arXiv subjects

Avishek Anand

Publications and source records attributed to Avishek Anand.

At least 91 records · Page 5Linked to original sources

arXiv2019

TableNet: An Approach for Determining Fine-grained Relations for Wikipedia Tables

Wikipedia tables represent an important resource, where information is organized w.r.t table schemas consisting of columns. In turn each column, may contain instance values that point to other Wikipedia articles or primitive values (e.g. numbers, strings etc.). In this work, we focus on the problem of interlinking Wikipedia tables for two types of table relations: equivalent and subPartOf. Through such relations, we can further harness semantically related information by accessing related tables or facts therein. Determining the relation type of a table pair is not trivial, as it is dependent on the schemas, the values therein, and the semantic overlap of the cell values in the corresponding tables. We propose TableNet, an approach that constructs a knowledge graph of interlinked tables with subPartOf and equivalent relations. TableNet consists of two main steps: (i) for any source table we provide an efficient algorithm to find all candidate related tables with high coverage, and (ii) a neural based approach, which takes into account the table schemas, and the corresponding table data, we determine with high accuracy the table relation for a table pair. We perform an extensive experimental evaluation on the entire Wikipedia with more than 3.2 million tables. We show that with more than 88\% we retain relevant candidate tables pairs for alignment. Consequentially, with an accuracy of 90% we are able to align tables with subPartOf or equivalent relations. Comparisons with existing competitors show that TableNet has superior performance in terms of coverage and alignment accuracy.

cs.DB↗

arXiv2018

Asynchronous Training of Word Embeddings for Large Text Corpora

Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is typically sequentially processed and parameters are synchronously updated. Distributed architectures for asynchronous training that have been proposed either focus on scaling vocabulary sizes and dimensionality or suffer from expensive synchronization latencies. In this paper, we propose a scalable approach to train word embeddings by partitioning the input space instead in order to scale to massive text corpora while not sacrificing the performance of the embeddings. Our training procedure does not involve any parameter synchronization except a final sub-model merge phase that typically executes in a few minutes. Our distributed training scales seamlessly to large corpus sizes and we get comparable and sometimes even up to 45% performance improvement in a variety of NLP benchmarks using models trained by our distributed procedure which requires $1/10$ of the time taken by the baseline approach. Finally we also show that we are robust to missing words in sub-models and are able to effectively reconstruct word representations.

cs.LG↗

arXiv2018

Expedition: A Time-Aware Exploratory Search System Designed for Scholars

Archives are an important source of study for various scholars. Digitization and the web have made archives more accessible and led to the development of several time-aware exploratory search systems. However these systems have been designed for more general users rather than scholars. Scholars have more complex information needs in comparison to general users. They also require support for corpus creation during their exploration process. In this paper we present Expedition - a time-aware exploratory search system that addresses the requirements and information needs of scholars. Expedition possesses a suite of ad-hoc and diversity based retrieval models to address complex information needs; a newspaper-style user interface to allow for larger textual previews and comparisons; entity filters to more naturally refine a result list and an interactive annotated timeline which can be used to better identify periods of importance.

cs.IR↗

arXiv2018

History by Diversity: Helping Historians search News Archives

Longitudinal corpora like newspaper archives are of immense value to historical research, and time as an important factor for historians strongly influences their search behaviour in these archives. While searching for articles published over time, a key preference is to retrieve documents which cover the important aspects from important points in time which is different from standard search behavior. To support this search strategy, we introduce the notion of a Historical Query Intent to explicitly model a historian's search task and define an aspect-time diversification problem over news archives. We present a novel algorithm, HistDiv, that explicitly models the aspects and important time windows based on a historian's information seeking behavior. By incorporating temporal priors based on publication times and temporal expressions, we diversify both on the aspect and temporal dimensions. We test our methods by constructing a test collection based on The New York Times Collection with a workload of 30 queries of historical intent assessed manually. We find that HistDiv outperforms all competitors in subtopic recall with a slight loss in precision. We also present results of a qualitative user study to determine wether this drop in precision is detrimental to user experience. Our results show that users still preferred HistDiv's ranking.

