arXiv subjects

Saket Dingliwal

Publications and source records attributed to Saket Dingliwal.

25 records · Page 2Linked to original sources

arXiv2021

Few Shot Dialogue State Tracking using Meta-learning

Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models, and datasets with significant (5-25%) improvement over the baseline in a low-data setting. Our proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.

cs.CL↗

arXiv2020

Covariate Distribution Aware Meta-learning

Meta-learning has proven to be successful for few-shot learning across the regression, classification, and reinforcement learning paradigms. Recent approaches have adopted Bayesian interpretations to improve gradient-based meta-learners by quantifying the uncertainty of the post-adaptation estimates. Most of these works almost completely ignore the latent relationship between the covariate distribution $(p(x))$ of a task and the corresponding conditional distribution $p(y|x)$. In this paper, we identify the need to explicitly model the meta-distribution over the task covariates in a hierarchical Bayesian framework. We begin by introducing a graphical model that leverages the samples from the marginal $p(x)$ to better infer the posterior over the optimal parameters of the conditional distribution $(p(y|x))$ for each task. Based on this model we propose a computationally feasible meta-learning algorithm by introducing meaningful relaxations in our final objective. We demonstrate the gains of our algorithm over initialization based meta-learning baselines on popular classification benchmarks. Finally, to understand the potential benefit of modeling task covariates we further evaluate our method on a synthetic regression dataset.

cs.LG↗

arXiv2020

Restructuring Conversations using Discourse Relations for Zero-shot Abstractive Dialogue Summarization

Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting these models to a new domain requires the availability of domain-specific manually annotated corpus created by linguistic experts. We propose a zero-shot abstractive dialogue summarization method that uses discourse relations to provide structure to conversations, and then uses an out-of-the-box document summarization model to create final summaries. Experiments on the AMI and ICSI meeting corpus, with document summarization models like PGN and BART, shows that our method improves the ROGUE score by up to 3 points, and even performs competitively against other state-of-the-art methods.

cs.CL↗

arXiv2020

Robust Handwriting Recognition with Limited and Noisy Data

Despite the advent of deep learning in computer vision, the general handwriting recognition problem is far from solved. Most existing approaches focus on handwriting datasets that have clearly written text and carefully segmented labels. In this paper, we instead focus on learning handwritten characters from maintenance logs, a constrained setting where data is very limited and noisy. We break the problem into two consecutive stages of word segmentation and word recognition respectively and utilize data augmentation techniques to train both stages. Extensive comparisons with popular baselines for scene-text detection and word recognition show that our system achieves a lower error rate and is more suited to handle noisy and difficult documents

cs.CV↗

arXiv2020

Finding Input Characterizations for Output Properties in ReLU Neural Networks

Deep Neural Networks (DNNs) have emerged as a powerful mechanism and are being increasingly deployed in real-world safety-critical domains. Despite the widespread success, their complex architecture makes proving any formal guarantees about them difficult. Identifying how logical notions of high-level correctness relate to the complex low-level network architecture is a significant challenge. In this project, we extend the ideas presented in and introduce a way to bridge the gap between the architecture and the high-level specifications. Our key insight is that instead of directly proving the safety properties that are required, we first prove properties that relate closely to the structure of the neural net and use them to reason about the safety properties. We build theoretical foundations for our approach, and empirically evaluate the performance through various experiments, achieving promising results than the existing approach by identifying a larger region of input space that guarantees a certain property on the output.

cs.LG↗

arXiv2020

Advances in Symmetry Breaking for SAT Modulo Theories

Symmetry breaking is a popular technique to reduce the search space for SAT solving by exploiting the underlying symmetry over variables and clauses in a formula. The key idea is to first identify sets of assignments which fall in the same symmetry class, and then impose ordering constraints, called Symmetry Breaking Predicates (SBPs), such that only one (or a small subset) of these assignments is allowed to be a solution of the original SAT formula. While this technique has been exploited extensively in the SAT literature, there is little work on using symmetry breaking for SAT Modulo Theories (SMT). In SMT, logical constraints in SAT theories are combined with another set of theory operations defined over non-Boolean variables such as integers, reals, etc. SMT solvers typically use a combination of SAT solving techniques augmented with calls to the theory solver. In this work, we take up the advances in SAT symmetry breaking and apply them to the domain of SMT. Our key technical contribution is the formulation of symmetry breaking over the Boolean skeleton variables, which are placeholders for actual theory operations in SMT solving. These SBPs are then applied over the SAT solving part of the SMT solver. We implement our SBP ideas on top of CVC4, which is a state-of-the-art SMT solver. Our approach can result in significantly faster solutions on several benchmark problems compared to the state-of-the-art. Our final solver is a hybrid of the original CVC4 solver, and an SBP based solver, and can solve up to 3.8% and 3.1% more problems in the QF_NIA category of 2018 and 2019 SMT benchmarks, respectively, compared to CVC4, the top performer in this category.

cs.LO↗

arXiv2019

Literature Survey on Finding Influential Communities in Large Scale Networks

Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs is a problem of considerable interest as it often accounts for the functionality of the system. We aim to provide a thorough exposition of the topic, including the main elements of the problem, a brief introduction of the existing research for both disjoint and overlapping community search, the idea of influential communities, its implications and the current state of the art and finally provide some insight on possible directions for future research.

cs.SI↗