Browsing by Author "Subbian, Karthik"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
- Accepted Tutorials at The Web Conference 2022Tommasini, Riccardo; Basu Roy, Senjuti; Wang, Xuan; Wang, Hongwei; Ji, Heng; Han, Jiawei; Nakov, Preslav; Da San Martino, Giovanni; Alam, Firoj; Schedl, Markus; Lex, Elisabeth; Bharadwaj, Akash; Cormode, Graham; Dojchinovski, Milan; Forberg, Jan; Frey, Johannes; Bonte, Pieter; Balduini, Marco; Belcao, Matteo; Della Valle, Emanuele; Yu, Junliang; Yin, Hongzhi; Chen, Tong; Liu, Haochen; Wang, Yiqi; Fan, Wenqi; Liu, Xiaorui; Dacon, Jamell; Lye, Lingjuan; Tang, Jiliang; Gionis, Aristides; Neumann, Stefan; Ordozgoiti, Bruno; Razniewski, Simon; Arnaout, Hiba; Ghosh, Shrestha; Suchanek, Fabian; Wu, Lingfei; Chen, Yu; Li, Yunyao; Liu, Bang; Ilievski, Filip; Garijo, Daniel; Chalupsky, Hans; Szekely, Pedro; Kanellos, Ilias; Sacharidis, Dimitris; Vergoulis, Thanasis; Choudhary, Nurendra; Rao, Nikhil; Subbian, Karthik; Sengamedu, Srinivasan; Reddy, Chandan; Victor, Friedhelm; Haslhofer, Bernhard; Katsogiannis- Meimarakis, George; Koutrika, Georgia; Jin, Shengmin; Koutra, Danai; Zafarani, Reza; Tsvetkov, Yulia; Balachandran, Vidhisha; Kumar, Sachin; Zhao, Xiangyu; Chen, Bo; Guo, Huifeng; Wang, Yejing; Tang, Ruiming; Zhang, Yang; Wang, Wenjie; Wu, Peng; Feng, Fuli; He, Xiangnan (ACM, 2022-04-25)This paper summarizes the content of the 20 tutorials that have been given at The Web Conference 2022: 85% of these tutorials are lecture style, and 15% of these are hands on.
- ANTHEM: Attentive Hyperbolic Entity Model for Product SearchChoudhary, Nurendra; Rao, Nikhil; Katariya, Sumeet; Subbian, Karthik; Reddy, Chandan K. (ACM, 2022-02-11)Product search is a fundamentally challenging problem due to the large-size of product catalogues and the complexity of extracting semantic information from products. In addition to this, the blackbox nature of most search systems also hamper a smooth customer experience. Current approaches in this area utilize lexical and semantic product information to match user queries against products. However, these models lack (i) a hierarchical query representation, (ii) a mechanism to detect and capture inter-entity relationships within a query, and (iii) a query composition method specific to e-commerce domain. To address these challenges, in this paper, we propose an AtteNTive Hyperbolic Entity Model (ANTHEM), a novel attention-based product search framework that models query entities as two-vector hyperboloids, learns inter-entity intersections and utilizes attention to unionize individual entities and inter-entity intersections to predict product matches from the search space. ANTHEM utilizes the first and second vector of hyperboloids to determine the query’s semantic position and to tune its surrounding search volume, respectively. The attention networks capture the significance of intra-entity and inter-entity intersections to the final query space. Additionally, we provide a mechanism to comprehend ANTHEM and understand the significance of query entities towards the final resultant products. We evaluate the performance of our model on real data collected from popular e-commerce sites. Our experimental study on the offline data demonstrates compelling evidence of ANTHEM’s superior performance over state-of-the-art product search methods with an improvement of more than 10% on various metrics. We also demonstrate the quality of ANTHEM’s query encoder using a query matching task.
