arXiv subjects

Gautam Singh

Publications and source records attributed to Gautam Singh.

24 records · Page 2Linked to original sources

arXiv2018

Mining Procedures from Technical Support Documents

Guided troubleshooting is an inherent task in the domain of technical support services. When a customer experiences an issue with the functioning of a technical service or a product, an expert user helps guide the customer through a set of steps comprising a troubleshooting procedure. The objective is to identify the source of the problem through a set of diagnostic steps and observations, and arrive at a resolution. Procedures containing these set of diagnostic steps and observations in response to different problems are common artifacts in the body of technical support documentation. The ability to use machine learning and linguistics to understand and leverage these procedures for applications like intelligent chatbots or robotic process automation, is crucial. Existing research on question answering or intelligent chatbots does not look within procedures or deep-understand them. In this paper, we outline a system for mining procedures from technical support documents. We create models for solving important subproblems like extraction of procedures, identifying decision points within procedures, identifying blocks of instructions corresponding to these decision points and mapping instructions within a decision block. We also release a dataset containing our manual annotations on publicly available support documents, to promote further research on the problem.

cs.AI↗

arXiv2018

Generating Clues for Gender based Occupation De-biasing in Text

Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically. However, these AI models also learn gender, racial and ethnic biases present in the training data. In this paper, we present the first system that discovers the possibility that a given text portrays a gender stereotype associated with an occupation. If the possibility exists, the system offers counter-evidences of opposite gender also being associated with the same occupation in the context of user-provided geography and timespan. The system thus enables text de-biasing by assisting a human-in-the-loop. The system can not only act as a text pre-processor before training any AI model but also help human story writers write stories free of occupation-level gender bias in the geographical and temporal context of their choice.

cs.CL↗

arXiv2017

Fast Nearest-Neighbor Classification using RNN in Domains with Large Number of Classes

In scenarios involving text classification where the number of classes is large (in multiples of 10000s) and training samples for each class are few and often verbose, nearest neighbor methods are effective but very slow in computing a similarity score with training samples of every class. On the other hand, machine learning models are fast at runtime but training them adequately is not feasible using few available training samples per class. In this paper, we propose a hybrid approach that cascades 1) a fast but less-accurate recurrent neural network (RNN) model and 2) a slow but more-accurate nearest-neighbor model using bag of syntactic features. Using the cascaded approach, our experiments, performed on data set from IT support services where customer complaint text needs to be classified to return top-$N$ possible error codes, show that the query-time of the slow system is reduced to $1/6^{th}$ while its accuracy is being improved. Our approach outperforms an LSH-based baseline for query-time reduction. We also derive a lower bound on the accuracy of the cascaded model in terms of the accuracies of the individual models. In any two-stage approach, choosing the right number of candidates to pass on to the second stage is crucial. We prove a result that aids in choosing this cutoff number for the cascaded system.

cs.IR↗

arXiv2016

Cross-Lingual Predicate Mapping Between Linked Data Ontologies

Ontologies in different natural languages often differ in quality in terms of richness of schema or richness of internal links. This difference is markedly visible when comparing a rich English language ontology with a non-English language counterpart. Discovering alignment between them is a useful endeavor as it serves as a starting point in bridging the disparity. In particular, our work is motivated by the absence of inter-language links for predicates in the localised versions of DBpedia. In this paper, we propose and demonstrate an ad-hoc system to find possible owl:equivalentProperty links between predicates in ontologies of different natural languages. We seek to achieve this mapping by using pre-existing inter-language links of the resources connected by the given predicate. Thus, our methodology stresses on semantic similarity rather than lexical. Moreover, through an evaluation, we show that our system is capable of outperforming a baseline system that is similar to the one used in recent OAEI campaigns.

cs.AI↗

arXiv2015

Orientational Order in the Nematic and Heliconical Nematic Liquid Crystals

X-ray scattering and polarized microscopic studies of the structure and order parameters in the nematic (N) and heliconical, or the twist-bend nematic (Ntb), phase have been performed as a function of temperature. The nematic orientational order parameters and in the nematic phases of CB7CB and its mixtures with less than 20 wt% CB6CB reveal that they both increase with decreasing temperature in the N phase. Both order parameters decrease upon entering the Ntb phase and becomes negative providing a direct confirmation of the conical molecular orientational distribution. The heliconical tilt angle, estimated from the orientational distribution functions (ODFs), in all cases increases from zero at the N - Ntb transition to approximately 27° at about 40 K below the transition, in excellent agreement with freeze fracture transmission electron microscopy results of Chen and the birefringence results of Meyer. The growth of the tilt angle in the Ntb phase follows a single power law with exponents between ~0.09 +/- 0.01 to -0.12 +/- 0.01, which is far from the expected tricritical or mean field exponents of 0.25 or 0.5. The temperature dependence of the tilt angle calculated from the ODFs also is in good qualitative agreement with the values estimated from optical studies of their ropelike textures within adjacent blocks of left- and right-handed twist in homogeneously aligned cells.

cond-mat.soft↗

arXiv2014

Arginine-Phosphate Salt Bridges Between Histones and DNA: Intermolecular Actuators that Control Nucleosome Architecture

Structural bioinformatics and van der Waals density functional theory are combined to investigate the mechanochemical impact of a major class of histone-DNA interactions, namely the formation of salt bridges between arginine residues in histones and phosphate groups on the DNA backbone. Principal component analysis reveals that the configurational fluctuations of the sugar-phosphate backbone display sequence-specific variability, and clustering of nucleosomal crystal structures identifies two major salt bridge configurations: a monodentate form in which the arginine end-group guanidinium only forms one hydrogen bond with the phosphate, and a bidentate form in which it forms two. Density functional theory calculations highlight that the combination of sequence, denticity and salt bridge positioning enable the histones to tunably activate specific backbone deformations via mechanochemical stress. The results suggest that selection for specific placements of van der Waals contacts, with high-precision control of the spatial distribution of intermolecular forces, may serve as an underlying evolutionary design principle for the structure and function of nucleosomes, a conjecture that is corroborated by previous experimental studies.

q-bio.BM↗