Harsh Thakkar

Spurthi Setty, Harsh Thakkar, Alyssa Lee et al.

The effectiveness of Large Language Models (LLMs) in generating accurate responses relies heavily on the quality of input provided, particularly when employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by sourcing the most relevant text chunk(s) to base queries upon. Despite the significant advancements in LLMs' response quality in recent years, users may still encounter inaccuracies or irrelevant answers; these issues often stem from suboptimal text chunk retrieval by RAG rather than the inherent capabilities of LLMs. To augment the efficacy of LLMs, it is crucial to refine the RAG process. This paper explores the existing constraints of RAG pipelines and introduces methodologies for enhancing text retrieval. It delves into strategies such as sophisticated chunking techniques, query expansion, the incorporation of metadata annotations, the application of re-ranking algorithms, and the fine-tuning of embedding algorithms. Implementing these approaches can substantially improve the retrieval quality, thereby elevating the overall performance and reliability of LLMs in processing and responding to queries.

Endri Kacupaj, Joan Plepi, Kuldeep Singh et al.

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.

Joan Plepi, Endri Kacupaj, Kuldeep Singh et al.

Neural semantic parsing approaches have been widely used for Question Answering (QA) systems over knowledge graphs. Such methods provide the flexibility to handle QA datasets with complex queries and a large number of entities. In this work, we propose a novel framework named CARTON, which performs multi-task semantic parsing for handling the problem of conversational question answering over a large-scale knowledge graph. Our framework consists of a stack of pointer networks as an extension of a context transformer model for parsing the input question and the dialog history. The framework generates a sequence of actions that can be executed on the knowledge graph. We evaluate CARTON on a standard dataset for complex sequential question answering on which CARTON outperforms all baselines. Specifically, we observe performance improvements in F1-score on eight out of ten question types compared to the previous state of the art. For logical reasoning questions, an improvement of 11 absolute points is reached.

Renzo Angles, Harsh Thakkar, Dominik Tomaszuk

RDF triplestores and property graph databases are two approaches for data management which are based on modeling, storing, and querying graph-like data. In spite of such common principles, they present special features that complicate the task of database interoperability. While there exist some methods to transform RDF graphs into property graphs, and vice versa, they lack compatibility and a solid formal foundation. This paper presents three direct mappings (schema-dependent and schema-independent) for transforming an RDF database into a property graph database, including data and schema. We show that two of the proposed mappings satisfy the properties of semantics preservation and information preservation. The existence of both mappings allows us to conclude that the property graph data model subsumes the information capacity of the RDF data model.

Mohamed Nadjib Mami, Damien Graux, Harsh Thakkar et al.

Whereas the availability of data has seen a manyfold increase in past years, its value can be only shown if the data variety is effectively tackled ---one of the prominent Big Data challenges. The lack of data interoperability limits the potential of its collective use for novel applications. Achieving interoperability through the full transformation and integration of diverse data structures remains an ideal that is hard, if not impossible, to achieve. Instead, methods that can simultaneously interpret different types of data available in different data structures and formats have been explored. On the other hand, many query languages have been designed to enable users to interact with the data, from relational, to object-oriented, to hierarchical, to the multitude emerging NoSQL languages. Therefore, the interoperability issue could be solved not by enforcing physical data transformation, but by looking at techniques that are able to query heterogeneous sources using one uniform language. Both industry and research communities have been keen to develop such techniques, which require the translation of a chosen 'universal' query language to the various data model specific query languages that make the underlying data accessible. In this article, we survey more than forty query translation methods and tools for popular query languages, and classify them according to eight criteria. In particular, we study which query language is a most suitable candidate for that 'universal' query language. Further, the results enable us to discover the weakly addressed and unexplored translation paths, to discover gaps and to learn lessons that can benefit future research in the area.

Saeedeh Shekarpour, Denis Lukovnikov, Ashwini Jaya Kumar et al.

Question Answering (QA) systems are becoming the inspiring model for the future of search engines. While recently, underlying datasets for QA systems have been promoted from unstructured datasets to structured datasets with highly semantic-enriched metadata, but still question answering systems involve serious challenges which cause to be far beyond desired expectations. In this paper, we raise the challenges for building a Question Answering (QA) system especially with the focus of employing structured data (i.e. knowledge graph). This paper provide an exhaustive insight of the known challenges, so far. Thus, it helps researchers to easily spot open rooms for the future research agenda.

Harsh Thakkar, Dhiren Patel

Microbloging is an extremely prevalent broadcast medium amidst the Internet fraternity these days. People share their opinions and sentiments about variety of subjects like products, news, institutions, etc., every day on microbloging websites. Sentiment analysis plays a key role in prediction systems, opinion mining systems, etc. Twitter, one of the microbloging platforms allows a limit of 140 characters to its users. This restriction stimulates users to be very concise about their opinion and twitter an ocean of sentiments to analyze. Twitter also provides developer friendly streaming API for data retrieval purpose allowing the analyst to search real time tweets from various users. In this paper, we discuss the state-of-art of the works which are focused on Twitter, the online social network platform, for sentiment analysis. We survey various lexical, machine learning and hybrid approaches for sentiment analysis on Twitter.

Harsh Thakkar, Ganesh Iyer, Prasenjit Majumder

In this paper, we survey various user-centered or context-based biomedical health information retrieval systems. We present and discuss the performance of systems submitted in CLEF eHealth 2014 Task 3 for this purpose. We classify and focus on comparing the two most prevalent retrieval models in biomedical information retrieval namely: Language Model (LM) and Vector Space Model (VSM). We also report on the effectiveness of using external medical resources and ontologies like MeSH, Metamap, UMLS, etc. We observed that the L.M. based retrieval systems outperform VSM based systems on various fronts. From the results we conclude that the state-of-art system scores for MAP was 0.4146, P@10 was 0.7560 and NDCG@10 was 0.7445, respectively. All of these score were reported by systems built on language modelling approaches.