- An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-CommerceChoudhary, Nurendra; Huang, Edward W.; Subbian, Karthik; Reddy, Chandan (ACM, 2024-05-13)The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user’s short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been addressed using language models (LMs) and graph neural networks (GNNs) to capture semantic and inter-product behavior signals, respectively. However, the rapid development of new architectures has created a gap between research and the practical adoption of these techniques. Evaluating the generalizability of these models for deployment requires extensive experimentation on complex, real-world datasets, which can be non-trivial and expensive. Furthermore, such models often operate on latent space representations that are incomprehensible to humans, making it difficult to evaluate and compare the effectiveness of different models. This lack of interpretability hinders the development and adoption of new techniques in the field. To bridge this gap, we propose Plug and Play Graph LAnguage Model (PP-GLAM), an explainable ensemble of plug and play models. Our approach uses a modular framework with uniform data processing pipelines. It employs additive explanation metrics to independently decide whether to include (i) language model candidates, (ii) GNN model candidates, and (iii) inter-product behavioral signals. For the task of search relevance, we show that PP-GLAM outperforms several state-of-the-art baselines as well as a proprietary model on real-world multilingual, multi-regional e-commerce datasets. To promote better model comprehensibility and adoption, we also provide an analysis of the explainability and computational complexity of our model. We also provide the public codebase and provide a deployment strategy for practical implementation.
- Multimodal Representation Learning for Textual Reasoning over Knowledge GraphsChoudhary, Nurendra (Virginia Tech, 2023-05-18)Knowledge graphs (KGs) store relational information in a flexible triplet schema and have become ubiquitous for information storage in domains such as web search, e-commerce, social networks, and biology. Retrieval of information from KGs is generally achieved through logical reasoning, but this process can be computationally expensive and has limited performance due to the large size and complexity of relationships within the KGs. Furthermore, to extend the usage of KGs to non-expert users, retrieval over them cannot solely rely on logical reasoning but also needs to consider text-based search. This creates a need for multi-modal representations that capture both the semantic and structural features from the KGs. The primary objective of the proposed work is to extend the accessibility of KGs to non-expert users/institutions by enabling them to utilize non-technical textual queries to search over the vast amount of information stored in KGs. To achieve this objective, the research aims to solve four limitations: (i) develop a framework for logical reasoning over KGs that can learn representations to capture hierarchical dependencies between entities, (ii) design an architecture that can effectively learn the logic flow of queries from natural language text, (iii) create a multi-modal architecture that can capture inherent semantic and structural features from the entities and KGs, respectively, and (iv) introduce a novel hyperbolic learning framework to enable the scalability of hyperbolic neural networks over large graphs using meta-learning. The proposed work is distinct from current research because it models the logical flow of textual queries in hyperbolic space and uses it to perform complex reasoning over large KGs. The models developed in this work are evaluated on both the standard research setting of logical reasoning, as well as, real-world scenarios of query matching and search, specifically, in the e-commerce domain. In summary, the proposed work aims to extend the accessibility of KGs to non-expert users by enabling them to use non-technical textual queries to search vast amounts of information stored in KGs. To achieve this objective, the work proposes the use of multi-modal representations that capture both semantic and structural features from the KGs, and a novel hyperbolic learning framework to enable scalability of hyperbolic neural networks over large graphs. The work also models the logical flow of textual queries in hyperbolic space to perform complex reasoning over large KGs. The models developed in this work are evaluated on both the standard research setting of logical reasoning and real-world scenarios in the e-commerce domain.
- Novel Algorithms for Understanding Online ReviewsShi, Tian (Virginia Tech, 2021-09-14)This dissertation focuses on the review understanding problem, which has gained attention from both industry and academia, and has found applications in many downstream tasks, such as recommendation, information retrieval and review summarization. In this dissertation, we aim to develop machine learning and natural language processing tools to understand and learn structured knowledge from unstructured reviews, which can be investigated in three research directions, including understanding review corpora, understanding review documents, and understanding review segments. For the corpus-level review understanding, we have focused on discovering knowledge from corpora that consist of short texts. Since they have limited contextual information, automatically learning topics from them remains a challenging problem. We propose a semantics-assisted non-negative matrix factorization model to deal with this problem. It effectively incorporates the word-context semantic correlations into the model, where the semantic relationships between the words and their contexts are learned from the skip-gram view of a corpus. We conduct extensive sets of experiments on several short text corpora to demonstrate the proposed model can discover meaningful and coherent topics. For document-level review understanding, we have focused on building interpretable and reliable models for the document-level multi-aspect sentiment analysis (DMSA) task, which can help us to not only recover missing aspect-level ratings and analyze sentiment of customers, but also