arXiv subjects

Venktesh V

Publications and source records attributed to Venktesh V.

22 records · Page 2Linked to original sources

arXiv2022

Topic Aware Contextualized Embeddings for High Quality Phrase Extraction

Keyphrase extraction from a given document is the task of automatically extracting salient phrases that best describe the document. This paper proposes a novel unsupervised graph-based ranking method to extract high-quality phrases from a given document. We obtain the contextualized embeddings from pre-trained language models enriched with topic vectors from Latent Dirichlet Allocation (LDA) to represent the candidate phrases and the document. We introduce a scoring mechanism for the phrases using the information obtained from contextualized embeddings and the topic vectors. The salient phrases are extracted using a ranking algorithm on an undirected graph constructed for the given document. In the undirected graph, the nodes represent the phrases, and the edges between the phrases represent the semantic relatedness between them, weighted by a score obtained from the scoring mechanism. To demonstrate the efficacy of our proposed method, we perform several experiments on open source datasets in the science domain and observe that our novel method outperforms existing unsupervised embedding based keyphrase extraction methods. For instance, on the SemEval2017 dataset, our method advances the F1 score from 0.2195 (EmbedRank) to 0.2819 at the top 10 extracted keyphrases. Several variants of the proposed algorithm are investigated to determine their effect on the quality of keyphrases. We further demonstrate the ability of our proposed method to collect additional high-quality keyphrases that are not present in the document from external knowledge bases like Wikipedia for enriching the document with newly discovered keyphrases. We evaluate this step on a collection of annotated documents. The F1-score at the top 10 expanded keyphrases is 0.60, indicating that our algorithm can also be used for 'concept' expansion using external knowledge.

cs.IR↗

arXiv2021

TagRec: Automated Tagging of Questions with Hierarchical Learning Taxonomy

Online educational platforms organize academic questions based on a hierarchical learning taxonomy (subject-chapter-topic). Automatically tagging new questions with existing taxonomy will help organize these questions into different classes of hierarchical taxonomy so that they can be searched based on the facets like chapter. This task can be formulated as a flat multi-class classification problem. Usually, flat classification based methods ignore the semantic relatedness between the terms in the hierarchical taxonomy and the questions. Some traditional methods also suffer from the class imbalance issues as they consider only the leaf nodes ignoring the hierarchy. Hence, we formulate the problem as a similarity-based retrieval task where we optimize the semantic relatedness between the taxonomy and the questions. We demonstrate that our method helps to handle the unseen labels and hence can be used for taxonomy tagging in the wild. In this method, we augment the question with its corresponding answer to capture more semantic information and then align the question-answer pair's contextualized embedding with the corresponding label (taxonomy) vector representations. The representations are aligned by fine-tuning a transformer based model with a loss function that is a combination of the cosine similarity and hinge rank loss. The loss function maximizes the similarity between the question-answer pair and the correct label representations and minimizes the similarity to unrelated labels. Finally, we perform experiments on two real-world datasets. We show that the proposed learning method outperforms representations learned using the multi-class classification method and other state of the art methods by 6% as measured by Recall@k. We also demonstrate the performance of the proposed method on unseen but related learning content like the learning objectives without re-training the network.

cs.CL↗

arXiv2021

Fake News Detection System using XLNet model with Topic Distributions: CONSTRAINT@AAAI2021 Shared Task

With the ease of access to information, and its rapid dissemination over the internet (both velocity and volume), it has become challenging to filter out truthful information from fake ones. The research community is now faced with the task of automatic detection of fake news, which carries real-world socio-political impact. One such research contribution came in the form of the Constraint@AAA12021 Shared Task on COVID19 Fake News Detection in English. In this paper, we shed light on a novel method we proposed as a part of this shared task. Our team introduced an approach to combine topical distributions from Latent Dirichlet Allocation (LDA) with contextualized representations from XLNet. We also compared our method with existing baselines to show that XLNet + Topic Distributions outperforms other approaches by attaining an F1-score of 0.967.

cs.CL↗

arXiv2020

OneStopTuner: An End to End Architecture for JVM Tuning of Spark Applications

Java is the backbone of widely used big data frameworks, such as Apache Spark, due to its productivity, portability from JVM-based execution, and support for a rich set of libraries. However, the performance of these applications can widely vary depending on the runtime flags chosen out of all existing JVM flags. Manually tuning these flags is both cumbersome and error-prone. Automated tuning approaches can ease the task, but current solutions either require considerable processing time or target a subset of flags to avoid time and space requirements. In this paper, we present OneStopTuner, a Machine Learning based novel framework for autotuning JVM flags. OneStopTuner controls the amount of data generation by leveraging batch mode active learning to characterize the user application. Based on the user-selected optimization metric, OneStopTuner then discards the irrelevant JVM flags by applying feature selection algorithms on the generated data. Finally, it employs sample efficient methods such as Bayesian optimization and regression guided Bayesian optimization on the shortlisted JVM flags to find the optimal values for the chosen set of flags. We evaluated OneStopTuner on widely used Spark benchmarks and compare its performance with the traditional simulated annealing based autotuning approach. We demonstrate that for optimizing execution time, the flags chosen by OneStopTuner provides a speedup of up to 1.35x over default Spark execution, as compared to 1.15x speedup by using the flag configurations proposed by simulated annealing. OneStopTuner was able to reduce the number of executions for data-generation by 70% and was able to suggest the optimal flag configuration 2.4x faster than the standard simulated annealing based approach, excluding the time for data-generation.

cs.DC↗