Adversarial Example Generation with Syntactically Controlled
            Paraphrase Networks

Iyyer, Mohit; Wieting, John; Gimpel, Kevin; Zettlemoyer, Luke

doi:10.18653/v1/n18-1170

Cited by 475 publications

(445 citation statements)

References 41 publications

Supporting

Mentioning

444

Contrasting

Order By: Relevance

“…The works (Samanta & Mehta, 2017;Iyyer et al, 2018) start to craft adversarial sentences that grammatically correct and maintain the syntax structure of the original sentence. The work in (Samanta & Mehta, 2017) achieves this by using synonyms to replace original words, or adding some words which have different meanings in different contexts.…”

Section: Attacking Words and Lettersmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Liu

et al. 2020

Int. J. Autom. Comput.

441

204

View full text Add to dashboard Cite

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text.

show abstract

Section: Attacking Words and Lettersmentioning

confidence: 99%

“…The work in (Samanta & Mehta, 2017) achieves this by using synonyms to replace original words, or adding some words which have different meanings in different contexts. On the other hand, the work (Iyyer et al, 2018) manages to fool the text classifier by paraphrasing the structure of sentences.…”

Section: Attacking Words and Lettersmentioning

confidence: 99%

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Liu

et al. 2020

Int. J. Autom. Comput.

441

204

View full text Add to dashboard Cite

show abstract

“…The first two baselines directly output the corresponding syntactic or semantic input for each instance. For the last baseline, we consider SCPN (Iyyer et al, 2018). As SCPN requires parse trees for both the syntactic and semantic inputs, we follow the process in their paper and use the Stanford shiftreduce constituency parser to parse both, then use the parsed sentences as inputs to SCPN.…”

Section: Baselinesmentioning

confidence: 99%

“…These systems can be used in various application areas, such as text summarization (Fan et al, 2018), adversarial example generation (Iyyer et al, 2018), dialogue (Niu and Bansal, 2018), and data-to-document generation (Wiseman et al, 2018). However, prior work on controlled generation has typically assumed a known, finite set of values that the controlled attribute can take on.…”

Section: Introductionmentioning

confidence: 99%

Controllable Paraphrase Generation with a Syntactic Exemplar

Chen

Tang

Wiseman

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

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. 1 arXiv:1906.00565v1 [cs.CL] 3 Jun 2019Encoders. At test time, we want to have different combinations of semantic and syntactic inputs, which naturally suggests separate parameterizations for q φ (y|x) and q φ (z|x). Specifically, q φ (y|x) is parameterized by a word averaging encoder followed by a three-layer feedforward neural network since it has been observed that word averaging encoders perform surprisingly well for semantic tasks (Wieting et al., 2016). q φ (z|x) is parameterized by a bidirectional long short-term memory network (LSTM; Hochreiter and Schmidhuber, 1997) also followed by a three-layer feedforward neural network, where we concatenate the forward and backward vectors produced by the biLSTM and then take the average of these vectors.Decoders. As shown in Figure 3, at each time step, we concatenate the syntactic variable z with the previous word's embedding as the input to the

show abstract

“…Stylistic control is important as a way to address a well-known limitation of vanilla neural NLG models, namely that they reduce the stylistic variation seen in the input, and thus produce outputs that tend to be dull and repetitive (Li et al, 2016). The majority of other work on stylistic control has been done in a text-to-text setting where MRs and corpora with fixed meaning and varying style are not available (Fan et al, 2017;Iyyer et al, 2018;Wiseman et al, 2018;Ficler and Goldberg, 2017). Sometimes variation is evaluated in terms of model performance in some other task, such as machine translation or summarization.…”

Section: Related Workmentioning

confidence: 99%

Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast

Harrison¹,

Reed²,

Oraby³

et al. 2019

Proceedings of the 1st Workshop on Discourse Structure in Neural NLG

View full text Add to dashboard Cite

Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused solely on the semantic fidelity of outputs, recent work has started to explore methods for controlling the style of the generated text while simultaneously achieving semantic accuracy. Here we experiment with two stylistic benchmark tasks, generating language that exhibits variation in personality, and generating discourse contrast. We report a huge performance improvement in both stylistic control and semantic accuracy over the state of the art on both of these benchmarks. We test several different models and show that putting stylistic conditioning in the decoder and eliminating the semantic re-ranker used in earlier models results in more than 15 points higher BLEU for Personality, with a reduction of semantic error to near zero. We also report an improvement from .75 to .81 in controlling contrast and a reduction in semantic error from 16% to 2%.

show abstract

Adversarial Example Generation with Syntactically Controlled Paraphrase Networks

Cited by 475 publications

References 41 publications

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Controllable Paraphrase Generation with a Syntactic Exemplar

Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast

Contact Info

Product

Resources

About