2,237 Hits in 3.6 sec

Paraphrase recognition via dissimilarity significance classification

Long Qiu, Min-Yen Kan, Tat-Seng Chua
2006 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06   unpublished
Unlike most PR systems that focus on sentence similarity, our framework detects dissimilarities between sentences and makes its paraphrase judgment based on the significance of such dissimilarities.  ...  We propose a supervised, two-phase framework to address the problem of paraphrase recognition (PR).  ...  recognition (PR) problem: a supervised, two-phase framework emphasizing dissimilarity classification.  ... 
doi:10.3115/1610075.1610079 fatcat:qhie4m4jnjhxneyqthhsxra67u

A Novel Approach for Developing Paraphrase Detection System using Machine Learning

Rudradityo Saha, G. Bharadwaja Kumar
2021 International Journal of Computer Applications  
The proposed paraphrase detection system has achieved comparable performance with existing paraphrase detection systems.  ...  Research Paraphrase (MSRP) Corpus and assessed on the same.  ...  pair and then deciding whether the dissimilarities are significant or not.  ... 
doi:10.5120/ijca2021921389 fatcat:clya63hxdvfz3kpmszhrjmhc2i

Re-examining Machine Translation Metrics for Paraphrase Identification

Nitin Madnani, Joel R. Tetreault, Martin Chodorow
2012 North American Chapter of the Association for Computational Linguistics  
We propose to re-examine the hypothesis that automated metrics developed for MT evaluation can prove useful for paraphrase identification in light of the significant work on the development of new MT metrics  ...  We show that a meta-classifier trained using nothing but recent MT metrics outperforms all previous paraphrase identification approaches on the Microsoft Research Paraphrase corpus.  ...  Qiu et al. (2006) build a framework that detects dissimilarities between sentences and makes its paraphrase judgment based on the significance of such dissimilarities.  ... 
dblp:conf/naacl/MadnaniTC12 fatcat:cthis463lvahpncjtriwbmgale

Paraphrase acquisition via crowdsourcing and machine learning

Steven Burrows, Martin Potthast, Benno Stein
2013 ACM Transactions on Intelligent Systems and Technology  
The empirical contributions include machine learning experiments to explore if passage-level paraphrases can be identified in a two-class classification problem using paraphrase similarity features, and  ...  This paper contributes to paraphrase acquisition and focuses on two aspects that are not addressed by current research: (1) acquisition via crowdsourcing, and (2) acquisition of passage-level samples.  ...  Acknowledgements We thank João Paulo Cordeiro and colleagues for their kind assistance with operationalizing the paraphrase similarity metrics.  ... 
doi:10.1145/2483669.2483676 fatcat:tqlifvwj6bgftdxjolk6njfu54

A Reflective View on Text Similarity

Daniel Bär, Torsten Zesch, Iryna Gurevych
2011 Recent Advances in Natural Language Processing  
As detecting paraphrases is a classification task, we use an additional majority baseline which classifies all results according to the predominant class of true paraphrases.  ...  recognition (Tsatsaronis et al., 2010) .  ... 
dblp:conf/ranlp/BarZG11 fatcat:vewjy6vctvewjfhm3gxlvyv7du


Seungyeop Han, Matthai Philipose, Yun-Cheng Ju
2013 Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing - UbiComp '13  
The central challenge is to create statistical recognition models that are accurate and resource-efficient in the face of the variety of natural language, while requiring little specialized knowledge from  ...  We show that given a few examples from the developer, it is possible to elicit comprehensive sets of paraphrases of the examples using internet crowds.  ...  The exhaustive-paraphrasing approach implemented via automated crowdsourcing is novel. The derived architecture allowing modular addition of applications and purely local recognition is new.  ... 
doi:10.1145/2493432.2493458 dblp:conf/huc/HanPJ13 fatcat:miul72dn6rg3lf3yznroy3z32m

XeroAlign: Zero-Shot Cross-lingual Transformer Alignment [article]

Milan Gritta, Ignacio Iacobacci
2021 arXiv   pre-print
XLM-RA's text classification accuracy exceeds that of XLM-R trained with labelled data and performs on par with state-of-the-art models on a cross-lingual adversarial paraphrasing task.  ...  Zero-shot paraphrase detection is another instance of text classification.  ...  Both of these datasets are based on the original English-only ATIS (Price, 1990) featuring users interacting with an automated air travel information service (via intent recognition and slot filling  ... 
arXiv:2105.02472v2 fatcat:wnttyap5wbblncujqf3nquoeqi

Neural Paraphrase Generation with Stacked Residual LSTM Networks [article]

