paper-with-me

홈 › Papers

Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation

2019-06-01 · NAACL 2019 6 · Ashutosh Kumar, Satwik Bhattamishra, Bh, Manik ari, Partha Talukdar

Inducing diversity in the task of paraphrasing is an important problem in NLP with applications in data augmentation and conversational agents. Previous paraphrasing approaches have mainly focused on the issue of generating semantically similar paraphrases while paying little attention towards diversity. In fact, most of the methods rely solely on top-k beam search sequences to obtain a set of paraphrases. The resulting set, however, contains many structurally similar sentences. In this work, we focus on the task of obtaining highly diverse paraphrases while not compromising on paraphrasing quality. We provide a novel formulation of the problem in terms of monotone submodular function maximization, specifically targeted towards the task of paraphrasing. Additionally, we demonstrate the effectiveness of our method for data augmentation on multiple tasks such as intent classification and paraphrase recognition. In order to drive further research, we have made the source code available.

📄 PDF Abstract BibTeX

Code (1)

malllabiisc/DiPS 공식 구현 pytorch

Tasks

Data AugmentationDiversityintent-classificationIntent Classification

Similar Papers 제목 키워드 기반

Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification

2018-12-01 · Qi Lei, Lingfei Wu, Pin-Yu Chen, Alexandros G. Dimakis 외

Adversarial examples are carefully constructed modifications to an input that completely change the output of a classifier but are imperceptible to humans. Despite these successful attacks for continuous data (such as im…

Adversarial TextGeneral ClassificationSentencetext-classification+1

Fair Submodular Cover

2024-07-05 · Wenjing Chen, Shuo Xing, Samson Zhou, Victoria G. Crawford

Submodular optimization is a fundamental problem with many applications in machine learning, often involving decision-making over datasets with sensitive attributes such as gender or age. In such settings, it is often de…

Decision MakingFairness

Multi-objective Evolutionary Algorithms are Still Good: Maximizing Monotone Approximately Submodular Minus Modular Functions

2019-10-12 · Chao Qian

As evolutionary algorithms (EAs) are general-purpose optimization algorithms, recent theoretical studies have tried to analyze their performance for solving general problem classes, with the goal of providing a general t…

Evolutionary AlgorithmsExperimental Design

Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization

2016-06-22 · NeurIPS 2016 12 · Alexander Kirillov, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

We consider the problem of jointly inferring the M-best diverse labelings for a binary (high-order) submodular energy of a graphical model. Recently, it was shown that this problem can be solved to a global optimum, for …

Diversity

Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach

2022-06-08 · NeurIPS 2021 12 · Fan Yang, Kai He, Linxiao Yang, Hongxia Du 외

Rule sets are highly interpretable logical models in which the predicates for decision are expressed in disjunctive normal form (DNF, OR-of-ANDs), or, equivalently, the overall model comprises an unordered collection of …