A literature review on question answering techniques, paradigms and systems

Soares, Marco Antonio; Parreiras, Fernando Silva

doi:10.1016/j.jksuci.2018.08.005

Cited by 93 publications

(33 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The term Answer Type refers to a class of objects that the question is looking for. Finaly, the term Question Focus is the property or entity being searched by the question [9].…”

Section: Basic Concepts 21 Questionn Answering Systemmentioning

confidence: 99%

An ontology driven question answering system for fatawa retrieval

Benlaharche

Laboudi

Nouaouria

et al. 2021

IJEECS

View full text Add to dashboard Cite

This work aims to propose a system for the Algerian Fatawa House in orderto facilitate the task of the Expert Mufti who is responsible of giving fatawa for Algerian people inquiries. In fact, as this house is recent and does not have sufficient human resources, it is difficult to satisfy all inquiries coming daily, this leads the askers to wait for a long time before getting answers. The proposed system allows the askers to express concerns they may have. By using a case-based reasoning mechanism combined with ontology domain, the system tries to retrieve similar cases from the knowledge base. In the casewhere the response already exists, the system immediately provides the answer to the askers. Otherwise, an inquery is automatically formulated and sent to the expert Mufti-which is a certified scholar-in order either to validate the generated response by the system or give a new answer. Such a question-answering system may be very helpful for askers to get their answers faster since it allows both the storage of previous <em>fatawas</em> and their retrieval for processing coming inquiries. To validate our proposal, we rely on <em>fatawas</em> concerning the Islamic finance and banking transactions domain. Overall, the results are encouraging and satisfactory.

show abstract

“…The term Answer Type refers to a class of objects that the question is looking for. Finaly, the term Question Focus is the property or entity being searched by the question [9].…”

Section: Basic Concepts 21 Questionn Answering Systemmentioning

confidence: 99%

An ontology driven question answering system for fatawa retrieval

Benlaharche

Laboudi

Nouaouria

et al. 2021

IJEECS

View full text Add to dashboard Cite

show abstract

“…NLP mempelajari cara mengaktifkan komputer untuk memproses dan memahami bahasa yang digunakan manusia dalam kehidupan sehari-hari, memahami pengetahuan manusia, dan berkomunikasi dengan manusia dalam bahasa alami. Aplikasi T NLP termasuk pencarian informasi (IR), ekstraksi pengetahuan, sistem tanya jawab (QA), kategorisasi teks, terjemahan mesin, bantuan penulisan, identifikasi suara, komposisi, dan sebagainya [10]- [12]. Perkembangan internet dan produksi dokumen digital dalam jumlah besar telah menghasilkan kebutuhan mendesak akan pemrosesan teks cerdas, dan oleh karena itu, teori serta keterampilan NLP menjadi semakin penting.…”

Section: A Natural Language Pocessing (Nlp)unclassified

Deteksi Plagiarisme Menggunakan Algoritma Levenshtein Distance

Yuslena¹,

Khatimi²,

Fajrin³

2021

JTekInfULM

View full text Add to dashboard Cite

Deteksi kesamaan dokumen untuk sistem plagiarisme termasuk dalam riset Natural Language Processing dalam bidang kecerdasan buatan. Plagiarisme banyak terjadi pada dokumen di lingkungan akademisi, begitupun yang terjadi pada PSMTS ULM. Deteksi plagiarisme diperlukan agar menjaga orisinalitas dari hasil tesis mahasiswa. Ada beberapa algoritma yang digunakan peneliti sebelumnya untuk mendeteksi plagiarisme. Namun, algoritma yang diperlukan adalah algoritma yang cepat karena yang sedang terjadi pada tesis mahasiswa relatif memiliki string yang banyak dan data tesis yang akan terus bertambah setiap saatnya mengakibatkan memperlambat kinerja algoritma. algoritma Levenshtein Distance mengungguli algoritma adaptif. Proses preprocessing yang terdiri dari metode case folding, tokenizing, stopword removal, dan stemming yang dapat melakukan estimasi proses sistem menjadi lebih cepat. Algoritma Levenshtein Distence dapat mendeteksi plagiasi dengan baik dan rata-rata lama proses sistem tanpa dilakukan preprocessing adalah 6,283 ms dan dengan preprocessing adalah 4,920 ms.

show abstract

“…Currently, computer vision and natural language processing (NLP) remains the leading area of exploit and has witnessed a wide range of architectural designs and application. For example, natural language tasks such as machine translation, language understanding, question-answering, parsing, sentiment analysis, textual generation, and language model have been well addressed using a couple of deep learning models [7]. In the same way, computing the combination of edges and shapes have resulted in learning and extracting features from images in the field of computer vision.…”

Section: Introductionmentioning

confidence: 99%

Fully Convolutional CaptionNet: Siamese Difference Captioning Attention Model

et al. 2019

View full text Add to dashboard Cite

The generation of the textual description of the differences in images is a relatively new concept that requires the fusion of both computer vision and natural language techniques. In this paper, we present a novel Fully Convolutional CaptionNet (FCC) that employs an encoder-decoder framework to perform visual feature extractions, compute the feature distances, and generate new sentences describing the measured distances. After extracting the features of the images, a contrastive function is used to compute their weighted L1 distance which is learned and selectively attended to determine salient sections of the feature at every time step. The attended feature region is adequately matched to corresponding words iteratively until a sentence is completed. We propose the application of upsampling network to enlarge the features' field of view, this provides a robust pixel-based discrepancy computation. Our extensive experiments indicate that the FCC model outperforms other learning models on the benchmark Spot-the-Diff datasets by generating succinct and meaningful textual differences in images. INDEX TERMSImage captioning, deep learning, Siamese network, recurrent neural network, convolutional neural network, attention, fully convolutional networks.

show abstract

A literature review on question answering techniques, paradigms and systems

Cited by 93 publications

References 86 publications

An ontology driven question answering system for fatawa retrieval

An ontology driven question answering system for fatawa retrieval

Deteksi Plagiarisme Menggunakan Algoritma Levenshtein Distance

Fully Convolutional CaptionNet: Siamese Difference Captioning Attention Model

Contact Info

Product

Resources

About