Paraphrase Detection Task

A Paraphrase Detection Task is a semantic detection task for linguistic sentences in a paraphrase relation.

• Context:
  • It can be solved by a Paraphrase Detection System (that implements a paraphrase detection algorithm).
• Example(s):
  • IsParaphrase(“Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence.”;
    “Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence.”
    ) ⇒ true
  • based on Microsoft Research Paraphrase Corpus.
  • based on DIRT Paraphrase Collection.
  • based on Sekine's Paraphrase Database.
  • …
• Counter-Example(s):
  • Paraphrase Generation.
  • Text Summarization.
• See: Semantic Identity, Paraphrase.

---

---

References

2018

• https://aclweb.org/aclwiki/Paraphrase_Identification_(State_of_the_art)
• source: Microsoft Research Paraphrase Corpus (MSRP)
• task: given a pair of sentences, classify them as paraphrases or not paraphrases
• see: Dolan et al. (2004).
• train: 4,076 sentence pairs (2,753 positive: 67.5%)
• test: 1,725 sentence pairs (1,147 positive: 66.5%)
• see also: Similarity (State of the art)

Sample data

• Sentence 1: Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence.
• Sentence 2: Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence.
• Class: 1 (true paraphrase)

2015a

• (Yin & Schütze, 2015) ⇒ Wenpeng Yin, and Hinrich Schütze. (2015). “Convolutional Neural Network for Paraphrase Identification.” In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 901-911.

2015

• (Kiros et al., 2015) ⇒ Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard S. Zemel, Antonio Torralba, Raquel Urtasun, and Sanja Fidler. (2015). “Skip-thought Vectors.” In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS-2015).
  • QUOTE: We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets.

2011

• (Socher et al., 2011) ⇒ Richard Socher, Eric H. Huang, Jeffrey Pennin, Christopher D. Manning, and Andrew Y. Ng. (2011). “Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection.” In: Advances in Neural Information Processing Systems, pp. 801-809.

2009

• (Das & Smith, 2009) ⇒ Dipanjan Das, and Noah A. Smith. (2009). “Paraphrase Identification As Probabilistic Quasi-synchronous Recognition.” In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL/IJCNLP-2009).

2004

• (Dolan et al., 2004) ⇒ Bill Dolan, Chris Quirk, and Chris Brockett. (2004). “Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources.” In: Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004).

---