detect aspect and opinion terms from reviews. We conduct three studies in this research direction. In the first study, we collect a new DMSA dataset in the healthcare domain and systematically investigate reviews in this dataset, including a comprehensive statistical analysis and topic modeling to discover aspects. We also propose a multi-task learning framework with self-attention networks to predict sentiment and ratings for given aspects. In the second study, we propose corpus-level and concept-based explanation methods to interpret attention-based deep learning models for text classification, including sentiment classification. The proposed corpus-level explanation approach aims to capture causal relationships between keywords and model predictions via learning importance of keywords for predicted labels across a training corpus based on attention weights. We also propose a concept-based explanation method that can automatically learn higher level concepts and their importance to model predictions. We apply these methods to the classification task and show that they are powerful in extracting semantically meaningful keywords and concepts, and explaining model predictions. In the third study, we propose an interpretable and uncertainty aware multi-task learning framework for DMSA, which can achieve competitive performance while also being able to interpret the predictions made. Based on the corpus-level explanation method, we propose an attention-driven keywords ranking method, which can automatically discover aspect terms and aspect-level opinion terms from a review corpus using the attention weights. In addition, we propose a lecture-audience strategy to estimate model uncertainty in the context of multi-task learning. For the segment-level review understanding, we have focused on the unsupervised aspect detection task, which aims to automatically extract interpretable aspects and identify aspect-specific segments from online reviews. The existing deep learning-based topic models suffer from several problems such as extracting noisy aspects and poorly mapping aspects discovered by models to the aspects of interest. To deal with these problems, we propose a self-supervised contrastive learning framework in order to learn better representations for aspects and review segments. We also introduce a high-resolution selective mapping method to efficiently assign aspects discovered by the model to the aspects of interest. In addition, we propose using a knowledge distillation technique to further improve the aspect detection performance.
- Probabilistic Entity Representation Model for Reasoning over Knowledge GraphsChoudhary, Nurendra; Rao, Nikhil; Katariya, Sumeet; Subbian, Karthik; Reddy, Chandan K. (2021-10-26)Logical reasoning over Knowledge Graphs (KGs) is a fundamental technique that can provide efficient querying mechanism over large and incomplete databases. Current approaches employ spatial geometries such as boxes to learn query representations that encompass the answer entities and model the logical operations of projection and intersection. However, their geometry is restrictive and leads to non-smooth strict boundaries, which further results in ambiguous answer entities. Furthermore, previous works propose transformation tricks to handle unions which results in non-closure and, thus, cannot be chained in a stream. In this paper, we propose a Probabilistic Entity Representation Model (PERM) to encode entities as a Multivariate Gaussian density with mean and covariance parameters to capture its semantic position and smooth decision boundary, respectively. Additionally, we also define the closed logical operations of projection, intersection, and union that can be aggregated using an end-to-end objective function. On the logical query reasoning problem, we demonstrate that the proposed PERM significantly outperforms the state-of-the-art methods on various public benchmark KG datasets on standard evaluation metrics. We also evaluate PERM’s competence on a COVID-19 drugrepurposing case study and show that our proposed work is able to recommend drugs with substantially better F1 than current methods. Finally, we demonstrate the working of our PERM’s query answering process through a low-dimensional visualization of the Gaussian representations.
- Self-supervised Short Text Modeling through Auxiliary Context GenerationChoudhary, Nurendra; Aggarwal, Charu; Subbian, Karthik; Reddy, Chandan K. (ACM, 2022-04-12)Short text is ambiguous and often relies predominantly on the domain and context at hand in order to attain semantic relevance. Existing classification models perform poorly on short text due to data sparsity and inadequate context. Auxiliary context, which can often provide sufficient background regarding the domain, is typically available in several application scenarios. While some of the existing works aim to leverage real-world knowledge to enhance short text representations, they fail to place appropriate emphasis on the auxiliary context. Such models do not harness the full potential of the available context in auxiliary sources. To address this challenge, we reformulate short text classification as a dual channel self-supervised learning problem (that leverages auxiliary context) with a generation network and a corresponding prediction model. We propose a self-supervised framework, Pseudo-Auxiliary Context generation network for Short text Modeling (PACS), to comprehensively leverage auxiliary context and is jointly learned with a prediction network in an end-to-end manner. Our PACS model consists of two sub-networks: a Context Generation Network (CGN) that models the auxiliary context?s distribution and a Prediction Network (PN) to map the short text features and auxiliary context distribution to the final class label. Our experimental results on diverse datasets demonstrate that PACS outperforms formidable state-of-the-art baselines. We also demonstrate the performance of our model on cold start scenarios (where contextual information is non-existent) during prediction. Furthermore, we perform interpretability and ablation studies to analyze various representational features captured by our model and the individual contribution of its modules to the overall performance of PACS, respectively.