arXiv subjects

Paramita Das

Publications and source records attributed to Paramita Das.

15 recordsLinked to original sources

arXiv2025

Social Biases in Knowledge Representations of Wikidata separates Global North from Global South

Knowledge Graphs have become increasingly popular due to their wide usage in various downstream applications, including information retrieval, chatbot development, language model construction, and many others. Link prediction (LP) is a crucial downstream task for knowledge graphs, as it helps to address the problem of the incompleteness of the knowledge graphs. However, previous research has shown that knowledge graphs, often created in a (semi) automatic manner, are not free from social biases. These biases can have harmful effects on downstream applications, especially by leading to unfair behavior toward minority groups. To understand this issue in detail, we develop a framework -- AuditLP -- deploying fairness metrics to identify biased outcomes in LP, specifically how occupations are classified as either male or female-dominated based on gender as a sensitive attribute. We have experimented with the sensitive attribute of age and observed that occupations are categorized as young-biased, old-biased, and age-neutral. We conduct our experiments on a large number of knowledge triples that belong to 21 different geographies extracted from the open-sourced knowledge graph, Wikidata. Our study shows that the variance in the biased outcomes across geographies neatly mirrors the socio-economic and cultural division of the world, resulting in a transparent partition of the Global North from the Global South.

cs.IR↗

arXiv2025

REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives

Wikipedia is an invaluable resource for factual information about a wide range of entities. However, the quality of articles on less-known entities often lags behind that of the well-known ones. This study proposes a novel approach to enhancing Wikipedia's B and C category biography articles by leveraging personal narratives such as autobiographies and biographies. By utilizing a multi-staged retrieval-augmented generation technique -- REVerSum -- we aim to enrich the informational content of these lesser-known articles. Our study reveals that personal narratives can significantly improve the quality of Wikipedia articles, providing a rich source of reliable information that has been underutilized in previous studies. Based on crowd-based evaluation, REVerSum generated content outperforms the best performing baseline by 17% in terms of integrability to the original Wikipedia article and 28.5\% in terms of informativeness. Code and Data are available at: https://github.com/sayantan11995/wikipedia_enrichment

cs.CL↗

arXiv2024

On the effective transfer of knowledge from English to Hindi Wikipedia

Although Wikipedia is the largest multilingual encyclopedia, it remains inherently incomplete. There is a significant disparity in the quality of content between high-resource languages (HRLs, e.g., English) and low-resource languages (LRLs, e.g., Hindi), with many LRL articles lacking adequate information. To bridge these content gaps, we propose a lightweight framework to enhance knowledge equity between English and Hindi. In case the English Wikipedia page is not up-to-date, our framework extracts relevant information from external resources readily available (such as English books) and adapts it to align with Wikipedia's distinctive style, including its \textit{neutral point of view} (NPOV) policy, using in-context learning capabilities of large language models. The adapted content is then machine-translated into Hindi for integration into the corresponding Wikipedia articles. On the other hand, if the English version is comprehensive and up-to-date, the framework directly transfers knowledge from English to Hindi. Our framework effectively generates new content for Hindi Wikipedia sections, enhancing Hindi Wikipedia articles respectively by 65% and 62% according to automatic and human judgment-based evaluations.

cs.CL↗

arXiv2024

Language-Agnostic Modeling of Wikipedia Articles for Content Quality Assessment across Languages

Wikipedia is the largest web repository of free knowledge. Volunteer editors devote time and effort to creating and expanding articles in more than 300 language editions. As content quality varies from article to article, editors also spend substantial time rating articles with specific criteria. However, keeping these assessments complete and up-to-date is largely impossible given the ever-changing nature of Wikipedia. To overcome this limitation, we propose a novel computational framework for modeling the quality of Wikipedia articles. State-of-the-art approaches to model Wikipedia article quality have leveraged machine learning techniques with language-specific features. In contrast, our framework is based on language-agnostic structural features extracted from the articles, a set of universal weights, and a language version-specific normalization criterion. Therefore, we ensure that all language editions of Wikipedia can benefit from our framework, even those that do not have their own quality assessment scheme. Using this framework, we have built datasets with the feature values and quality scores of all revisions of all articles in the existing language versions of Wikipedia. We provide a descriptive analysis of these resources and a benchmark of our framework. In addition, we discuss possible downstream tasks to be addressed with these datasets, which are released for public use.