cs.IR↗

arXiv2018

Discovering Entities with Just a Little Help from You

Linking entities like people, organizations, books, music groups and their songs in text to knowledge bases (KBs) is a fundamental task for many downstream search and mining applications. Achieving high disambiguation accuracy crucially depends on a rich and holistic representation of the entities in the KB. For popular entities, such a representation can be easily mined from Wikipedia, and many current entity disambiguation and linking methods make use of this fact. However, Wikipedia does not contain long-tail entities that only few people are interested in, and also at times lags behind until newly emerging entities are added. For such entities, mining a suitable representation in a fully automated fashion is very difficult, resulting in poor linking accuracy. What can automatically be mined, though, is a high-quality representation given the context of a new entity occurring in any text. Due to the lack of knowledge about the entity, no method can retrieve these occurrences automatically with high precision, resulting in a chicken-egg problem. To address this, our approach automatically generates candidate occurrences of entities, prompting the user for feedback to decide if the occurrence refers to the actual entity in question. This feedback gradually improves the knowledge and allows our methods to provide better candidate suggestions to keep the user engaged. We propose novel human-in-the-loop retrieval methods for generating candidates based on gradient interleaving of diversification and textual relevance approaches. We conducted extensive experiments on the FACC dataset, showing that our approaches convincingly outperform carefully selected baselines in both intrinsic and extrinsic measures while keeping users engaged.

cs.IR↗

arXiv2018

Designing Search Tasks for Archive Search

Longitudinal corpora like legal, corporate and newspaper archives are of immense value to a variety of users, and time as an important factor strongly influences their search behavior in these archives. While many systems have been developed to support users temporal information needs, questions remain over how users utilize these advances to satisfy their needs. Analyzing their search behavior will provide us with novel insights into search strategy, guide better interface and system design and highlight new problems for further research. In this paper we propose a set of search tasks, with varying complexity, that IIR researchers can utilize to study user search behavior in archives. We discuss how we created and refined these tasks as the result of a pilot study using a temporal search engine. We not only propose task descriptions but also pre and post-task evaluation mechanisms that can be employed for a large-scale study (crowdsourcing). Our initial findings show the viability of such tasks for investigating search behavior in archives.

cs.IR↗

arXiv2018

Interpreting search result rankings through intent modeling

Given the recent interest in arguably accurate yet non-interpretable neural models, even with textual features, for document ranking we try to answer questions relating to how to interpret rankings. In this paper we take first steps towards a framework for the interpretability of retrieval models with the aim of answering 3 main questions "What is the intent of the query according to the ranker?", "Why is a document ranked higher than another for the query?" and "Why is a document relevant to the query?" Our framework is predicated on the assumption that text based retrieval model behavior can be estimated using query expansions in conjunction with a simpler retrieval model irrespective of the underlying ranker. We conducted experiments with the Clueweb test collection. We show how our approach performs for both simpler models with a closed form notation (which allows us to measure the accuracy of the interpretation) and neural ranking models. Our results indicate that we can indeed interpret more complex models with reasonable accuracy under certain simplifying assumptions. In a case study we also show our framework can be employed to interpret the results of the DRMM neural retrieval model in various scenarios.

cs.IR↗

arXiv2018

EXS: Explainable Search Using Local Model Agnostic Interpretability

Retrieval models in information retrieval are used to rank documents for typically under-specified queries. Today machine learning is used to learn retrieval models from click logs and/or relevance judgments that maximizes an objective correlated with user satisfaction. As these models become increasingly powerful and sophisticated, they also become harder to understand. Consequently, it is hard for to identify artifacts in training, data specific biases and intents from a complex trained model like neural rankers even if trained purely on text features. EXS is a search system designed specifically to provide its users with insight into the following questions: `What is the intent of the query according to the ranker?', `Why is this document ranked higher than another?' and `Why is this document relevant to the query?'. EXS uses a version of a popular posthoc explanation method for classifiers -- LIME, adapted specifically to answer these questions. We show how such a system can effectively help a user understand the results of neural rankers and highlight areas of improvement.

cs.IR↗

arXiv2018

User Fairness in Recommender Systems

Recent works in recommendation systems have focused on diversity in recommendations as an important aspect of recommendation quality. In this work we argue that the post-processing algorithms aimed at only improving diversity among recommendations lead to discrimination among the users. We introduce the notion of user fairness which has been overlooked in literature so far and propose measures to quantify it. Our experiments on two diversification algorithms show that an increase in aggregate diversity results in increased disparity among the users.

cs.CY↗

arXiv2018

Posthoc Interpretability of Learning to Rank Models using Secondary Training Data

