arXiv subjects

Vivek Kulkarni

Publications and source records attributed to Vivek Kulkarni.

At least 37 records · Page 2Linked to original sources

arXiv2019

DialectGram: Detecting Dialectal Variation at Multiple Geographic Resolutions

Several computational models have been developed to detect and analyze dialect variation in recent years. Most of these models assume a predefined set of geographical regions over which they detect and analyze dialectal variation. However, dialect variation occurs at multiple levels of geographic resolution ranging from cities within a state, states within a country, and between countries across continents. In this work, we propose a model that enables detection of dialectal variation at multiple levels of geographic resolution obviating the need for a-priori definition of the resolution level. Our method DialectGram, learns dialect-sensitive word embeddings while being agnostic of the geographic resolution. Specifically it only requires one-time training and enables analysis of dialectal variation at a chosen resolution post-hoc -- a significant departure from prior models which need to be re-trained whenever the pre-defined set of regions changes. Furthermore, DialectGram explicitly models senses thus enabling one to estimate the proportion of each sense usage in any given region. Finally, we quantitatively evaluate our model against other baselines on a new evaluation dataset DialectSim (in English) and show that DialectGram can effectively model linguistic variation.

cs.CL↗

arXiv2019

What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog

The ability to engage in goal-oriented conversations has allowed humans to gain knowledge, reduce uncertainty, and perform tasks more efficiently. Artificial agents, however, are still far behind humans in having goal-driven conversations. In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective. This task is challenging since these questions must not only be consistent with a strategy to achieve a goal, but also consider the contextual information in the image. We propose an end-to-end goal-oriented visual dialogue system, that combines reinforcement learning with regularized information gain. Unlike previous approaches that have been proposed for the task, our work is motivated by the Rational Speech Act framework, which models the process of human inquiry to reach a goal. We test the two versions of our model on the GuessWhat?! dataset, obtaining significant results that outperform the current state-of-the-art models in the task of generating questions to find an undisclosed object in an image.

cs.CL↗

arXiv2019

TWEETQA: A Social Media Focused Question Answering Dataset

With social media becoming increasingly pop-ular on which lots of news and real-time eventsare reported, developing automated questionanswering systems is critical to the effective-ness of many applications that rely on real-time knowledge. While previous datasets haveconcentrated on question answering (QA) forformal text like news and Wikipedia, wepresent the first large-scale dataset for QA oversocial media data. To ensure that the tweetswe collected are useful, we only gather tweetsused by journalists to write news articles. Wethen ask human annotators to write questionsand answers upon these tweets. Unlike otherQA datasets like SQuAD in which the answersare extractive, we allow the answers to be ab-stractive. We show that two recently proposedneural models that perform well on formaltexts are limited in their performance when ap-plied to our dataset. In addition, even the fine-tuned BERT model is still lagging behind hu-man performance with a large margin. Our re-sults thus point to the need of improved QAsystems targeting social media text.

cs.CL↗

arXiv2019

VirtuWind - An SDN- and NFV-based Architecture for Softwarized Industrial Networks

VirtuWind proposes the application of Software Defined Networking (SDN) and Network Functions Virtualization (NFV) in critical infrastructure networks. We aim at introducing network programmability, reconfigurability and multi-tenant capability both inside isolated and inter-connected industrial networks. Henceforth, we present the design of the VirtuWind architecture that addresses the requirements of industrial communications: granular Quality of Service (QoS) guarantees, system modularity and secure and isolated per-tenant network access. We present the functional components of our architecture and provide an overview of the appropriate realization mechanisms. Finally, we map two exemplary industrial system use-cases to the designed architecture to showcase its applicability in an exemplary industrial wind park network.

cs.NI↗

arXiv2018

MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings

Many knowledge graph embedding methods operate on triples and are therefore implicitly limited by a very local view of the entire knowledge graph. We present a new framework MOHONE to effectively model higher order network effects in knowledge-graphs, thus enabling one to capture varying degrees of network connectivity (from the local to the global). Our framework is generic, explicitly models the network scale, and captures two different aspects of similarity in networks: (a) shared local neighborhood and (b) structural role-based similarity. First, we introduce methods that learn network representations of entities in the knowledge graph capturing these varied aspects of similarity. We then propose a fast, efficient method to incorporate the information captured by these network representations into existing knowledge graph embeddings. We show that our method consistently and significantly improves the performance on link prediction of several different knowledge-graph embedding methods including TRANSE, TRANSD, DISTMULT, and COMPLEX(by at least 4 points or 17% in some cases).

cs.CL↗

arXiv2018

DOLORES: Deep Contextualized Knowledge Graph Embeddings

We introduce a new method DOLORES for learning knowledge graph embeddings that effectively captures contextual cues and dependencies among entities and relations. First, we note that short paths on knowledge graphs comprising of chains of entities and relations can encode valuable information regarding their contextual usage. We operationalize this notion by representing knowledge graphs not as a collection of triples but as a collection of entity-relation chains, and learn embeddings for entities and relations using deep neural models that capture such contextual usage. In particular, our model is based on Bi-Directional LSTMs and learn deep representations of entities and relations from constructed entity-relation chains. We show that these representations can very easily be incorporated into existing models to significantly advance the state of the art on several knowledge graph prediction tasks like link prediction, triple classification, and missing relation type prediction (in some cases by at least 9.5%).

