A Text Semantic Similarity Approach for Arabic Paraphrase Detection

Mahmoud, Adnen; Zrigui, Ahmed; Zrigui, Mounir

doi:10.1007/978-3-319-77116-8_25

Cited by 20 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As Madnani and Dorr (2010) pointed out, paraphrases may occur at different levels, such as word-level, phrase-level, and sentence-level. Although there has been some work that concerned the identification of lexical and phrasal paraphrases (Ganitkevitch et al, 2013;Pavlick et al, 2015), most recent work on paraphrase identification has been performed at the sentence level, and has involved determining whether a given sentence pair is a paraphrase or not in a classification setup (Dolan and Brockett, 2005;Fernando and Stevenson, 2008;Xu et al, 2014;Zhang et al, 2019b;Liu et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

Testing Paraphrase Models on Recognising Sentence Pairs at Different Degrees of Semantic Overlap

Peng,

Weir,

Weeds

2023

Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)

View full text Add to dashboard Cite

Paraphrase detection is useful in many natural language understanding applications. Current works typically formulate this problem as a sentence pair binary classification task. However, this setup is not a good fit for many of the intended applications of paraphrase models.In particular, such applications often involve finding the closest paraphrases of the target sentence from a group of candidate sentences where they exhibit different degrees of semantic overlap with the target sentence. To apply models to this paraphrase retrieval scenario, the model must be sensitive to the degree to which two sentences are paraphrases of one another. However, many existing datasets ignore and fail to test models in this setup. In response, we propose adversarial paradigms to create evaluation datasets, which could examine the sensitivity to different degrees of semantic overlap. Empirical results show that, while paraphrase models and different sentence encoders appear successful on standard evaluations, measuring the degree of semantic overlap still remains a big challenge for them.

show abstract

Section: Related Workmentioning

confidence: 99%

Testing Paraphrase Models on Recognising Sentence Pairs at Different Degrees of Semantic Overlap

Peng,

Weir,

Weeds

2023

Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)

View full text Add to dashboard Cite

show abstract

“…When it comes to PI, there exist a wide range of traditional approaches that are relatively effective for the task: (1) lexical overlap features such as n-gram overlap (Wan et al 2006) and machine translation evaluation metrics (Madnani, Tetreault, and Chodorow 2012); (2) using external lexical knowledge like WordNet (Fellbaum, 1998;Fernando and Stevenson 2008); (3) modeling divergence of dependency syntax between two sentences (Das and Smith 2009); (4) distributional models with matrix factorization (Guo and Diab 2012;Ji and Eisenstein 2013). The traditional approaches mainly consist of unsupervised methods and feature engineering.…”

Section: Technical Background and Research Goalmentioning

confidence: 99%

Parameter-efficient feature-based transfer for paraphrase identification

2022

View full text Add to dashboard Cite

There are many types of approaches for Paraphrase Identification (PI), an NLP task of determining whether a sentence pair has equivalent semantics. Traditional approaches mainly consist of unsupervised learning and feature engineering, which are computationally inexpensive. However, their task performance is moderate nowadays. To seek a method that can preserve the low computational costs of traditional approaches but yield better task performance, we take an investigation into neural network-based transfer learning approaches. We discover that by improving the usage of parameters efficiently for feature-based transfer, our research goal can be accomplished. Regarding the improvement, we propose a pre-trained task-specific architecture. The fixed parameters of the pre-trained architecture can be shared by multiple classifiers with small additional parameters. As a result, the computational cost left involving parameter update is only generated from classifier-tuning: the features output from the architecture combined with lexical overlap features are fed into a single classifier for tuning. Furthermore, the pre-trained task-specific architecture can be applied to natural language inference and semantic textual similarity tasks as well. Such technical novelty leads to slight consumption of computational and memory resources for each task and is also conducive to power-efficient continual learning. The experimental results show that our proposed method is competitive with adapter-BERT (a parameter-efficient fine-tuning approach) over some tasks while consuming only 16% trainable parameters and saving 69-96% time for parameter update.

show abstract

“…Various methods such as Term Frequency-Inverse Document Frequency (TF-IDF), Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA), word2vec, Global Vector Representation (GloVe), and Convolutional Neural Network (CNN) were experimented for paraphrase detection. Another group of researchers [10] used a deep learning based method to detect Arabic paraphrasing. This method consists of pre-processing phase, and word2vec phase.…”

Section: A Similarity Checking Work In Foreign Languagesmentioning

confidence: 99%

Sensed-Lexicon based Approach for Identification of Similarity among Punjabi Documents

Kaur¹,

Saini²

2021

IJACSA

View full text Add to dashboard Cite

Textual similarity among documents often leads to copyright issues. Manual measurement of similarity among documents is a time consuming infeasible activity. In this paper, we proposed a technique for measuring similarity at sensedlexicon level for documents written in Punjabi language using Gurumukhi script. 50 Punjabi document pairs were manually collected with the help of Punjabi native writers. The proposed technique consisted of major 4 levels. Level 0 consists of data collection phase. Level 1 consists of noise removal and stop word removal sub levels. Extracted tokens were stemmed, lemmatized and synonyms were replaced based on part of speech tagging in level 2. Vector space representation corresponding to each document leads to n-gram generation of documents in level 2. Extracted n-grams were weighted based on term frequency. In level 3, string based token level similarity indexes such as Jaccard Similarity Index (JSI), Cosine Similarity Index (CSI) and Levenshtien Distance Index (LDI) were experimented with weighed tokens. In this work, Human Intelligence Task (HIT) based rating has been utilized for measuring the similarity among documents between 0-100. Results obtained from HIT based rating are compared with results obtained from the proposed technique with various combinations of pre-processing levels. Results revealed that on the basis of majority voting, combination of stop word removal with stemming and 'noun' based synonym replacement leads to the best combination with bi-gram tokens. Statistical analysis indicates strong correlation between CSI and HIT based rating.

show abstract

A Text Semantic Similarity Approach for Arabic Paraphrase Detection

Cited by 20 publications

References 9 publications

Testing Paraphrase Models on Recognising Sentence Pairs at Different Degrees of Semantic Overlap

Testing Paraphrase Models on Recognising Sentence Pairs at Different Degrees of Semantic Overlap

Parameter-efficient feature-based transfer for paraphrase identification

Sensed-Lexicon based Approach for Identification of Similarity among Punjabi Documents

Contact Info

Product

Resources

About