Abstract

A system and method for automatically extracting contract data from electronic contracts includes an administrator module configured to provide templates for inputting document patterns and a list of contract data tags for each of a plurality of contract document types. A parser is configured to convert an electronic contract document into a contract text document and reformat the contract text document to provide a pattern for the text contract document. A pattern recognition engine is configured to determine a list of contract document types in the electronic contract by comparing and matching patterns of all known contract document types with the pattern of the contract text document. A contract data extraction engine is configured to extract contract data for each contract document type on the list.

Abstract

Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image since they are composed of invertible transformations. However, the requirement of invertibility of the transformation prevents standard and expressive neural network models such as CNNs from being directly used. Emergent convolutions were proposed to construct an invertible 3×3 CNN layer using a pair of masked CNN layers, making them inefficient. We study conditions such that 3×3 CNNs are invertible, allowing them to construct expressive normalizing flows. We derive necessary and sufficient conditions on a padded CNN for it to be invertible. Our conditions for invertibility are simple, can easily be maintained during the training process. Since we require only a single CNN layer for every effective invertible CNN layer, our approach is more efficient than emerging convolutions. We also proposed a coupling method, Quad-coupling. We benchmark our approach and show similar performance results to emergent convolutions while improving the model's efficiency

Abstract

Quality assessment of agricultural produce is a crucial step in minimizing food stock wastage. However, this is currently done manually and often requires expert supervision, especially in smaller seeds like corn. We propose a novel computer vision-based system for automating this process. We build a novel seed image acquisition setup, which captures both the top and bottom views. Dataset collection for this problem has challenges of data annotation costs/time and class imbalance. We address these challenges by i.) using a Conditional Generative Adversarial Network (CGAN) to generate real-looking images for the classes with lesser images and ii.) annotate a large dataset with minimal expert human intervention by using a Batch Active Learning (BAL) based annotation tool. We benchmark different image classification models on the dataset obtained. We are able to get accuracies of up to 91.6% for testing the physical purity of seed samples.

Abstract

This paper describes a new method for speech activity detection (SAD) based on the recently proposed single frequency filtering (SFF) analysis of speech signals and a neural network model. The SFF analysis gives instantaneous spectrum of the speech signal at each sampling instant. The frequency resolution of the spectrum is decided by the number of frequencies used in the SFF analysis, which in turn depends on the frequency spacing. Using a frequency spacing of 10 Hz and a sampling frequency of 8 kHz, a 401 dimensional spectrum, covering 0–4 kHz, is obtained at each sampling instant. This is used as a feature vector to train an artificial neural network (ANN) model to discriminate (noisy) speech and nonspeech (mostly noise). The output of the trained ANN model for a given test utterance gives speech/nonspeech decision at every sampling instant. Post processing of the decision is used for SAD. The system generated SAD is evaluated on the Apollo corpus for SAD task in terms of detection cost function (DCF). The DCF values of the proposed system on the development and evaluation datasets are 3.1% and 4.6%, respectively, whereas the DCF values of the reported baseline system are 8.6% and 11.7%, respectively.

Abstract

Sparse arrays are special geometrical arrangements of sensors which overcome some of the drawbacks associated with dense uniform arrays and require fewer sensors. For direction finding applications, sparse arrays with the same number of sensors can resolve more sources while providing higher resolution than a dense uniform array. This has been verified numerically and with real data for one-dimensional microphone arrays. In this study the use of nested and co-prime arrays is examined with sparse Bayesian learning (SBL), which is a compressive sensing algorithm, for estimating sparse vectors and support. SBL is an iterative parameter estimation method and can process multiple snapshots as well as multiple frequency data within its Bayesian framework. A multi-frequency variant of SBL is proposed, which accounts for non-flat frequency spectra of the sources. Experimental validation of azimuth and elevation [two-dimensional (2D)] direction-of-arrival (DOA)estimation are provided using sparse arrays and real data acquired in an anechoic chamber with a rectangular array. Both co-prime and nested arrays are obtained by sampling this rectangular array. The SBL method is compared with conventional beamforming and multiple signal classification for 2D DOA estimation of experimental data.