cs.CL↗

arXiv2018

Multi-view Models for Political Ideology Detection of News Articles

A news article's title, content and link structure often reveal its political ideology. However, most existing works on automatic political ideology detection only leverage textual cues. Drawing inspiration from recent advances in neural inference, we propose a novel attention based multi-view model to leverage cues from all of the above views to identify the ideology evinced by a news article. Our model draws on advances in representation learning in natural language processing and network science to capture cues from both textual content and the network structure of news articles. We empirically evaluate our model against a battery of baselines and show that our model outperforms state of the art by 10 percentage points F1 score.

cs.CL↗

arXiv2018

Hate Lingo: A Target-based Linguistic Analysis of Hate Speech in Social Media

While social media empowers freedom of expression and individual voices, it also enables anti-social behavior, online harassment, cyberbullying, and hate speech. In this paper, we deepen our understanding of online hate speech by focusing on a largely neglected but crucial aspect of hate speech -- its target: either "directed" towards a specific person or entity, or "generalized" towards a group of people sharing a common protected characteristic. We perform the first linguistic and psycholinguistic analysis of these two forms of hate speech and reveal the presence of interesting markers that distinguish these types of hate speech. Our analysis reveals that Directed hate speech, in addition to being more personal and directed, is more informal, angrier, and often explicitly attacks the target (via name calling) with fewer analytic words and more words suggesting authority and influence. Generalized hate speech, on the other hand, is dominated by religious hate, is characterized by the use of lethal words such as murder, exterminate, and kill; and quantity words such as million and many. Altogether, our work provides a data-driven analysis of the nuances of online-hate speech that enables not only a deepened understanding of hate speech and its social implications but also its detection.

cs.CL↗

arXiv2018

Simple Models for Word Formation in English Slang

We propose generative models for three types of extra-grammatical word formation phenomena abounding in English slang: Blends, Clippings, and Reduplicatives. Adopting a data-driven approach coupled with linguistic knowledge, we propose simple models with state of the art performance on human annotated gold standard datasets. Overall, our models reveal insights into the generative processes of word formation in slang -- insights which are increasingly relevant in the context of the rising prevalence of slang and non-standard varieties on the Internet.

cs.CL↗

arXiv2017

TFW, DamnGina, Juvie, and Hotsie-Totsie: On the Linguistic and Social Aspects of Internet Slang

Slang is ubiquitous on the Internet. The emergence of new social contexts like micro-blogs, question-answering forums, and social networks has enabled slang and non-standard expressions to abound on the web. Despite this, slang has been traditionally viewed as a form of non-standard language -- a form of language that is not the focus of linguistic analysis and has largely been neglected. In this work, we use UrbanDictionary to conduct the first large-scale linguistic analysis of slang and its social aspects on the Internet to yield insights into this variety of language that is increasingly used all over the world online. We begin by computationally analyzing the phonological, morphological and syntactic properties of slang. We then study linguistic patterns in four specific categories of slang namely alphabetisms, blends, clippings, and reduplicatives. Our analysis reveals that slang demonstrates extra-grammatical rules of phonological and morphological formation that markedly distinguish it from the standard form shedding insight into its generative patterns. Next, we analyze the social aspects of slang by studying subject restriction and stereotyping in slang usage. Analyzing tens of thousands of such slang words reveals that the majority of slang on the Internet belongs to two major categories: sex and drugs. We also noted that not only is slang usage not immune to prevalent social biases and prejudices but also reflects such biases and stereotypes more intensely than the standard variety.

cs.CL↗

arXiv2017

Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings

We present Walklets, a novel approach for learning multiscale representations of vertices in a network. In contrast to previous works, these representations explicitly encode multiscale vertex relationships in a way that is analytically derivable. Walklets generates these multiscale relationships by subsampling short random walks on the vertices of a graph. By `skipping' over steps in each random walk, our method generates a corpus of vertex pairs which are reachable via paths of a fixed length. This corpus can then be used to learn a series of latent representations, each of which captures successively higher order relationships from the adjacency matrix. We demonstrate the efficacy of Walklets's latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, DBLP, Flickr, and YouTube. Our results show that Walklets outperforms new methods based on neural matrix factorization. Specifically, we outperform DeepWalk by up to 10% and LINE by 58% Micro-F1 on challenging multi-label classification tasks. Finally, Walklets is an online algorithm, and can easily scale to graphs with millions of vertices and edges.

