Abstract

Idiomatic expressions have always been a bottleneck for language comprehension and natural language understanding, specifically for tasks like Machine Translation (MT). MT systems predominantly produce literal translations of idiomatic expressions as they do not exhibit generic and linguistically deterministic patterns which can be exploited for comprehension of the non- compositional meaning of the expressions. These expressions occur in parallel corpora used for training, but due to the comparatively high occurrences of the constituent words of idiomatic expressions in literal context, the idiomatic meaning gets overpowered by the compositional meaning of the expression. State of the art Metaphor Detection Systems are able to detect non-compositional usage at word level but miss out on idiosyncratic phrasal idiomatic expressions. This creates a dire need for a dataset with a wider coverage and higher occurrence of commonly occurring idiomatic expressions, the spans of which can be used for Metaphor Detection. With this in mind, we present our English Possible Idiomatic Expressions (EPIE) corpus containing 25,206 sentences labelled with lexical instances of 717 idiomatic expressions. These spans also cover literal usages for the given set of idiomatic expressions. We also present the utility of our dataset by using it to train a sequence labelling module and testing on three independent datasets with high accuracy, precision and recall scores.

Abstract

Inspecting and assessing the quality of traffic infrastructure (such as the state of the signboards or road markings) is challenging for humans due to (i) the massive length of roads that countries will have and (ii) the regular frequency at which this needs to be done. In this paper, we demonstrate a scalable system that uses computer vision for automatic inspection of road infrastructure from a simple video captured from a moving vehicle. We validated our method on 1500 kms of roads captured in and around the city of Hyderabad, India. Qualitative and quantitative results demonstrate the feasibility, scalability and effectiveness of our solution.

Abstract

Question Answer pair generation is a task that has been worked upon by multiple researchers in many languages. It has been a topic of interest due to its extensive uses in different fields like self assessment, academics, busi ness website FAQs etc. Many experiments were conducted on Question Answering pair generation in English, concentrating on basic Whquestions with a rulebased approach. We have built the first hybrid machine learning and rulebased solution in Telugu which is ef ficient for short stories or short passages in children’s books. Our work covers the funda mental question forms with the question types: adjective, yes/no, adverb, verb, when, where, whose, quotative, and quantitative(how many/ how much). We constructed rules for question generation using POS tags and UD tags along with linguistic information of the surrounding context of the word.

Abstract

n this study, a 3D seismic response of soil deposit, soil-ash deposit and soil-ash-foundation system was investigated. Homogeneous sand deposit of 80m × 9m × 20m was initially analyzed. A pond ash layer is on top of the sand deposit with varying thicknesses and the efficiency of the pond ash layer on the sand deposit was evaluated for its best suitability. The optimum sand-ash deposit overlain by a shallow foundation has been analysed under the excitation of the Nepal (Mw:7.8) and North East India earthquake (Mw:7.5). A seismic response analysis was performed using finite element software PLAXIS3D. The finite element model adopted for the present study has been validated using 1D nonlinear ground response analysis programs. e.g. DEEPSOIL and Cyclic1D. Results of the response analysis have been determined in terms of acceleration, displacement, excess pore pressure, and excess pore pressure ratio. It was observed that, the sand-pond ash-foundation system experienced liquefaction when excited under the Nepal earthquake motion whereas it is safe against the North East India earthquake.

Abstract

ndian Musicology defines 22 distinct shrutis (microtones), 12 swa- rasthanas (semitones) and 7 swaras (tones). By implementing the mathematical concepts like cycle of fourths and fifths, these shrutis acquire a discrete frequency ratio which justifies the Bharatha’s 22 shrutis experiment. Indian classical music defines the 7 swaras and each swara is associated to an animal/bird call. The Grama system in Indian music distributes the 22 shrutis amongst the 7 swaras. We based our work on the Shadja Grama system. The traversal of pitches in a swara are more important in understanding the swara as compared to the fre- quency ratio. This shows us that swaras have peculiar properties and an identity independent of the octave.

