Re-examining Machine Translation Metrics for Paraphrase Identification

By Nitin Madnani, Joel R. Tetreault, Martin Chodorow. 2012

250 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Skip-Thought Vectors (2015, neutral): “0 MTMETRICS [28] 77.”
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs (2015, methodology): “For better comparability of approaches in our experiments, we use a simple SVM classifier, which performs slightly worse than Madnani et al. (2012)’s more complex meta-classifier.”
Convolutional Neural Network for Paraphrase Identification (2015, methodology): “Since we want to show that Bi-CNN-MI performs better than previous NN work, we compare with three NN approaches: NLM, ARC and RAE (Ta- ble 1).2 We also include the majority baseline (“baseline”) and MT (Madnani et al., 2012).”
Discriminative Improvements to Distributional Sentence Similarity (2013, methodology): “…identiﬁcation, we note three high-level approaches: (1) string similarity metrics such as n-gram overlap and BLEU score (Wan et al., 2006; Madnani et al., 2012), as well as string kernels (Bu et al., 2012); (2) syntactic operations on the parse structure (Wu, 2005; Das and Smith, 2009);…”
Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks (2015, methodology): “For POS embeddings, we run the Stanford POS tag-ger (Manning et al., 2014) on the English side of the Xinhua machine translation parallel corpus, which consists of Xinhua news articles with approximately 25 million words.”
Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016, methodology): “For example, n -gram overlap features at the word and character levels (Madnani et al., 2012; Wan et al., 2006), syntax features (Das and Smith, 2009; Xu et al., 2014), knowledge-based features using Word-Net (Fellbaum, 1998; Fern and Stevenson, 2008) and word-alignment features (Sultan et al.,…”
Evaluating Neural Word Representations in Tensor-Based Compositional Settings (2014, methodology): “The state-of-the art result (0.77 accuracy and 0.84 F-score7) by the time of this writing has been obtained using 8 machine translation metrics and three constituent classifiers (Madnani et al., 2012).”
MultiGranCNN: An Architecture for General Matching of Text Chunks on Multiple Levels of Granularity (2015, methodology): “Madnani et al. (2012) 2) performs better than ﬁne-tuning them; also, Table 3 shows that the best result is achieved if no convolution is used in mfCNN.”
Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering (2019, methodology): “Madnani et al. (2012) identify paraphrases by relying only on MT metrics as features.”
SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT) (2015, methodology): “These can be categorized into supervised methods (Qiu et al., 2006; Wan et al., 2006; Das and Smith, 2009; Socher et al., 2011; Blacoe and Lapata, 2012; Madnani et al., 2012; Ji and Eisenstein, 2013) and unsupervised methods (Mihalcea et al.”
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs (2021, methodology): “We verify SynPG on four paraphrase datasets: ParaNMT-50M (Wieting and Gimpel, 2018), Quora (Iyer et al., 2017), PAN (Madnani et al., 2012), and MRPC (Dolan et al., 2004).”
UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement (2016, methodology): “Traditional approaches are based on hand-crafted feature engineering (Wan et al., 2006; Madnani et al., 2012; Fellbaum, 1998; Fern and Stevenson, 2008; Das and Smith, 2009; Guo and Diab, 2012; Sultan et al., 2014; Kashyap et al., 2014; Lynum et al., 2014).”