Faisal Mahbub Chowdhury

Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Nandana Mihindukulasooriya et al.

We propose KnowGL, a tool that allows converting text into structured relational data represented as a set of ABox assertions compliant with the TBox of a given Knowledge Graph (KG), such as Wikidata. We address this problem as a sequence generation task by leveraging pre-trained sequence-to-sequence language models, e.g. BART. Given a sentence, we fine-tune such models to detect pairs of entity mentions and jointly generate a set of facts consisting of the full set of semantic annotations for a KG, such as entity labels, entity types, and their relationships. To showcase the capabilities of our tool, we build a web application consisting of a set of UI widgets that help users to navigate through the semantic data extracted from a given input text. We make the KnowGL model available at https://huggingface.co/ibm/knowgl-large.

Nandana Mihindukulasooriya, Niharika S. D'Souza, Faisal Chowdhury et al. · ibm-research

A KG represents a network of entities and illustrates relationships between them. KGs are used for various applications, including semantic search and discovery, reasoning, decision-making, natural language processing, machine learning, and recommendation systems. Triple (subject-relation-object) extraction from text is the fundamental building block of KG construction and has been widely studied, for example, in early benchmarks such as ACE 2002 to more recent ones, such as WebNLG 2020, REBEL and SynthIE. While the use of LLMs is explored for KG construction, handcrafting reasonable task-specific prompts for LLMs is a labour-intensive exercise and can be brittle due to subtle changes in the LLM models employed. Recent work in NLP tasks (e.g. autonomy generation) uses automatic prompt optimization/engineering to address this challenge by generating optimal or near-optimal task-specific prompts given input-output examples. This empirical study explores the application of automatic prompt optimization for the triple extraction task using experimental benchmarking. We evaluate different settings by changing (a) the prompting strategy, (b) the LLM being used for prompt optimization and task execution, (c) the number of canonical relations in the schema (schema complexity), (d) the length and diversity of input text, (e) the metric used to drive the prompt optimization, and (f) the dataset being used for training and testing. We evaluate three different automatic prompt optimizers, namely, DSPy, APE, and TextGrad and use two different triple extraction datasets, SynthIE and REBEL. Through rigorous empirical evaluation, our main contribution highlights that automatic prompt optimization techniques can generate reasonable prompts similar to humans for triple extraction. In turn, these optimized prompts achieve improved results, particularly with increasing schema complexity and text size.

Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury et al.

Automatically inducing high quality knowledge graphs from a given collection of documents still remains a challenging problem in AI. One way to make headway for this problem is through advancements in a related task known as slot filling. In this task, given an entity query in form of [Entity, Slot, ?], a system is asked to fill the slot by generating or extracting the missing value exploiting evidence extracted from relevant passage(s) in the given document collection. The recent works in the field try to solve this task in an end-to-end fashion using retrieval-based language models. In this paper, we present a novel approach to zero-shot slot filling that extends dense passage retrieval with hard negatives and robust training procedures for retrieval augmented generation models. Our model reports large improvements on both T-REx and zsRE slot filling datasets, improving both passage retrieval and slot value generation, and ranking at the top-1 position in the KILT leaderboard. Moreover, we demonstrate the robustness of our system showing its domain adaptation capability on a new variant of the TACRED dataset for slot filling, through a combination of zero/few-shot learning. We release the source code and pre-trained models.

Md Faisal Mahbub Chowdhury, Robert Farrell

This paper describes a new approach, called Terminological Bucket Indexing (TBI), for efficient indexing and retrieval of both nested and super terms using a single method. We propose a hybrid data structure for facilitating faster indexing building. An evaluation of our approach with respect to widely used existing approaches on several publicly available dataset is provided. Compared to Trie based approaches, TBI provides comparable performance on nested term retrieval and far superior performance on super term retrieval. Compared to traditional hash table, TBI needs 80\% less time for indexing.

Md Faisal Mahbub Chowdhury, Vijil Chenthamarakshan, Rishav Chakravarti et al.

State of the art approaches for (embedding based) unsupervised semantic search exploits either compositional similarity (of a query and a passage) or pair-wise word (or term) similarity (from the query and the passage). By design, word based approaches do not incorporate similarity in the larger context (query/passage), while compositional similarity based approaches are usually unable to take advantage of the most important cues in the context. In this paper we propose a new compositional similarity based approach, called variable centroid vector (VCVB), that tries to address both of these limitations. We also presents results using a different type of compositional similarity based approach by exploiting universal sentence embedding. We provide empirical evaluation on two different benchmarks.

Michael R. Glass, Md Faisal Mahbub Chowdhury, Alfio M. Gliozzo

This paper addresses automatic extraction of abbreviations (encompassing acronyms and initialisms) and corresponding long-form expansions from plain unstructured text. We create and are going to release a multilingual resource for abbreviations and their corresponding expansions, built automatically by exploiting Wikipedia redirect and disambiguation pages, that can be used as a benchmark for evaluation. We address a shortcoming of previous work where only the redirect pages were used, and so every abbreviation had only a single expansion, even though multiple different expansions are possible for many of the abbreviations. We also develop a principled machine learning based approach to scoring expansion candidates using different techniques such as indicators of near synonymy, topical relatedness, and surface similarity. We show improved performance over seven languages, including two with a non-Latin alphabet, relative to strong baselines.