Aaditya Prakash, Sadid A. Hasan, Kathy Lee, Vivek Datla, Ashequl Qadir, Joey Liu, Oladimeji Farri
2016 arXiv   pre-print
In this paper, we propose a novel neural approach for paraphrase generation.  ...  To the best of our knowledge, this work is the first to explore deep learning models for paraphrase generation.  ...  There are several works on paraphrase recognition (Socher et al., 2011; Yin and Schütze, 2015; Kiros et al., 2015) , but those employ classification techniques and do not attempt to generate paraphrases  ... 
arXiv:1610.03098v3 fatcat:mv7r77eoujczzh3n5w4qi3r4xu

Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity

Eunah Cho, He Xie, John P. Lalor, Varun Kumar, William M. Campbell
2019 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)  
In this work, we explore functionality-specific semi-supervised learning via self-training.  ...  First, we consider paraphrase detection methods that attempt to find utterance variants of labeled training data with good coverage.  ...  For the next step in the figure, we iteratively refine our selection by applying both intent classification (IC) and named entity recognition (NER) to the filtered utterances.  ... 
doi:10.1109/asru46091.2019.9003747 dblp:conf/asru/ChoXLKC19 fatcat:c5yhyq6hije6zc6ydquhuy6ubi

Certainty factor model in paraphrase detection

Senem Kumova Metin, Bahar Karaoğlan, Tarık Kışla, Katira Soleymanzadeh
2021 Pamukkale University Journal of Engineering Sciences  
The proposed CF model in paraphrase identification is realized by utilizing the renowned paraphrase corpus of Microsoft Research (MSRP) [2] that is stated to be a standard resource in paraphrase identification  ...  We propose the use of certainty factor (CF) model in paraphrase detection.  ...  In paraphrase recognition, Wan et al.  ... 
doi:10.5505/pajes.2020.75350 fatcat:aw5geqmftnfrbpl4nbdpq3nrgq

Semantic Similarity Modeling Based on Multi-Granularity Interaction Matching

Xu Li, Chunlong Yao, Qinyang Zhang Zhang, Guoqi Zhang
2019 International Journal of Innovative Computing, Information and Control  
The sentence-pair encoding is input to an output layer to determine the classification.  ...  The effectiveness of our model is demonstrated using two tasks: paraphrase identification and semantic relatedness measurement.  ...  This approach is different from other approaches because it is focusing on dissimilarities between the pairs of sentences.  ... 
doi:10.24507/ijicic.15.05.1685 fatcat:lpwzojs6hbbk3b2lxjeah7gsje

To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks

Matthew E. Peters, Sebastian Ruder, Noah A. Smith
2019 Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)  
., 2018) using both and across seven diverse tasks including named entity recognition, natural language inference (NLI), and paraphrase detection.  ...  Target Tasks and Datasets We evaluate on a diverse set of target tasks: named entity recognition (NER), sentiment analysis (SA), and three sentence pair tasks, natural language inference (NLI), paraphrase  ... 
doi:10.18653/v1/w19-4302 dblp:conf/rep4nlp/PetersRS19 fatcat:fomcgna5kfagdhlcupdvj6qouy

Semantic and Heuristic Based Approach for Paraphrase Identification

Muhidin A. Mohamed, Mourad Oussalah
2018 2018 14th International Conference on Semantics, Knowledge and Grids (SKG)  
In this paper, we propose a semantic-based paraphrase identification approach.  ...  The paraphrase identification system is then evaluated using two different datasets; namely, Microsoft Research Paraphrase Corpus (MSRPC) and TREC-9 Question Variants.  ...  This is typically achieved using namedentity recognition software.  ... 
doi:10.1109/skg.2018.00037 dblp:conf/skg/Mohamed018 fatcat:ckugovkxvrd3heel5likpm5jdu

Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data [article]

David Lowell, Brian E. Howard, Zachary C. Lipton, Byron C. Wallace
2020 arXiv   pre-print
semi-supervised technique that applies a consistency loss to penalize differences between a model's predictions on (a) observed (unlabeled) examples; and (b) corresponding 'noised' examples produced via  ...  This method has recently gained traction for text classification. In this paper, we re-examine UDA and demonstrate its efficacy on several sequential tasks.  ...  For example, consider the strategy of paraphrasing via backtranslation.  ... 
arXiv:2010.11966v1 fatcat:dn4avca7xnd63mhteqqd44nzeq

A multi-cascaded model with data augmentation for enhanced paraphrase detection in short texts

Muhammad Haroon Shakeel, Asim Karim, Imdadullah Khan
2020 Information Processing & Management  
The learned features, together with hand-crafted linguistic features, are then forwarded to a discriminator network for final classification.  ...  Our data augmentation strategy considers the notions of paraphrases and non-paraphrases as binary relations over the set of texts.  ...  We obtain the best performance of 90.3% when in addition to augmenting paraphrases via steps P3, P2, and P1 additional non-paraphrases are generated via step NP1.  ... 
doi:10.1016/j.ipm.2020.102204 fatcat:7ehvysetjrhmncciqfstqso6pi
« Previous Showing results 1 — 15 out of 2,237 results