Search Results for author: Sunita Sarawagi

Found 31 papers, 20 papers with code

Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding

no code implementations ACL 2022 Soumya Chatterjee, Sunita Sarawagi, Preethi Jyothi

Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded.

Machine Translation Translation

Long Range Probabilistic Forecasting in Time-Series using High Order Statistics

1 code implementation5 Nov 2021 Prathamesh Deshpande, Sunita Sarawagi

Long range forecasts are the starting point of many decision support systems that need to draw inference from high-level aggregate patterns on forecasted values.

Time Series Time Series Forecasting

Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time

1 code implementation NeurIPS 2021 Anshul Nasery, Soumyadeep Thakur, Vihari Piratla, Abir De, Sunita Sarawagi

In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the train and test distributions.

Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations

1 code implementation NeurIPS 2021 Vihari Piratla, Soumen Chakrabarty, Sunita Sarawagi

Our goal is to evaluate the accuracy of a black-box classification model, not as a single aggregate on a given test data distribution, but as a surface over a large number of combinations of attributes characterizing multiple test data distributions.

Training Data Augmentation for Code-Mixed Translation

1 code implementation NAACL 2021 Abhirut Gupta, Aditya Vavre, Sunita Sarawagi

Machine translation of user-generated code-mixed inputs to English is of crucial importance in applications like web search and targeted advertising.

Data Augmentation Machine Translation +1

Deep Indexed Active Learning for Matching Heterogeneous Entity Representations

1 code implementation8 Apr 2021 Arjit Jain, Sunita Sarawagi, Prithviraj Sen

We propose DIAL, a scalable active learning approach that jointly learns embeddings to maximize recall for blocking and accuracy for matching blocked pairs.

Active Learning Entity Resolution +1

Error-driven Fixed-Budget ASR Personalization for Accented Speakers

1 code implementation4 Mar 2021 Abhijeet Awasthi, Aman Kansal, Sunita Sarawagi, Preethi Jyothi

We consider the task of personalizing ASR models while being constrained by a fixed budget on recording speaker-specific utterances.

Missing Value Imputation on Multidimensional Time Series

no code implementations2 Mar 2021 Parikshit Bansal, Prathamesh Deshpande, Sunita Sarawagi

Missing values are commonplace in decision support platforms that aggregate data over long time stretches from disparate sources, and reliable data analytics calls for careful handling of missing data.

Imputation Time Series

Long Horizon Forecasting With Temporal Point Processes

1 code implementation8 Jan 2021 Prathamesh Deshpande, Kamlesh Marathe, Abir De, Sunita Sarawagi

In recent years, marked temporal point processes (MTPPs) have emerged as a powerful modeling machinery to characterize asynchronous events in a wide variety of applications.

Point Processes

What's in a Name? Are BERT Named Entity Representations just as Good for any other Name?

no code implementations WS 2020 Sriram Balasubramanian, Naman jain, Gaurav Jindal, Abhijeet Awasthi, Sunita Sarawagi

We evaluate named entity representations of BERT-based NLP models by investigating their robustness to replacements from the same typed class in the input.

Black-box Adaptation of ASR for Accented Speech

1 code implementation24 Jun 2020 Kartik Khandelwal, Preethi Jyothi, Abhijeet Awasthi, Sunita Sarawagi

Accordingly, we propose a novel coupling of an open-source accent-tuned local model with the black-box service where the output from the service guides frame-level inference in the local model.


Learning from Rules Generalizing Labeled Exemplars

2 code implementations ICLR 2020 Abhijeet Awasthi, Sabyasachi Ghosh, Rasna Goyal, Sunita Sarawagi

Empirical evaluation on five different tasks shows that (1) our algorithm is more accurate than several existing methods of learning from a mix of clean and noisy supervision, and (2) the coupled rule-exemplar supervision is effective in denoising rules.


Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units

1 code implementation24 Jun 2019 Prathamesh Deshpande, Sunita Sarawagi

We present ARU, an Adaptive Recurrent Unit for streaming adaptation of deep globally trained time-series forecasting models.

Time Series Time Series Forecasting

Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings

1 code implementation ACL 2019 Vihari Piratla, Sunita Sarawagi, Soumen Chakrabarti

Given a small corpus $\mathcal D_T$ pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of $\mathcal D_T$.

Calibration of Encoder Decoder Models for Neural Machine Translation

no code implementations3 Mar 2019 Aviral Kumar, Sunita Sarawagi

We study the calibration of several state of the art neural machine translation(NMT) systems built on attention-based encoder-decoder models.

Machine Translation Translation

Surprisingly Easy Hard-Attention for Sequence to Sequence Learning

1 code implementation EMNLP 2018 Shiv Shankar, Siddhant Garg, Sunita Sarawagi

In this paper we show that a simple beam approximation of the joint distribution between attention and output is an easy, accurate, and efficient attention mechanism for sequence to sequence learning.

Hard Attention Image Captioning +2

Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings

1 code implementation ICML 2018 Aviral Kumar, Sunita Sarawagi, Ujjwal Jain

Modern neural networks have recently been found to be poorly calibrated, primarily in the direction of over-confidence.

Labeled Memory Networks for Online Model Adaptation

no code implementations5 Jul 2017 Shiv Shankar, Sunita Sarawagi

In this paper, we establish their potential in online adapting a batch trained neural network to domain-relevant labeled data at deployment time.

Few-Shot Learning

Length bias in Encoder Decoder Models and a Case for Global Conditioning

no code implementations EMNLP 2016 Pavel Sountsov, Sunita Sarawagi

Encoder-decoder networks are popular for modeling sequences probabilistically in many applications.

Occurrence Statistics of Entities, Relations and Types on the Web

no code implementations14 May 2016 Aman Madaan, Sunita Sarawagi

This is owing to the severe mismatch in the distributions of such entities on the web and in the relatively diminutive training data.

Entity Disambiguation

Cannot find the paper you are looking for? You can Submit a new open access paper.