Abstract

In a developing country like India, agriculture provides large scale employment in rural areas, thus serving as the backbone of an economic system. For farmers it is important to decide which crop to grow, what Government schemes benefit them the most and what is the best selling price of the crop. In this paper we described the Speech to Speech interaction between farmer and government through an application using speech recognition system for Telugu language that will form the interface to the webpage providing information about the government schemes and commodity prices through voice. The proposed Kisan Information System (KIS) is integration of Speech recognition, Dialogue Manager, and Speech Synthesis modules. The performance of the KIS is better compared with existing one for Telugu language.

Abstract

It is critical for aerial robots flying in city scale urban environments to make very quick estimates of a building depth with respect to itself. It should be done in a matter of few views to navigate itself, avoiding collisions with such a towering structure. As such, no one has attacked this problem. We bring together several modules combining deep learning and 3D vision to showcase a quick reconstruction in a few views. We exploit the inherent planar structure in the buildings (facades, windows) for this purpose. We evaluate the efficacy of our pipeline with various constraints and errors from multi-view geometry using ablation studies. We then retrieve the skyline of the buildings in synthetic as well as real-world scenes.

Abstract

Wharfs and jetties are the key structures in port transportation systems that support export and import activities. Wharf structures during a seismic event are susceptible to severe damage and may have an adverse effect on port operations. Historical earthquakes such as 1995 Kobe earthquake (Mw = 6.9; Japan) Chang [1], 1999 Chi-Chi earthquake (Mw = 7.3; Taiwan), 2004 the Great Indian Ocean earthquake (Mw = 9.1; Sumatra) and Haiti earthquake (2010) DesRoches [2] damaged major port structures, such as caissons, quays and pile-supported wharfs [3]. These ports suffered severe economic losses due to the collapse of wharfs leading to downtime in port operations. This attracted the attention of researchers towards seismic analysis and design of port structures, especially pile-supported wharfs. In the present study, a wharf structure from Vishakhapatnam port (Andhra Pradesh, India) has been chosen for pushover analysis. For the structural model of the pile-supported wharf considered, shell elements were used for modelling the deck. Winkler model has been used for representation of the pile–soil system, in which the piles were represented by beam elements and soils were represented by springs. Pushover analysis has been carried out with distribution of lateral loads according to the fundamental modal shape of the wharf structure to derive the capacity curve of the wharf structure. Capacity spectrum method which is a nonlinear static procedure has been used to efficiently construct a response matrix of the wharf. Nonlinear static pushover analysis has been performed, and it has been observed that the hinge sequence obtained for the wharf in transverse direction in the present study matches with the

Abstract

Although several automatic itinerary generation services have made travel planning easy, often times travellers find themselves in unique situations where they cannot make the best out of their trip. Visitors differ in terms of many factors such as suffering from a disability, being of a particular dietary preference, travelling with a toddler, etc. While most tourist spots are universal, others may not be inclusive for all. In this paper, we focus on the problem of mining inclusion and exclusion phrases associated with 11 such factors, from reviews related to a tourist spot. While existing work on tourism data mining mainly focuses on structured extraction of trip related information, personalized sentiment analysis, and automatic itinerary generation, to the best of our knowledge this is the first work on inclusion/exclusion phrase mining from tourism reviews. Using a dataset of 2000 reviews related to 1000 tourist spots, our broad level classifier provides a binary overlap F1 of 80 and 82 to classify a phrase as inclusion or exclusion respectively. Further, our inclusion/exclusion classifier provides an F1 of 98 and 97 for 11-class inclusion and exclusion classification respectively. We believe that our work can significantly improve the quality of an automatic itinerary generation service.

Abstract

WikiHow is an open-domain repository of in- structional articles for a variety of tasks, which can be revised by users. In this paper, we extract pairwise versions of an instruction be- fore and after a revision was made. Starting from a noisy dataset of revision histories, we specifically extract and analyze edits that in- volve cases of vagueness in instructions. We further investigate the ability of a neural model to distinguish between two versions of an in- struction in our data by adopting a pairwise ranking task from previous work and showing improvements over existing baselines