cs.CY↗

arXiv2023

Diversity matters: Robustness of bias measurements in Wikidata

With the widespread use of knowledge graphs (KG) in various automated AI systems and applications, it is very important to ensure that information retrieval algorithms leveraging them are free from societal biases. Previous works have depicted biases that persist in KGs, as well as employed several metrics for measuring the biases. However, such studies lack the systematic exploration of the sensitivity of the bias measurements, through varying sources of data, or the embedding algorithms used. To address this research gap, in this work, we present a holistic analysis of bias measurement on the knowledge graph. First, we attempt to reveal data biases that surface in Wikidata for thirteen different demographics selected from seven continents. Next, we attempt to unfold the variance in the detection of biases by two different knowledge graph embedding algorithms - TransE and ComplEx. We conduct our extensive experiments on a large number of occupations sampled from the thirteen demographics with respect to the sensitive attribute, i.e., gender. Our results show that the inherent data bias that persists in KG can be altered by specific algorithm bias as incorporated by KG embedding learning algorithms. Further, we show that the choice of the state-of-the-art KG embedding algorithm has a strong impact on the ranking of biased occupations irrespective of gender. We observe that the similarity of the biased occupations across demographics is minimal which reflects the socio-cultural differences around the globe. We believe that this full-scale audit of the bias measurement pipeline will raise awareness among the community while deriving insights related to design choices of data and algorithms both and refrain from the popular dogma of ``one-size-fits-all''.

cs.LG↗

arXiv2022

Unitary connections on Bratteli diagrams

In this paper, we extend Ocneanu's theory of connections on graphs to define a 2-category whose 0-cells are tracial Bratteli diagrams, and whose 1-cells are generalizations of unitary connections. We show that this 2-category admits an embedding into the 2-category of hyperfinite von Neumann algebras, generalizing fundamental results from subfactor theory to a 2-categorical setting.

math.QA↗

arXiv2021

Quality change: norm or exception? Measurement, Analysis and Detection of Quality Change in Wikipedia

Wikipedia has been turned into an immensely popular crowd-sourced encyclopedia for information dissemination on numerous versatile topics in the form of subscription free content. It allows anyone to contribute so that the articles remain comprehensive and updated. For enrichment of content without compromising standards, the Wikipedia community enumerates a detailed set of guidelines, which should be followed. Based on these, articles are categorized into several quality classes by the Wikipedia editors with increasing adherence to guidelines. This quality assessment task by editors is laborious as well as demands platform expertise. As a first objective, in this paper, we study evolution of a Wikipedia article with respect to such quality scales. Our results show novel non-intuitive patterns emerging from this exploration. As a second objective we attempt to develop an automated data driven approach for the detection of the early signals influencing the quality change of articles. We posit this as a change point detection problem whereby we represent an article as a time series of consecutive revisions and encode every revision by a set of intuitive features. Finally, various change point detection algorithms are used to efficiently and accurately detect the future change points. We also perform various ablation studies to understand which group of features are most effective in identifying the change points. To the best of our knowledge, this is the first work that rigorously explores English Wikipedia article quality life cycle from the perspective of quality indicators and provides a novel unsupervised page level approach to detect quality switch, which can help in automatic content monitoring in Wikipedia thus contributing significantly to the CSCW community.

cs.SI↗

arXiv2021

When expertise gone missing: Uncovering the loss of prolific contributors in Wikipedia

Success of planetary-scale online collaborative platforms such as Wikipedia is hinged on active and continued participation of its voluntary contributors. The phenomenal success of Wikipedia as a valued multilingual source of information is a testament to the possibilities of collective intelligence. Specifically, the sustained and prudent contributions by the experienced prolific editors play a crucial role to operate the platform smoothly for decades. However, it has been brought to light that growth of Wikipedia is stagnating in terms of the number of editors that faces steady decline over time. This decreasing productivity and ever increasing attrition rate in both newcomer and experienced editors is a major concern for not only the future of this platform but also for several industry-scale information retrieval systems such as Siri, Alexa which depend on Wikipedia as knowledge store. In this paper, we have studied the ongoing crisis in which experienced and prolific editors withdraw. We performed extensive analysis of the editor activities and their language usage to identify features that can forecast prolific Wikipedians, who are at risk of ceasing voluntary services. To the best of our knowledge, this is the first work which proposes a scalable prediction pipeline, towards detecting the prolific Wikipedians, who might be at a risk of retiring from the platform and, thereby, can potentially enable moderators to launch appropriate incentive mechanisms to retain such `would-be missing' valued Wikipedians.

