Paraphrase Generation Task

A Paraphrase Generation Task is a linguistic generation task of linguistic passages that are in a paraphrase relation with an input passage.

• Context:
  • It can be solved by a Paraphrase Generation System (that implements a paraphrase generation algorithm).
• Example(s):
  • GenerateParaphrase(“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.”.
  • Controllable Paraphrasing (Chen et al., 2019).
  • …
• Counter-Example(s):
  • Paraphrase Identification.
  • Text Summarization.
• See: Semantic Identity, Paraphrase.

---

---

References

2019

• (Chen et al., 2019) ⇒ Mingda Chen, Qingming Tang, Sam Wiseman, and Kevin Gimpel. (2019). “Controllable Paraphrase Generation with a Syntactic Exemplar.” In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5972-5984.
  • ABSTRACT: Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel task, where the syntax of a generated sentence is controlled rather by a sentential exemplar. To evaluate quantitatively with standard metrics, we create a novel dataset with human annotations. We also develop a variational model with a neural module specifically designed for capturing syntactic knowledge and several multitask training objectives to promote disentangled representation learning. Empirically, the proposed model is observed to achieve improvements over baselines and learn to capture desirable characteristics.
  • QUOTE: ... Controllable text generation has recently become an area of intense focus in the natural language processing (NLP) community. Recent work has focused both on generating text satisfying certain stylistic requirements such as being formal or exhibiting a particular sentiment (Hu et al., 2017; Shen et al., 2017; Ficler and Goldberg, 2017), as well as on generating text meeting structural requirements, such as conforming to a particular template (Iyyer et al., 2018;Wiseman et al., 2018). ...

X: his teammates’ eyes got an ugly, hostile expression.
Y: the smell of flowers was thick and sweet.
Z: the eyes of his teammates had turned ugly and hostile.

X: we need to further strengthen the agency’s capacities.
Y: the damage in this area seems to be quite minimal.
Z: the capacity of this office needs to be reinforced even further.

2018

• (Gupta et al., 2018) ⇒ Ankush Gupta, Arvind Agarwal, Prawaan Singh, and Piyush Rai. (2018). “A Deep Generative Framework for Paraphrase Generation.” In: Thirty-Second AAAI Conference on Artificial Intelligence.
  • ABSTRACT: Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generating paraphrases automatically. Our proposed method is based on a combination of deep generative models (VAE) with sequence-to-sequence models (LSTM) to generate paraphrases, given an input sentence. Traditional VAEs when combined with recurrent neural networks can generate free text but they are not suitable for paraphrase generation for a given sentence. We address this problem by conditioning the both, encoder and decoder sides of VAE, on the original sentence, so that it can generate the given sentence's paraphrases. Unlike most existing models, our model is simple, modular and can generate multiple paraphrases, for a given sentence. Quantitative evaluation of the proposed method on a benchmark paraphrase dataset demonstrates its efficacy, and its performance improvement over the state-of-the-art methods by a significant margin, whereas qualitative human evaluation indicate that the generated paraphrases are well-formed, grammatically correct, and are relevant to the input sentence. Furthermore, we evaluate our method on a newly released question paraphrase dataset, and establish a new baseline for future research.

2016

• (Prakash et al., 2016) ⇒ Aaditya Prakash, Sadid A. Hasan, Kathy Lee, Vivek Datla, Ashequl Qadir, Joey Liu, and Oladimeji Farri. (2016). “Neural Paraphrase Generation with Stacked Residual LSTM Networks.” In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2923-2934.
  • ABSTRACT: In this paper, we propose a novel neural approach for paraphrase generation. Conventional paraphrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To the best of our knowledge, this work is the first to explore deep learning models for paraphrase generation. Our primary contribution is a stacked residual LSTM network, where we add residual connections between LSTM layers. This allows for efficient training of deep LSTMs. We evaluate our model and other state-of-the-art deep learning models on three different datasets: PPDB, WikiAnswers and MSCOCO. Evaluation results demonstrate that our model outperforms sequence to sequence, attention-based and bi- directional LSTM models on BLEU, METEOR, TER and an embedding-based sentence similarity metric.

---