mlsanityData to 14 Oct 2026

DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation

arXiv 2107.05380 ↗First posted 7 Jul 2021cs.CL cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper we study test time decoding; an ubiquitous step in almost all sequential text generation task spanning across a wide array of natural language processing (NLP) problems. Our main contribution is to develop a continuous relaxation framework for the combinatorial NP-hard decoding problem and propose Disco - an efficient algorithm based on standard first order gradient based. We provide tight analysis and show that our proposed algorithm linearly converges to within ε neighborhood of the optima. Finally, we perform preliminary experiments on the task of adversarial text generation and show superior performance of Disco over several popular decoding approaches.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 33 references that are in the map. First posted on arXiv 7 Jul 2021.

Builds on

13 of 33 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  5. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  7. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  8. 2018Generating Natural Language Adversarial Examplescited by 424
  9. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 286
  10. 2014SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimationcited by 172
  11. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 140
  12. 2014word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding methodcited by 112
1 more
  1. 2017Deep Submodular Functionscited by 12

Built on by

Not cited yet.