Search Results for author:
Found 38 papers, 24 papers with code
Parallel Iterative Edit Models for Local Sequence Transduction
We present a Parallel Iterative Edit (PIE) model for the problem of local sequence transduction arising in tasks like Grammatical error correction (GEC).
Ranked #13 on
Grammatical Error Correction
on CoNLL-2014 Shared Task
Grammatical Error Correction
Optical Character Recognition (OCR)
Learning from Rules Generalizing Labeled Exemplars
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.
Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
The domain specific components are discarded after training and only the common component is retained.
Ranked #1 on
Domain Generalization
on LipitK
Missing Value Imputation on Multidimensional Time Series
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.
Generalizing Across Domains via Cross-Gradient Training
We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains.
Ranked #83 on
Domain Generalization
on PACS
Long Horizon Forecasting With Temporal Point Processes
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.
Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings
Modern neural networks have recently been found to be poorly calibrated, primarily in the direction of over-confidence.
Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts
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.
Deep Indexed Active Learning for Matching Heterogeneous Entity Representations
We propose DIAL, a scalable active learning approach that jointly learns embeddings to maximize recall for blocking and accuracy for matching blocked pairs.
Surprisingly Easy Hard-Attention for Sequence to Sequence Learning
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.
Error-driven Fixed-Budget ASR Personalization for Accented Speakers
We consider the task of personalizing ASR models while being constrained by a fixed budget on recording speaker-specific utterances.
Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time
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.
Data Programming using Continuous and Quality-Guided Labeling Functions
Scarcity of labeled data is a bottleneck for supervised learning models.
Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages
This results in improved zero-shot transfer from related HRLs to LRLs without reducing HRL representation and accuracy.
CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL
Standard dense retrieval techniques are inadequate for schema subsetting of a large structured database, where the correct semantics of retrieval demands that we rank sets of schema elements rather than individual elements.
Focus on the Common Good: Group Distributional Robustness Follows
We consider the problem of training a classification model with group annotated training data.
Benchmarking and Improving Text-to-SQL Generation under Ambiguity
Research in Text-to-SQL conversion has been largely benchmarked against datasets where each text query corresponds to one correct SQL.
Black-box Adaptation of ASR for Accented Speech
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.
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study
RelateLM uses transliteration to convert the unseen script of limited LRL text into the script of a Related Prominent Language (RPL) (Hindi in our case).
Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations
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.
Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings
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 $\mathcal D_T$.
Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units
We present ARU, an Adaptive Recurrent Unit for streaming adaptation of deep globally trained time-series forecasting models.
Training Data Augmentation for Code-Mixed Translation
Machine translation of user-generated code-mixed inputs to English is of crucial importance in applications like web search and targeted advertising.
ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting
Accurate demand forecasts can help on-line retail organizations better plan their supply-chain processes.
Labeled Memory Networks for Online Model Adaptation
In this paper, we establish their potential in online adapting a batch trained neural network to domain-relevant labeled data at deployment time.
Length bias in Encoder Decoder Models and a Case for Global Conditioning
Encoder-decoder networks are popular for modeling sequences probabilistically in many applications.
Occurrence Statistics of Entities, Relations and Types on the Web
This is owing to the severe mismatch in the distributions of such entities on the web and in the relatively diminutive training data.
Posterior Attention Models for Sequence to Sequence Learning
Modern neural architectures critically rely on attention for mapping structured inputs to sequences.
Calibration of Encoder Decoder Models for Neural Machine Translation
We study the calibration of several state of the art neural machine translation(NMT) systems built on attention-based encoder-decoder models.
What's in a Name? Are BERT Named Entity Representations just as Good for any other Name?
We evaluate named entity representations of BERT-based NLP models by investigating their robustness to replacements from the same typed class in the input.
NLP Service APIs and Models for Efficient Registration of New Clients
Each client uses an unsupervised, corpus-based sketch to register to the service.
Adaptive Discounting of Implicit Language Models in RNN-Transducers
RNN-Transducer (RNN-T) models have become synonymous with streaming end-to-end ASR systems.
Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding
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.
Bootstrapping Multilingual Semantic Parsers using Large Language Models
Despite cross-lingual generalization demonstrated by pre-trained multilingual models, the translate-train paradigm of transferring English datasets across multiple languages remains to be a key mechanism for training task-specific multilingual models.
Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers
Text-to-SQL parsers typically struggle with databases unseen during the train time.
Structured Case-based Reasoning for Inference-time Adaptation of Text-to-SQL parsers
To the best of our knowledge, we are the first to attempt inference-time adaptation of Text-to-SQL models, and harness trainable structured similarity between subqueries.
Improving RNN-Transducers with Acoustic LookAhead
RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities.
Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing
The main challenge in this estimation task is the potential confounding of treatment assignment with an individual's covariates in the training data, whereas during inference ICTE requires prediction on independently sampled treatments.
