Controllable Paraphrase Generation with a Syntactic Exemplar

By Mingda Chen, Qingming Tang, Sam Wiseman, Kevin Gimpel. 2019

116 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, 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 Natural Language Processing

Citations in the corpus

Tailor: Generating and Perturbing Text with Semantic Controls (2021, background): “Recent works incorporating syntactic structures for paraphrasing (Iyyer et al., 2018; Chen et al., 2019; Bao et al., 2019; Kumar et al., 2020; Sun et al., 2021; Huang and Chang, 2021) or discrete semantic signatures for diverse generation (Weir et al., 2020) are similar to T ailor in their…”
Syntax-Guided Controlled Generation of Paraphrases (2020, methodology): “During training , each terminal node in the tree C Y , pruned at H, is equipped with information about the span of words it needs to generate.”
Reformulating Unsupervised Style Transfer as Paraphrase Generation (2020, methodology): “Syntax can also be controlled using an exemplar sentence (Chen et al., 2019; Guu et al., 2018; Peng et al., 2019).”
A Survey of Knowledge-enhanced Text Generation (2020, background): “, an article) [43, 149] [81] Machine Sentence [152, 174] - [31, 124] - [103, 177] [1, 6] [15, 165] translation [131] Content Document [83] - - [41, 67, 150] - manipulation Content Document [46, 90] - - [22, 73] paraphrasing”
Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model (2023, background): “Recent works emphasize the importance of syntactic control in paraphrase generation, allowing the model to generate an output paraphrase tailored to users’ need (Chen et al., 2019).”
AESOP: Paraphrase Generation with Adaptive Syntactic Control (2021, methodology): “After qualitative checks, we share the same ﬁnding with previous works (Kumar et al., 2020; Chen et al., 2019a) that SCPN tends to strictly adhere to syntactic parses at the cost of semantics.”
Paraphrase Generation: A Survey of the State of the Art (2021, background): “Meth-ods in the ﬁrst class ﬁrst encode the syntax tree of an exemplar sentence into a list of vector representations and then feed them into decoder at each timestep when decoding (Iyyer et al., 2018; Chen et al., 2019; Goyal and Durrett, 2020; Kumar et al., 2020).”
Compound Probabilistic Context-Free Grammars for Grammar Induction (2019, methodology): “It is possible that the model is utilizing the subtrees to capture broad template-like structures and then using z to ﬁll them in, similar to recent works that also train models to separate “what to say” from “how to say it” (Wiseman et al., 2018; Peng et al., 2019; Chen et al., 2019a,b).”
An Empirical Survey of Data Augmentation for Limited Data Learning in NLP (2021, background): “…work focuses on directly training end-to-end models to generate paraphrases (Prakash et al., 2016), and further augments the decoding phase with syntactic information (Iyyer et al., 2018; Chen et al., 2019), latent variables (Gupta et al., 2017), and sub-modular objectives (Kumar et al., 2019).”