Abstract

The task of fact-checking has been formalised as the assessment of the truthfulness of a claim. Be it a political proclamation or a technological development, verification of a new tidbit of information before its propagation to the general public is of utmost importance. Failing to do so leads to the spread of misinformation, which is a devious tool. Fact-checking is commonly performed by journalists, manually looking up information pertaining to the statement in question. This is a drawn out and tedious process with a chance of the concerned person not covering the domain exhaustively. Some of this effort is reduced by the use of knowledge bases created over a period of time. In this work under Task 2 (Factuality) of the CLEF 2018 CheckThat! Lab, we detail a neural network based methodology which models the textual data of a claim based on various representations of its words and characters. An affixed attention mechanism allows us to encapsulate linguistic features common in false claims. We achieve an accuracy of 39.57% on the task dataset.

Abstract

Fricatives are produced by creating a turbulence in the air– flow by passing it through a stricture in the vocal tract cavity. Fricatives are characterized by their noise–like behavior, which makes it difficult to analyze. Difference in the place of articulation leads to different classes of fricatives. Identification of fricative segment boundaries in speech helps in improving the performance of several applications. The present study attempts towards the identification and classification of fricative segments in continuous speech, based on the statistical behavior of instantaneous spectral characteristics. The proposed method uses parameters such as the dominant resonance frequencies, the center of gravity along with the statistical moments of the spectrum obtained using the zero time windowing (ZTW) method. The ZTW spectra exhibits a high temporal resolution and therefore gives accurate segment boundaries in speech. The proposed algorithm is tested on the TIMIT dataset for English language. A high identification rate of 97.5% is achieved for segment boundaries of the sibilant fricative class. Voiced nonsibilants show a lower identification rate than their voiceless counterparts due to their vowel–like spectral characteristics. A high classification rate of 93.2% is achieved be

Abstract

This paper describes the BUT ‘Jilebi’ team’s speech recognition systems created for the 2018 low resource speech recognition challenge for Indian languages. We investigate modifications of multilingual time-delay neural network (TDNN) architectures with transfer learning and compare them to bi-directional residual memory networks (BRMN) and bi-directional LSTM. Our best submission based on system combination achieved word error rates of 13.92% (Tamil), 14.71% (Telugu) and 14.06% (Gujarati). We present the details of submitted systems and also the post-evaluation analysis done for lexicon discovery using unsupervised word segmentation.

Abstract

We show an effective way of adding context information to shallow neural language models. We propose to use Subspace Multinomial Model (SMM) for context modeling and we add the extracted i-vectors in a computationally efficient way. By adding this information, we shrink the gap between shallow feed-forward network and an LSTM from 65 to 31 points of perplexity on the Wikitext-2 corpus (in the case of neural 5-gram model). Furthermore, we show that SMM i-vectors are suitable for domain adaptation and a very small amount of adaptation data (e.g. endmost 5 % of a Wikipedia article) brings a substantial improvement. Our proposed changes are compatible with most optimization techniques used for shallow feedforward LMs.

Abstract

Graph grammars, being a natural extension of string grammars as well as tree grammars, are highly expressive as well as powerful enough to capture the generative structure of a wide variety of scenarios - both simple and complex. But, unfortunately, we do not find many instances which leverage this power graph grammars provide us. Most of the graph grammars available so far are either toy grammars or limited to addressing highly specialized problems. In this paper, we present Vaiśeṣika Graph Grammar (VGG) system, which is as wide as any graph grammar can get i.e., a grammar for reality as theorized in Vaiśeṣika - the foundational ontology found in Indian analytic tradition. This paper extends the work presented in [1]. In [1], the generative as well as the interpretation rules of this system were presented. Here, apart from briefly discussing some of these rules, we also present a parser for such a system which makes it extremely powerful in terms of its ability to classify an input graph as a valid Vaiśeṣika graph or an invalid one which, in itself, is an immensely significant breakthrough for any ontological application. Apart from that, we also present a verification mechanism to verify the interpretations of graphs generated by the generative rules. This is done, at least statistically, if not formally, to give a statistical proof of the soundness of the system (that every generated graph has at least one Vaiśeṣika

Abstract

With neural networks rapidly becoming deeper, there emerges a need for compact models. One popular approach for this is to train small student networks to mimic larger and deeper teacher models, rather than directly learn from the training data. We propose a novel technique to train studentteacher networks without directly providing label information to the student. However, our main contribution is to learn how to learn from the teacher by a unique strategy - having the student compete with a discriminator.

Abstract

This paper describes the systems submitted by IIT (BHU), Varanasi/IIIT Hyderabad (IITBHU–IIITH) for Task 1 of CoNLL– SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection (Cotterell et al., 2018). The task is to generate the inflected form given a lemma and set of morphological features. The systems are evaluated on over 100 distinct languages and three different resource settings (low, medium and high). We formulate the task as a sequence to sequence learning problem. As most of the characters in inflected form are copied from the lemma, we use Pointer-Generator Network (See et al., 2017) which makes it easier for the system to copy characters from the lemma. PointerGenerator Network also helps in dealing with out-of-vocabulary characters during inference. Our best performing system stood 4th among 28 systems, 3rd among 23 systems and 4th among 23 systems for the low, medium and high resource setting respectively.

Abstract

The inter-cell interference coordination techniques which include frequency reuse and Dynamic Channel Allocation (DCA) play a vital role in improving the spectrum efficiency. The techniques of frequency reuse are very sophisticated. Depending on the traffic demand, channels allocated to each cell is varied in DCA. In OFDM based cellular systems, the channel information and interference signals can be measured easily whose knowledge is essential for DCA. Hence, in OFDM systems, DCA can improve the spectral efficiency to a great extent. The next generation cellular systems would incorporate small cell (Micro, Pico and Femto) base stations for extensive frequency reuse and spectrum utility. They would also include millimeter wave (mmWave) for communication i.e. 5G cellular networks. DCA techniques in such a HetNet would improve the efficiency to a great extent. With the development of Software Defined Mobile Networking (SDMN), the protocol-specific features of mobile networks for various radio access technologies can be carried out with software improving the functionality of network. Thus, the implementation of DCA techniques becomes less complex. In this paper, DCA in small cells with respect to three cases namely spatial, temporal and spatio-temporal allocation is proposed. The problem formulated for DCA is solved using integer linear programming (ILP) technique and the solution is an effective prediction based model to optimize the channel allocation problem. Simulation results show the performance for various number of available resources and number of cells for allocation.

Abstract

In this work, the Switched-capacitor Power Amplifier (SCPA) impairments are modelled and analysed along with their effect on the efficiency, the linearity and the output power. The proposed model considers the mismatch between the switch On-resistances, the variation of switch On-resistance with VDS and its effects on the SCPA performance. Additionally, the influence of supply non-idealities are modelled. The proposed model provides expected Integral Non-Linearity for the SCPA as well as some insight on possible design improvements and SCPA limitations.

Abstract

In this paper, we tackle the problem of fake news detection from social media by exploiting the presence of echo chamber communities (communities sharing same beliefs) that exist within the social network of the users. By modeling the echo-chambers as closely-connected communities within the social network, we represent a news article as a 3-mode tensor of the structure - <;News, User, Community> and propose a tensor factorization based method to encode the news article in a latent embedding space preserving the community structure. We also propose an extension of the above method, which jointly models the community and content information of the news article through a coupled matrix-tensor factorization framework. We empirically demonstrate the efficacy of our method for the task of Fake News Detection over two real-world datasets.