cs.SI↗

arXiv2017

Latent Human Traits in the Language of Social Media: An Open-Vocabulary Approach

Over the past century, personality theory and research has successfully identified core sets of characteristics that consistently describe and explain fundamental differences in the way people think, feel and behave. Such characteristics were derived through theory, dictionary analyses, and survey research using explicit self-reports. The availability of social media data spanning millions of users now makes it possible to automatically derive characteristics from language use -- at large scale. Taking advantage of linguistic information available through Facebook, we study the process of inferring a new set of potential human traits based on unprompted language use. We subject these new traits to a comprehensive set of evaluations and compare them with a popular five factor model of personality. We find that our language-based trait construct is often more generalizable in that it often predicts non-questionnaire-based outcomes better than questionnaire-based traits (e.g. entities someone likes, income and intelligence quotient), while the factors remain nearly as stable as traditional factors. Our approach suggests a value in new constructs of personality derived from everyday human language use.

cs.CL↗

arXiv2017

Citation histories of papers: sometimes the rich get richer, sometimes they don't

We describe a simple model of how a publication's citations change over time, based on pure-birth stochastic processes with a linear cumulative advantage effect. The model is applied to citation data from the Physical Review corpus provided by APS. Our model reveals that papers fall into three different clusters: papers that have rapid initial citations and ultimately high impact (fast-hi), fast to rise but quick to plateau (fast-flat), or late bloomers (slow-late), which may either never achieve many citations, or do so many years after publication. In "fast-hi" and "slow-late", there is a rich-get-richer effect: papers that have many citations accumulate additional citations more rapidly while the "fast-flat" papers do not display this effect. We conclude by showing that only a few years of post-publication statistics are needed to identify high impact ("fast-hi") papers.

cs.DL↗

arXiv2016

Data Centroid Based Multi-Level Fuzzy Min-Max Neural Network

Recently, a multi-level fuzzy min max neural network (MLF) was proposed, which improves the classification accuracy by handling an overlapped region (area of confusion) with the help of a tree structure. In this brief, an extension of MLF is proposed which defines a new boundary region, where the previously proposed methods mark decisions with less confidence and hence misclassification is more frequent. A methodology to classify patterns more accurately is presented. Our work enhances the testing procedure by means of data centroids. We exhibit an illustrative example, clearly highlighting the advantage of our approach. Results on standard datasets are also presented to evidentially prove a consistent improvement in the classification rate.

cs.AI↗

arXiv2016

Domain Adaptation for Named Entity Recognition in Online Media with Word Embeddings

Content on the Internet is heterogeneous and arises from various domains like News, Entertainment, Finance and Technology. Understanding such content requires identifying named entities (persons, places and organizations) as one of the key steps. Traditionally Named Entity Recognition (NER) systems have been built using available annotated datasets (like CoNLL, MUC) and demonstrate excellent performance. However, these models fail to generalize onto other domains like Sports and Finance where conventions and language use can differ significantly. Furthermore, several domains do not have large amounts of annotated labeled data for training robust Named Entity Recognition models. A key step towards this challenge is to adapt models learned on domains where large amounts of annotated training data are available to domains with scarce annotated data. In this paper, we propose methods to effectively adapt models learned on one domain onto other domains using distributed word representations. First we analyze the linguistic variation present across domains to identify key linguistic insights that can boost performance across domains. We propose methods to capture domain specific semantics of word usage in addition to global semantics. We then demonstrate how to effectively use such domain specific knowledge to learn NER models that outperform previous baselines in the domain adaptation setting.

cs.CL↗

arXiv2016

On the Convergent Properties of Word Embedding Methods

Do word embeddings converge to learn similar things over different initializations? How repeatable are experiments with word embeddings? Are all word embedding techniques equally reliable? In this paper we propose evaluating methods for learning word representations by their consistency across initializations. We propose a measure to quantify the similarity of the learned word representations under this setting (where they are subject to different random initializations). Our preliminary results illustrate that our metric not only measures a intrinsic property of word embedding methods but also correlates well with other evaluation metrics on downstream tasks. We believe our methods are is useful in characterizing robustness -- an important property to consider when developing new word embedding methods.

cs.CL↗

arXiv2016

Theano: A Python framework for fast computation of mathematical expressions

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.

cs.SC↗

arXiv2016

Freshman or Fresher? Quantifying the Geographic Variation of Internet Language

We present a new computational technique to detect and analyze statistically significant geographic variation in language. Our meta-analysis approach captures statistical properties of word usage across geographical regions and uses statistical methods to identify significant changes specific to regions. While previous approaches have primarily focused on lexical variation between regions, our method identifies words that demonstrate semantic and syntactic variation as well. We extend recently developed techniques for neural language models to learn word representations which capture differing semantics across geographical regions. In order to quantify this variation and ensure robust detection of true regional differences, we formulate a null model to determine whether observed changes are statistically significant. Our method is the first such approach to explicitly account for random variation due to chance while detecting regional variation in word meaning. To validate our model, we study and analyze two different massive online data sets: millions of tweets from Twitter spanning not only four different countries but also fifty states, as well as millions of phrases contained in the Google Book Ngrams. Our analysis reveals interesting facets of language change at multiple scales of geographic resolution -- from neighboring states to distant continents. Finally, using our model, we propose a measure of semantic distance between languages. Our analysis of British and American English over a period of 100 years reveals that semantic variation between these dialects is shrinking.

cs.CL↗