cs.SI↗

arXiv2016

Tube algebra of group-type subfactors

We describe the tube algebra and its representations in the cases of diagonal and Bisch-Haagerup subfactors possibly with a scalar 3-cocycle obstruction. We show that these categories are additively equivalent to the direct product over conjugacy classes of representation category of a centralizer subgroup (corresponding to the conjugacy class) twisted by a scalar 2-cocycle obtained from the 3-cocycle obstruction.

math.OA↗

arXiv2012

Drinfeld center of planar algebra

We introduce fusion, contragradient and braiding of Hilbert affine representations of a subfactor planar algebra $P$ (not necessarily having finite depth). We prove that if $N \subset M$ is a subfactor realization of $P$, then the Drinfeld center of the $N$-$N$-bimodule category generated by $_N L^2 (M)_M$, is equivalent to the category of Hilbert affine representations of $P$ satisfying certain finiteness criterion. As a consequence, we prove Kevin Walker's conjecture for planar algebras.

math.QA↗

arXiv2010

Weights on bimodules

The concept of a {\em weight} on a planar algebra was introduced in \cite{DGG}. In this article we give an alternate characterization of weights on a planar algebra in terms of `weight functions' on the vertices of the principal graphs. Using this characterization we show that the property of bifinite bimodules of having a `trivial perturbation class' is closed under Connes fusion. We give a direct and constructive method of perturbing a bifinite bimodule by a positive weight in such a way that the bimodule planar algebra of the perturbed bimodule is isomorphic to the perturbation of the one associated to the initial bimodule by the given weight.

math.QA↗

arXiv2010

Affine modules and the Drinfeld Center

Given a finite index subfactor, we show that the {\em affine morphisms at zero level} in the affine category over the planar algebra associated to the subfactor is isomorphic to the fusion algebra of the subfactor as a *-algebra. This identification paves the way to analyze the structure of affine $P$-modules with weight zero for any subfactor planar algebra $P$ (possibly having infinite depth). Further, for irreducible depth two subfactor planar algebras, we establish an additive equivalence between the category of affine $P$-modules and the center of the category of $N$-$N$-bimodules generated by $L^2(M)$; this partially verifies a conjecture of Jones and Walker.

math.QA↗

arXiv2010

Perturbations of planar algebras

We analyze the effect of pivotal structures (on a 2-category) on the planar algebra associated to a 1-cell as in \cite{Gho08} and come up with the notion of {\em perturbations of planar algebras by weights} (a concept that appeared earlier in Michael Burns' thesis \cite{Bur03}); we establish a one-to-one correspondence between weights and pivotal structures. Using the construction of \cite{Gho08}, to each bifinite bimodule over $II_1$-factors, we associate a {\em bimodule planar algebra} in such a way that extremality of the bimodule corresponds to sphericality of the planar algebra. As a consequence of this, we reproduce an extension of Jones' theorem (\cite{Jon}) (of associating `subfactor planar algebras' to extremal subfactors). Conversely, given a bimodule planar algebra, we construct a bifinite bimodule whose associated bimodule planar algebra is the one which we start with, using perturbations and Jones-Walker-Shlyakhtenko-Kodiyalam-Sunder method of reconstructing an extremal subfactor from a subfactor planar algebra. The perturbation technique helps us to construct an example of a family of non-spherical planar algebras starting from a particular spherical one; we also show that this family is associated to a known family of subfactors constructed by Jones.

math.QA↗

arXiv2009

The planar algebra of group-type subfactors

If $G$ is a countable, discrete group generated by two finite subgroups $H$ and $K$ and $P$ is a II$_1$ factor with an outer G-action, one can construct the group-type subfactor $P^H \subset P \rtimes K$ introduced in \cite{BH}. This construction was used in \cite{BH} to obtain numerous examples of infinite depth subfactors whose standard invariant has exotic growth properties. We compute the planar algebra (in the sense of Jones \cite{J2}) of this subfactor and prove that any subfactor with an abstract planar algebra of "group type" arises from such a subfactor. The action of Jones' planar operad is determined explicitly.

math.OA↗

arXiv2008

The planar algebra of diagonal subfactors

There is a natural construction which associates to a finitely generated, countable, discrete group $G$ and a 3-cocycle $ω$ of $G$ an inclusion of II$_1$ factors, the so-called diagonal subfactors (with cocycle). In the case when the cocycle is trivial these subfactors are well studied and their standard invariant (or planar algebra) is known. We give a description of the planar algebra of these subfactors when a cocycle is present. The action of Jones' planar operad involves the 3-cocycle $ω$ explicitly and some interesting identities for 3-cocycles appear when naturality of the action is verified.

math.OA↗