammar-based questions, each elaborated in detail with scientific interpretation. This process contributes to the validation and refinement of our question generation methodology. A benchmarking approach using Bloom's Taxonomy was employed to validate the accuracy of the generated questions, ensuring they were aligned with educational objectives and targeted the desired levels of cognitive complexity. The empirical evaluation of the proposed methodology is conducted using the bilingual evaluation understudy (BLEU) score and manual scoring. The accuracy achieved using the BLEU score is 90.37% for the 'wh' questions, based on the corpus created from the sixth standard science textbook published by the Maharashtra State Board, Maharashtra, India. A diverse set of high-quality Marathi language questions has been successfully curated, suitable for compiling question papers aligned with Bloom's taxonomy levels.

show abstract

Neural Question Generation for the Portuguese Language: A Preliminary Study

Leite

Cardoso

2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Question Generation aims to automatically generate questions based on a given input provided as context. A controllable question generation scheme focuses on generating questions with specific attributes, allowing better control. In this study, we propose a few-shot prompting strategy for controlling the generation of question-answer pairs from children's narrative texts. We aim to control two attributes: the question's explicitness and underlying narrative elements. With empirical evaluation, we show the effectiveness of controlling the generation process by employing few-shot prompting side by side with a reference model. Our experiments highlight instances where the few-shot strategy surpasses the reference model, particularly in scenarios such as semantic closeness evaluation and the diversity and coherency of question-answer pairs. However, these improvements are not always statistically significant. The code is publicly available at github.com/bernardoleite/few-shot-prompting-qg-control.

show abstract

Factual Question Generation for the Portuguese Language

Cited by 7 publications

References 18 publications

A Systematic Review on Semantic Role Labeling for Information Extraction in Low-Resource Data

A Systematic Review on Semantic Role Labeling for Information Extraction in Low-Resource Data

Bloom’s Taxonomy based automatic Marathi question generation

Neural Question Generation for the Portuguese Language: A Preliminary Study

Contact Info

Product

Resources

About