arXiv subjects

Duy Nguyen

Publications and source records attributed to Duy Nguyen.

41 records · Page 3Linked to original sources

arXiv2020

Adaptive Name Entity Recognition under Highly Unbalanced Data

For several purposes in Natural Language Processing (NLP), such as Information Extraction, Sentiment Analysis or Chatbot, Named Entity Recognition (NER) holds an important role as it helps to determine and categorize entities in text into predefined groups such as the names of persons, locations, quantities, organizations or percentages, etc. In this report, we present our experiments on a neural architecture composed of a Conditional Random Field (CRF) layer stacked on top of a Bi-directional LSTM (BI-LSTM) layer for solving NER tasks. Besides, we also employ a fusion input of embedding vectors (Glove, BERT), which are pre-trained on the huge corpus to boost the generalization capacity of the model. Unfortunately, due to the heavy unbalanced distribution cross-training data, both approaches just attained a bad performance on less training samples classes. To overcome this challenge, we introduce an add-on classification model to split sentences into two different sets: Weak and Strong classes and then designing a couple of Bi-LSTM-CRF models properly to optimize performance on each set. We evaluated our models on the test set and discovered that our method can improve performance for Weak classes significantly by using a very small data set (approximately 0.45\%) compared to the rest classes.

cs.CL↗

arXiv2016

Fast learning rates with heavy-tailed losses

We study fast learning rates when the losses are not necessarily bounded and may have a distribution with heavy tails. To enable such analyses, we introduce two new conditions: (i) the envelope function $\sup_{f \in \mathcal{F}}|\ell \circ f|$, where $\ell$ is the loss function and $\mathcal{F}$ is the hypothesis class, exists and is $L^r$-integrable, and (ii) $\ell$ satisfies the multi-scale Bernstein's condition on $\mathcal{F}$. Under these assumptions, we prove that learning rate faster than $O(n^{-1/2})$ can be obtained and, depending on $r$ and the multi-scale Bernstein's powers, can be arbitrarily close to $O(n^{-1})$. We then verify these assumptions and derive fast learning rates for the problem of vector quantization by $k$-means clustering with heavy-tailed distributions. The analyses enable us to obtain novel learning rates that extend and complement existing results in the literature from both theoretical and practical viewpoints.

stat.ML↗

arXiv2015

The Data Reduction Pipeline for the Apache Point Observatory Galactic Evolution Experiment

The Apache Point Observatory Galactic Evolution Experiment (APOGEE), part of the Sloan Digital Sky Survey III, explores the stellar populations of the Milky Way using the Sloan 2.5-m telescope linked to a high resolution (R~22,500), near-infrared (1.51-1.70 microns) spectrograph with 300 optical fibers. For over 150,000 predominantly red giant branch stars that APOGEE targeted across the Galactic bulge, disks and halo, the collected high S/N (>100 per half-resolution element) spectra provide accurate (~0.1 km/s) radial velocities, stellar atmospheric parameters, and precise (~0.1 dex) chemical abundances for about 15 chemical species. Here we describe the basic APOGEE data reduction software that reduces multiple 3D raw data cubes into calibrated, well-sampled, combined 1D spectra, as implemented for the SDSS-III/APOGEE data releases (DR10, DR11 and DR12). The processing of the near-IR spectral data of APOGEE presents some challenges for reduction, including automated sky subtraction and telluric correction over a 3 degree diameter field and the combination of spectrally dithered spectra. We also discuss areas for future improvement.

astro-ph.IM↗

arXiv2015

Learning From Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers

We prove new fast learning rates for the one-vs-all multiclass plug-in classifiers trained either from exponentially strongly mixing data or from data generated by a converging drifting distribution. These are two typical scenarios where training data are not iid. The learning rates are obtained under a multiclass version of Tsybakov's margin assumption, a type of low-noise assumption, and do not depend on the number of classes. Our results are general and include a previous result for binary-class plug-in classifiers with iid data as a special case. In contrast to previous works for least squares SVMs under the binary-class setting, our results retain the optimal learning rate in the iid case.

stat.ML↗

arXiv2012

Verifying Search Results Over Web Collections

Searching accounts for one of the most frequently performed computations over the Internet as well as one of the most important applications of outsourced computing, producing results that critically affect users' decision-making behaviors. As such, verifying the integrity of Internet-based searches over vast amounts of web contents is essential. We provide the first solution to this general security problem. We introduce the concept of an authenticated web crawler and present the design and prototype implementation of this new concept. An authenticated web crawler is a trusted program that computes a special "signature" $s$ of a collection of web contents it visits. Subject to this signature, web searches can be verified to be correct with respect to the integrity of their produced results. This signature also allows the verification of complicated queries on web pages, such as conjunctive keyword searches. In our solution, along with the web pages that satisfy any given search query, the search engine also returns a cryptographic proof. This proof, together with the signature $s$, enables any user to efficiently verify that no legitimate web pages are omitted from the result computed by the search engine, and that no pages that are non-conforming with the query are included in the result. An important property of our solution is that the proof size and the verification time both depend solely on the sizes of the query description and the query result, but not on the number or sizes of the web pages over which the search is performed. Our authentication protocols are based on standard Merkle trees and the more involved bilinear-map accumulators. As we experimentally demonstrate, the prototype implementation of our system gives a low communication overhead between the search engine and the user, and allows for fast verification of the returned results on the user side.

cs.CR↗