Paraphrase Detection Algorithm
(Redirected from paraphrase detection algorithm)
Jump to navigation
Jump to search
A Paraphrase Detection Algorithm is a semantic NLP classification task that can be implemented by a paraphrase detection system to solve a paraphrase detection task.
- Example(s):
- Mihalcea et al. (2006) - Vector Based Similarity Unsupervised Paraphrase Detection Algorithm - cosine similarity with tf-idf weighting.
- Ji and Eisenstein (2013) - TF-KLD - Supervised - Matrix factorization with supervised reweighting.
- Cheng and Kartsaklis (2015) - SAMS-RecNN - Supervised - Recursive NNs using syntax-aware multi-sense word embeddings.
- Filice et al. (2015) - REL-TK - Supervised - Combination of Convolution Kernels and similarity scores.
- He et al. (2015) - Multi-Perspective CNN - Supervised - Multi-perspective Convolutional NNs and structured similarity layer.
- Counter-Example(s):
- See: Semantic Identity, Paraphrase.
References
2018
| Algorithm | Reference | Description | Supervision | Accuracy | F |
|---|---|---|---|---|---|
| Vector Based Similarity (Baseline) | Mihalcea et al. (2006) | cosine similarity with tf-idf weighting | unsupervised | 65.4% | 75.3% |
| ESA | Hassan (2011) | explicit semantic space | unsupervised | 67.0% | 79.3% |
| KM | Kozareva and Montoyo (2006) | combination of lexical and semantic features | supervised | 76.6% | 79.6% |
| LSA | Hassan (2011) | latent semantic space | unsupervised | 68.8% | 79.9% |
| RMLMG | Rus et al. (2008) | graph subsumption | unsupervised | 70.6% | 80.5% |
| MCS | Mihalcea et al. (2006) | combination of several word similarity measures | unsupervised | 70.3% | 81.3% |
| STS | Islam and Inkpen (2007) | combination of semantic and string similarity | unsupervised | 72.6% | 81.3% |
| SSA | Hassan (2011) | salient semantic space | unsupervised | 72.5% | 81.4% |
| QKC | Qiu et al. (2006) | sentence dissimilarity classification | supervised | 72.0% | 81.6% |
| ParaDetect | Zia and Wasif (2012) | PI using semantic heuristic features | supervised | 74.7% | 81.8% |
| Vector-based similarity | Milajevs et al. (2014) | Additive composition of vectors and cosine distance | unsupervised | 73.0% | 82.0% |
| SDS | Blacoe and Lapata (2012) | simple distributional semantic space | supervised | 73.0% | 82.3% |
| matrixJcn | Fernando and Stevenson (2008) | JCN WordNet similarity with matrix | unsupervised | 74.1% | 82.4% |
| FHS | Finch et al. (2005) | combination of MT evaluation measures as features | supervised | 75.0% | 82.7% |
| PE | Das and Smith (2009) | product of experts | supervised | 76.1% | 82.7% |
| WDDP | Wan et al. (2006) | dependency-based features | supervised | 75.6% | 83.0% |
| SHPNM | Socher et al. (2011) | recursive autoencoder with dynamic pooling | supervised | 76.8% | 83.6% |
| MTMETRICS | Madnani et al. (2012) | combination of eight machine translation metrics | supervised | 77.4% | 84.1% |
| L.D.C Model | Wang et al. (2016) | Sentence Similarity Learning by Lexical Decomposition and Composition | supervised | 78.4% | 84.7% |
| Multi-Perspective CNN | He et al. (2015) | Multi-perspective Convolutional NNs and structured similarity layer | supervised | 78.6% | 84.7% |
| REL-TK | Filice et al. (2015) | Combination of Convolution Kernels and similarity scores | supervised | 79.1% | 85.2% |
| SAMS-RecNN | Cheng and Kartsaklis (2015) | Recursive NNs using syntax-aware multi-sense word embeddings | supervised | 78.6% | 85.3% |
| TF-KLD | Ji and Eisenstein (2013) | Matrix factorization with supervised reweighting | supervised | 80.4% | 85.9% |
2015
- (Cheng & Kartsaklis, 2015) ⇒ Jianpeng Cheng, and Dimitri Kartsaklis. (2015). “Syntax-aware Multi-sense Word Embeddings for Deep Compositional Models of Meaning.” In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015).
2013
- (Ji & Eisenstein, 2013) ⇒ Yangfeng Ji, and Jacob Eisenstein. (2013). “Discriminative Improvements to Distributional Sentence Similarity.” In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP 2013).
2006
- (Mihalcea et al., 2006) ⇒ Rada Mihalcea, Courtney Corley, and Carlo Strapparava. (2006). “Corpus-based and Knowledge-based Measures of Text Semantic Similarity.” In: Proceedings of the 2006 National Conference on Artificial Intelligence (AAAI 2006)