Sarthak Dash

Liangliang Zhang, Nandana Mihindukulasooriya, Niharika S. D'Souza et al.

Data products are reusable, self-contained assets designed for specific business use cases. Automating their discovery is of great industry interest, as it enables efficient data access in large data lakes and supports analytical workflows. However, no benchmark currently exists for data product discovery over hybrid table-text corpora. Existing datasets focus on answering single factoid questions over individual tables rather than assembling multiple related data assets into coherent products. To address this gap, we present DPDisc, the first large-scale benchmark for data product discovery, where systems must retrieve coherent collections of tables and passages to satisfy high-level Data Product Requests (DPRs). We introduce DPForge, an automated pipeline that systematically repurposes table-text QA datasets by clustering related tables and passages into coherent data products, generating professional-level analytical requests using an LLM ensemble, and validating quality through multi-phase LLM evaluation. DPDisc comprises 13,076 validated instances with full provenance, derived from three representative datasets spanning open-domain and financial domains. Baseline experiments with sparse, dense, and hybrid retrieval methods imply evaluation feasibility while revealing substantial performance gaps across domains, indicating opportunities for future research in structure-aware data product discovery. Code and datasets are available at: Dataset: https://huggingface.co/datasets/ibm-research/data-product-benchmark Code: https://github.com/ibm/data-product-benchmark

Faisal Chowdhury, Sola Shirai, Sarthak Dash et al.

A data product is created with the intention of solving a specific problem, addressing a specific business usecase or meeting a particular need, going beyond just serving data as a raw asset. Data products enable end users to gain greater insights about their data. Since it was first introduced over a decade ago, there has been considerable work, especially in industry, to create data products manually or semi-automatically. However, there exists hardly any benchmark to evaluate automatic data product creation. In this work, we present a benchmark, first of its kind, for this task. We call it DP-Bench. We describe how this benchmark was created by taking advantage of existing work in ELT (Extract-Load-Transform) and Text-to-SQL benchmarks. We also propose a number of LLM based approaches that can be considered as baselines for generating data products automatically. We make the DP-Bench and supplementary materials available in https://huggingface.co/datasets/ibm-research/dp-bench .

Sarthak Dash, Nandana Mihindukulasooriya, Alfio Gliozzo et al.

Inferring semantic types for entity mentions within text documents is an important asset for many downstream NLP tasks, such as Semantic Role Labelling, Entity Disambiguation, Knowledge Base Question Answering, etc. Prior works have mostly focused on supervised solutions that generally operate on relatively small-to-medium-sized type systems. In this work, we describe two systems aimed at predicting type information for the following two tasks, namely, a TypeSuggest module, an unsupervised system designed to predict types for a set of user-entered query terms, and an Answer Type prediction module, that provides a solution for the task of determining the correct type of the answer expected to a given query. Our systems generalize to arbitrary type systems of any sizes, thereby making it a highly appealing solution to extract type information at any granularity.

Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya et al.

Noun phrases and Relation phrases in open knowledge graphs are not canonicalized, leading to an explosion of redundant and ambiguous subject-relation-object triples. Existing approaches to solve this problem take a two-step approach. First, they generate embedding representations for both noun and relation phrases, then a clustering algorithm is used to group them using the embeddings as features. In this work, we propose Canonicalizing Using Variational Autoencoders (CUVA), a joint model to learn both embeddings and cluster assignments in an end-to-end approach, which leads to a better vector representation for the noun and relation phrases. Our evaluation over multiple benchmarks shows that CUVA outperforms the existing state-of-the-art approaches. Moreover, we introduce CanonicNell, a novel dataset to evaluate entity canonicalization systems.

Sarthak Dash, Md Faisal Mahbub Chowdhury, Alfio Gliozzo et al.

This paper introduces Strict Partial Order Networks (SPON), a novel neural network architecture designed to enforce asymmetry and transitive properties as soft constraints. We apply it to induce hypernymy relations by training with is-a pairs. We also present an augmented variant of SPON that can generalize type information learned for in-vocabulary terms to previously unseen ones. An extensive evaluation over eleven benchmarks across different tasks shows that SPON consistently either outperforms or attains the state of the art on all but one of these benchmarks.

Sarthak Dash, Michael R. Glass, Alfio Gliozzo et al.

In this paper, we propose a fully automated system to extend knowledge graphs using external information from web-scale corpora. The designed system leverages a deep learning based technology for relation extraction that can be trained by a distantly supervised approach. In addition to that, the system uses a deep learning approach for knowledge base completion by utilizing the global structure information of the induced KG to further refine the confidence of the newly discovered relations. The designed system does not require any effort for adaptation to new languages and domains as it does not use any hand-labeled data, NLP analytics and inference rules. Our experiments, performed on a popular academic benchmark demonstrate that the suggested system boosts the performance of relation extraction by a wide margin, reporting error reductions of 50%, resulting in relative improvement of up to 100%. Also, a web-scale experiment conducted to extend DBPedia with knowledge from Common Crawl shows that our system is not only scalable but also does not require any adaptation cost, while yielding substantial accuracy gain.

Sarthak Dash, Alfio Gliozzo

State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling of entities. In this paper, we argue that random sampling is not a good training strategy since it is highly likely to generate a huge number of nonsensical assertions during training, which does not provide relevant training signal to the system. Hence, it slows down the learning process and decreases accuracy. To address this issue, we propose an alternative approach called Distributional Negative Sampling that generates meaningful negative examples which are highly likely to be false. Our approach achieves a significant improvement in Mean Reciprocal Rank values amongst two different KBC algorithms in three standard academic benchmarks.