Paraphrase Identification as Probabilistic Quasi-Synchronous Recognition

By Dipanjan Das, Noah A. Smith. 2009

231 citations recorded by the source corpus.

We present a novel approach to deciding whether two sentences hold a paraphrase relationship. We employ a generative model that generates a paraphrase of a given sentence, and we use probabilistic inference to reason about whether two sentences share the paraphrase relationship. The model cleanly incorporates both syntax and lexical semantics using quasi-synchronous dependency grammars (Smith and Eisner, 2006). Furthermore, using a product of experts (Hinton, 2002), we combine the model with a complementary logistic regression model based on state-of-the-art lexical overlap features. We evaluate our models on the task of distinguishing true paraphrase pairs from false ones on a standard corpus, giving competitive state-of-the-art performance.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

A Decomposable Attention Model for Natural Language Inference (2016, methodology): “Our method is motivated by the central role played by alignment in machine translation (Koehn, 2009) and previous approaches to sentence similarity modeling (Haghighi et al., 2005; Das and Smith, 2009; Chang et al., 2010; Fader et al., 2013).”
Skip-Thought Vectors (2015, neutral): “7 PE [26] 76.”
Semantic Parsing via Paraphrasing (2014, methodology): “The NLP paraphrase literature is vast and ranges from simple methods employing surface features (Wan et al., 2006), through vector space models (Socher et al., 2011), to latent variable models (Das and Smith, 2009; Wang and Manning, 2010; Stern and Dagan, 2011).”
Convolutional Neural Network for Paraphrase Identification (2015, methodology): “We use the Microsoft Research Paraphrase Corpus (MSRP) (Dolan et al., 2004; Das and Smith, 2009).”
Discriminative Improvements to Distributional Sentence Similarity (2013, background): “…(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); and (3) distributional methods, such as latent semantic analysis (LSA; Landauer et al., 1998), which are most relevant to our work.”
Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks (2015, methodology): “Adding POS embeddings is expected to retain syntactic information which is reported to be effective for paraphrase identification (Das and Smith, 2009).”
Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016, methodology): “, 2006), syntax features (Das and Smith, 2009; Xu et al., 2014), knowledge-based features using WordNet (Fellbaum, 1998; Fern and Stevenson, 2008) and word-alignment features (Sultan et al.”
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; Mad-nani et al., 2012; Ji and Eisenstein, 2013) and unsupervised methods (Mihalcea et al., 2006; Rus et al., 2008; Fernando and Stevenson, 2008;…”
Semantic Matching in Search (2014, background): “These include collaborative filtering [101, 1, 2, 102, 45, 149, 9, 44], image annotation [83, 76, 159], paraphrasing and textual entailment [62, 54, 139, 203, 55, 85, 165, 35], question answering [37, 126, 21, 205, 178, 130], cross-language information retrieval [64, 141, 140], short text conversati”
Title Generation with Quasi-Synchronous Grammar (2010, methodology): “In our experiments, we obtain this combined representation from the output of the Stanford parser (Klein and Manning, 2003) but any other broadly similar parser could be used instead.”
Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering (2019, methodology): “We frame the ﬁne-tuning task as para-phrase identiﬁcation (Das and Smith, 2009), where given a pair of sentences, the task is to classify them as paraphrases or non-paraphrases. sentence in P ARA NMT-5 M , the sentence embed-dings generated by the WORD model trained in § 3.7. approximate For each…”
Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection (2011, background): “Most recently, Das and Smith [15] adopted the idea that paraphrases have related syntactic structure.”
Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions (2010, methodology): “, Gildea, 2003; Smith and Eisner, 2006; inter alia), and such methods have been applied successfully to semantic tasks (de Marneffe et al., 2006; Wang et al., 2007; Das and Smith, 2009).”
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).”
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features (2014, unknown): “This notation is summarized in Table 1.”
Re-examining Machine Translation Metrics for Paraphrase Identification (2012, methodology): “Das and Smith (2009) use an explicit model of alignment be-tween the corresponding parts of two paraphrastic sentences and combine it with a logistic regression classiﬁer built from n -gram overlap features.”
Discriminative Learning over Constrained Latent Representations (2010, background): “Note that LCLR outperforms (Das and Smith, 2009), which is a speciﬁcally designed joint approach for this task. for the RTE system and are summarized in Table 2.”