Alignment Based Approach for Arabic Textual Entailment

Boudaa, Tarik; Marouani, Mohamed El; Enneya, Nourddine

doi:10.1016/j.procs.2019.01.067

Cited by 12 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Child-Sum-Tree-based inference of texts generalizes well for SNLI and other entailment datasets (John et al, 2016). Text alignment based approaches along with machine learning are used for entailment recognition in Arabic language (Boudaa et al, 2019). Another method used asymmetric word embeddings to produce similarity based word-word interactions for textual entailment (Ma et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Siamese Networks for Inference in Malayalam Language Texts

Renjit

Idicula

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Me

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Siamese Networks for Inference in Malayalam Language Texts

Renjit

Idicula

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Me

View full text Add to dashboard Cite

“…Additionally, the system in [7] detects NLI for Arabic by employing a semantic similarity measure and a word sense disambiguation process. Another example is the ARTESys + system [11], which converts each P-H pair to a normalized representation and enriches it with useful information such as related keywords, POS tags, synonyms, antonyms, etc. Alhijawi and Awajan [1] proposed an RTE model that uses a genetic algorithm to determine the optimal combination of text similarity measures and their corresponding weights to form a similarity function.…”

Section: Related Workmentioning

confidence: 99%

Investigating the Use of Different Recurrent Neural Networks for Natural Language Inference in Arabic

Ben-Sghaier¹,

Bakari²,

Néji³

2023

Preprint

View full text Add to dashboard Cite

Natural language inference (NLI) is a subfield of natural language processing (NLP) that involves determining the logical relationship between two pieces of text, usually a premise and a hypothesis. The goal of an NLI system is to classify the inference relationship between the premise and the hypothesis into one of three categories, namely, entailment, contradiction and neutral. An understanding of this relationship is useful for performing several NLP tasks, such as, summarization, question-answering, information retrieval, etc. Given the potential of neural networks to handle complex natural language tasks, and the absence of prior research on their application to NLI in Arabic. In this context, we propose the investigation of different neural network models for the NLI task in Arabic language. Particularly, we carried out experiments using various types of recurrent neural networks, such as, Simple RNN, LSTM, GRU, Bi-LSTM, and BiGRU to find the one that performs best on the NLI task in Arabic. We performed our experiments using the existing datasets for Arabic NLI namely, ArbTE, XNLI, and ArNLI.

show abstract

“…Boudaa et al [10] used a support vector machine algorithm to detect the RTE for the Arabic language. The following analyses were used in the pre-processing stage: named entities, temporal expressions, number/countable pairs, and ordinary words (or sequences of ordinary words).…”

Section: Related Work On Arabic Languagementioning

confidence: 99%

Arnli: Arabic Natural Language Inference Entailment and Contradiction Detection

Jallad

Ghneim²

2023

csci

View full text Add to dashboard Cite

Natural Language Inference (NLI) is a hot topic research in natural language processing, contradiction detection between sentences is a special case of NLI. This is considered a difficult NLP task which has a big influence when added as a component in many NLP applications, such as Question Answering Systems, text Summarization. Arabic Language is one of the most challenging low-resources languages in detecting contradictions due to its rich lexical, semantics ambiguity. We have created a dataset of more than 12k sentences and named ArNLI, that will be publicly available. Moreover, we have applied a new model inspired by Stanford contradiction detection proposed solutions on English language. We proposed an approach to detect contradictions between pairs of sentences in Arabic language using contradiction vector combined with language model vector as an input to machine learning model. We analyzed results of different traditional machine learning classifiers and compared their results on our created dataset (ArNLI) and on an automatic translation of both PHEME, SICK English datasets. Best results achieved using Random Forest classifier with an accuracy of 99%, 60%, 75% on PHEME, SICK and ArNLI respectively.

show abstract

Alignment Based Approach for Arabic Textual Entailment

Cited by 12 publications

References 18 publications

Siamese Networks for Inference in Malayalam Language Texts

Siamese Networks for Inference in Malayalam Language Texts

Investigating the Use of Different Recurrent Neural Networks for Natural Language Inference in Arabic

Arnli: Arabic Natural Language Inference Entailment and Contradiction Detection

Contact Info

Product

Resources

About