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features influence the model prediction avoiding algorithmic transparency. Rankings are ordering over items encoding implicit comparisons typically learned using a family of features using learning-to-rank models. In this paper we focus on how best we can understand the decisions made by a ranker in a post-hoc model agnostic manner. We operate on the notion of interpretability based on explainability of rankings over an interpretable feature space. Furthermore we train a tree based model (inherently interpretable) using labels from the ranker, called secondary training data to provide explanations. Consequently, we attempt to study how well does a subset of features, potentially interpretable, explain the full model under different training sizes and algorithms. We do experiments on the learning to rank datasets with 30k queries and report results that serve show in certain settings we can learn a faithful interpretable ranker.

cs.IR↗

arXiv2017

Fine Grained Citation Span for References in Wikipedia

\emph{Verifiability} is one of the core editing principles in Wikipedia, editors being encouraged to provide citations for the added content. For a Wikipedia article, determining the \emph{citation span} of a citation, i.e. what content is covered by a citation, is important as it helps decide for which content citations are still missing. We are the first to address the problem of determining the \emph{citation span} in Wikipedia articles. We approach this problem by classifying which textual fragments in an article are covered by a citation. We propose a sequence classification approach where for a paragraph and a citation, we determine the citation span at a fine-grained level. We provide a thorough experimental evaluation and compare our approach against baselines adopted from the scientific domain, where we show improvement for all evaluation metrics.

cs.CL↗

arXiv2017

Finding News Citations for Wikipedia

An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated or missing altogether. In this work we address the problem of finding and updating news citations for statements in entity pages. We propose a two-stage supervised approach for this problem. In the first step, we construct a classifier to find out whether statements need a news citation or other kinds of citations (web, book, journal, etc.). In the second step, we develop a news citation algorithm for Wikipedia statements, which recommends appropriate citations from a given news collection. Apart from IR techniques that use the statement to query the news collection, we also formalize three properties of an appropriate citation, namely: (i) the citation should entail the Wikipedia statement, (ii) the statement should be central to the citation, and (iii) the citation should be from an authoritative source. We perform an extensive evaluation of both steps, using 20 million articles from a real-world news collection. Our results are quite promising, and show that we can perform this task with high precision and at scale.

cs.IR↗

arXiv2017

How much is Wikipedia Lagging Behind News?

Wikipedia, rich in entities and events, is an invaluable resource for various knowledge harvesting, extraction and mining tasks. Numerous resources like DBpedia, YAGO and other knowledge bases are based on extracting entity and event based knowledge from it. Online news, on the other hand, is an authoritative and rich source for emerging entities, events and facts relating to existing entities. In this work, we study the creation of entities in Wikipedia with respect to news by studying how entity and event based information flows from news to Wikipedia. We analyze the lag of Wikipedia (based on the revision history of the English Wikipedia) with 20 years of \emph{The New York Times} dataset (NYT). We model and analyze the lag of entities and events, namely their first appearance in Wikipedia and in NYT, respectively. In our extensive experimental analysis, we find that almost 20\% of the external references in entity pages are news articles encoding the importance of news to Wikipedia. Second, we observe that the entity-based lag follows a normal distribution with a high standard deviation, whereas the lag for news-based events is typically very low. Finally, we find that events are responsible for creation of emergent entities with as many as 12\% of the entities mentioned in the event page are created after the creation of the event page.

cs.IR↗

arXiv2017

Automated News Suggestions for Populating Wikipedia Entity Pages

Wikipedia entity pages are a valuable source of information for direct consumption and for knowledge-base construction, update and maintenance. Facts in these entity pages are typically supported by references. Recent studies show that as much as 20\% of the references are from online news sources. However, many entity pages are incomplete even if relevant information is already available in existing news articles. Even for the already present references, there is often a delay between the news article publication time and the reference time. In this work, we therefore look at Wikipedia through the lens of news and propose a novel news-article suggestion task to improve news coverage in Wikipedia, and reduce the lag of newsworthy references. Our work finds direct application, as a precursor, to Wikipedia page generation and knowledge-base acceleration tasks that rely on relevant and high quality input sources. We propose a two-stage supervised approach for suggesting news articles to entity pages for a given state of Wikipedia. First, we suggest news articles to Wikipedia entities (article-entity placement) relying on a rich set of features which take into account the \emph{salience} and \emph{relative authority} of entities, and the \emph{novelty} of news articles to entity pages. Second, we determine the exact section in the entity page for the input article (article-section placement) guided by class-based section templates. We perform an extensive evaluation of our approach based on ground-truth data that is extracted from external references in Wikipedia. We achieve a high precision value of up to 93\% in the \emph{article-entity} suggestion stage and upto 84\% for the \emph{article-section placement}. Finally, we compare our approach against competitive baselines and show significant improvements.