Abstract

This paper aims to establish the formal theory of painting. We are looking into two fundamental elements which are crucial to build a theory of painting, and those are strokes and Shapes, the central claim of this research is that the ‘Painting Exists between Stroke and Shape’, and the space of the painting is dynamic in nature, it exists not entirely in the matter (canvas/paper) nor in the mind (Imagination), it is in-between, it is like a hologram which is more than 2D less than 3D. We are using Indian Folk Paintings as a case to demonstrate our theory because of their uniqueness.

Abstract

Requirements Engineering in the industry is expertise-driven, heavily manual, and centered around various types of requirement specification documents being prepared and maintained. These specification documents are in diverse formats and vary depending on whether it is a business requirement document, functional specification, interface specification, client specification, and so on. These diverse specification documents embed crucial product knowledge such as functional decomposition of the domain into features, feature hierarchy, feature types and their specific feature characteristics, dependencies, business context, etc. Moreover, in a product development scenario, thousands of pages of requirement specification documentation is created over the years. Comprehending functionality and its associated context from large volumes of specification documents is a highly complex task. To address this problem, we propose to digitalize the requirement specification documents into processable models. This paper discusses the salient aspects involved in the digitalization of requirements knowledge from diverse requirement specification documents. It proposes an AI engine for the automatic transformation of diverse text-based requirement specifications into machine-processable models using NLP techniques and the generation of context-sensitive user stories. The paper describes the key requirement abstractions and concepts essential in an industrial scenario, the conceptual meta-model, and DizReq engine (AI engine for digitalizing requirements) implementation for automatically transforming diverse requirement specifications into user stories embedding the business context. The evaluation results from digitalizing specifications of an IT product suite are discussed: mean feature extraction efficiency is 40 features/file, mean user story extraction efficiency is 71 user stories/file, feature extraction accuracy is 94%, and requirement extraction accuracy is 98%. Keywords: NLP, NLP4RE, model extraction, requirements digitalization, requireme

Abstract

RF bio-sensing is often utilized for the detection of bio-samples by using the concept of shift in resonant frequency. It is widely reported that the shift in resonant frequency is narrower compared to the bandwidth of the device used for measuring this shift. As a result, wideband Vector Network Analyzer (VNA) proves to be an overkill and instead a narrowband measurement setup can fulfill this requirement. Therefore, in this paper, an integrated solution for the detection of materials having varying permittivities is presented. A DualBand Six Port Reflectometer (DBSPR) is proposed and designed using planer microstrip line technology for the purpose of characterizing the sensor using reflection and transmission coefficient. A Complimentary Split Ring Resonator (CSRR) based sensor having an unloaded resonance frequency of 2.3 GHz is utilized as a test set. The designed DBSPR operates at 1.12 GHz and 2.26 GHz with a 10dB bandwidth of 254 MHz and 215 MHz respectively. The DBSPR and CSRR sensor are integrated using a microstrip line. The integrated device is tested for two different materials having a permittivity of 2.3 and 4.3. A shift of 118 MHz is observed between these materials and thus shows the potential usefulness of the proposed setup.

Abstract

L-Lysine is an essential amino acid and bio-sample observing major significance in food processing, pharmaceutical and agricultural industries. Conventional sensing techniques require longer pre-processing times and are sensitive to ambient conditions. However, radio frequency (RF) sensing based on Complementary Split Ring Resonator (CSRR) exhibits a significant shift in the resonant frequency and is highly desirable for the L-Lysine’s quantitative analysis. The frequency shifts of 498.4 MHz, 482.9 MHz, 471.4 MHz, 459.9 MHz and 452.3 MHz are obtained through varying concentrations from 0 mg/ml to 40 mg/ml in step size 10 mg/ml of L-Lysine solution. Therefore, experimental results and analysis presented in this work indicate the proposed radio frequency sensor’s linearity in the abovereported concentration range.

Abstract

Problems involving code-mixed language are often plagued by a lack of resources and an absence of materials to perform sophisticated transfer learning with. In this paper we describe our submission to the Sentimix Hindi-English task involving sentiment classification of code-mixed texts, and with an F1 score of 67.1%, we demonstrate that simple convolution and attention may well produce reasonable results.