cs.IR↗

arXiv2017

Tempas: Temporal Archive Search Based on Tags

Limited search and access patterns over Web archives have been well documented. One of the key reasons is the lack of understanding of the user access patterns over such collections, which in turn is attributed to the lack of effective search interfaces. Current search interfaces for Web archives are (a) either purely navigational or (b) have sub-optimal search experience due to ineffective retrieval models or query modeling. We identify that external longitudinal resources, such as social bookmarking data, are crucial sources to identify important and popular websites in the past. To this extent we present Tempas, a tag-based temporal search engine for Web archives. Websites are posted at specific times of interest on several external platforms, such as bookmarking sites like Delicious. Attached tags not only act as relevant descriptors useful for retrieval, but also encode the time of relevance. With Tempas we tackle the challenge of temporally searching a Web archive by indexing tags and time. We allow temporal selections for search terms, rank documents based on their popularity and also provide meaningful query recommendations by exploiting tag-tag and tag-document co-occurrence statistics in arbitrary time windows. Finally, Tempas operates as a fairly non-invasive indexing framework. By not dealing with contents from the actual Web archive it constitutes an attractive and low-overhead approach for quick access into Web archives.

cs.IR↗

arXiv2017

The Dawn of Today's Popular Domains: A Study of the Archived German Web over 18 Years

The Web has been around and maturing for 25 years. The popular websites of today have undergone vast changes during this period, with a few being there almost since the beginning and many new ones becoming popular over the years. This makes it worthwhile to take a look at how these sites have evolved and what they might tell us about the future of the Web. We therefore embarked on a longitudinal study spanning almost the whole period of the Web, based on data collected by the Internet Archive starting in 1996, to retrospectively analyze how the popular Web as of now has evolved over the past 18 years. For our study we focused on the German Web, specifically on the top 100 most popular websites in 17 categories. This paper presents a selection of the most interesting findings in terms of volume, size as well as age of the Web. While related work in the field of Web Dynamics has mainly focused on change rates and analyzed datasets spanning less than a year, we looked at the evolution of websites over 18 years. We found that around 70% of the pages we investigated are younger than a year, with an observed exponential growth in age as well as in size up to now. If this growth rate continues, the number of pages from the popular domains will almost double in the next two years. In addition, we give insights into our data set, provided by the Internet Archive, which hosts the largest and most complete Web archive as of today.

cs.DL↗

arXiv2017

ArchiveSpark: Efficient Web Archive Access, Extraction and Derivation

Web archives are a valuable resource for researchers of various disciplines. However, to use them as a scholarly source, researchers require a tool that provides efficient access to Web archive data for extraction and derivation of smaller datasets. Besides efficient access we identify five other objectives based on practical researcher needs such as ease of use, extensibility and reusability. Towards these objectives we propose ArchiveSpark, a framework for efficient, distributed Web archive processing that builds a research corpus by working on existing and standardized data formats commonly held by Web archiving institutions. Performance optimizations in ArchiveSpark, facilitated by the use of a widely available metadata index, result in significant speed-ups of data processing. Our benchmarks show that ArchiveSpark is faster than alternative approaches without depending on any additional data stores while improving usability by seamlessly integrating queries and derivations with external tools.

cs.DL↗

arXiv2017

On the Applicability of Delicious for Temporal Search on Web Archives

Web archives are large longitudinal collections that store webpages from the past, which might be missing on the current live Web. Consequently, temporal search over such collections is essential for finding prominent missing webpages and tasks like historical analysis. However, this has been challenging due to the lack of popularity information and proper ground truth to evaluate temporal retrieval models. In this paper we investigate the applicability of external longitudinal resources to identify important and popular websites in the past and analyze the social bookmarking service Delicious for this purpose. The timestamped bookmarks on Delicious provide explicit cues about popular time periods in the past along with relevant descriptors. These are valuable to identify important documents in the past for a given temporal query. Focusing purely on recall, we analyzed more than 12,000 queries and find that using Delicious yields average recall values from 46% up to 100%, when limiting ourselves to the best represented queries in the considered dataset. This constitutes an attractive and low-overhead approach for quick access into Web archives by not dealing with the actual contents.

cs.IR↗