Md. Faisal Mahbub Chowdhury

Also published as: Md Faisal Mahbub Chowdhury


2022

pdf
Re2G: Retrieve, Rerank, Generate
Michael Glass | Gaetano Rossiello | Md Faisal Mahbub Chowdhury | Ankita Naik | Pengshan Cai | Alfio Gliozzo
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger. However, for tasks that require a large amount of knowledge, non-parametric memory allows models to grow dramatically with a sub-linear increase in computational cost and GPU memory requirements. Recent models such as RAG and REALM have introduced retrieval into conditional generation. These models incorporate neural initial retrieval from a corpus of passages. We build on this line of research, proposing Re2G, which combines both neural initial retrieval and reranking into a BART-based sequence-to-sequence generation. Our reranking approach also permits merging retrieval results from sources with incomparable scores, enabling an ensemble of BM25 and neural initial retrieval. To train our system end-to-end, we introduce a novel variation of knowledge distillation to train the initial retrieval, reranker and generation using only ground truth on the target sequence output. We find large gains in four diverse tasks: zero-shot slot filling, question answering, fact checking and dialog, with relative gains of 9% to 34% over the previous state-of-the-art on the KILT leaderboard. We make our code available as open source.

pdf
KGI: An Integrated Framework for Knowledge Intensive Language Tasks
Md Faisal Mahbub Chowdhury | Michael Glass | Gaetano Rossiello | Alfio Gliozzo | Nandana Mihindukulasooriya
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

In this paper, we present a system to showcase the capabilities of the latest state-of-the-art retrieval augmented generation models trained on knowledge-intensive language tasks, such as slot filling, open domain question answering, dialogue, and fact-checking. Moreover, given a user query, we show how the output from these different models can be combined to cross-examine the outputs of each other. Particularly, we show how accuracy in dialogue can be improved using the question answering model. We are also releasing all models used in the demo as a contribution of this paper. A short video demonstrating the system is available at https://ibm.box.com/v/emnlp2022-demos.

2021

pdf
Robust Retrieval Augmented Generation for Zero-shot Slot Filling
Michael Glass | Gaetano Rossiello | Md Faisal Mahbub Chowdhury | Alfio Gliozzo
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

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.

pdf
Dynamic Facet Selection by Maximizing Graded Relevance
Michael Glass | Md Faisal Mahbub Chowdhury | Yu Deng | Ruchi Mahindru | Nicolas Rodolfo Fauceglia | Alfio Gliozzo | Nandana Mihindukulasooriya
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing

Dynamic faceted search (DFS), an interactive query refinement technique, is a form of Human–computer information retrieval (HCIR) approach. It allows users to narrow down search results through facets, where the facets-documents mapping is determined at runtime based on the context of user query instead of pre-indexing the facets statically. In this paper, we propose a new unsupervised approach for dynamic facet generation, namely optimistic facets, which attempts to generate the best possible subset of facets, hence maximizing expected Discounted Cumulative Gain (DCG), a measure of ranking quality that uses a graded relevance scale. We also release code to generate a new evaluation dataset. Through empirical results on two datasets, we show that the proposed DFS approach considerably improves the document ranking in the search results.

2020

pdf
Taxonomy Construction of Unseen Domains via Graph-based Cross-Domain Knowledge Transfer
Chao Shang | Sarthak Dash | Md. Faisal Mahbub Chowdhury | Nandana Mihindukulasooriya | Alfio Gliozzo
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Extracting lexico-semantic relations as graph-structured taxonomies, also known as taxonomy construction, has been beneficial in a variety of NLP applications. Recently Graph Neural Network (GNN) has shown to be powerful in successfully tackling many tasks. However, there has been no attempt to exploit GNN to create taxonomies. In this paper, we propose Graph2Taxo, a GNN-based cross-domain transfer framework for the taxonomy construction task. Our main contribution is to learn the latent features of taxonomy construction from existing domains to guide the structure learning of an unseen domain. We also propose a novel method of directed acyclic graph (DAG) generation for taxonomy construction. Specifically, our proposed Graph2Taxo uses a noisy graph constructed from automatically extracted noisy hyponym hypernym candidate pairs, and a set of taxonomies for some known domains for training. The learned model is then used to generate taxonomy for a new unknown domain given a set of terms for that domain. Experiments on benchmark datasets from science and environment domains show that our approach attains significant improvements correspondingly over the state of the art.

2019

pdf
Automatic Taxonomy Induction and Expansion
Nicolas Rodolfo Fauceglia | Alfio Gliozzo | Sarthak Dash | Md. Faisal Mahbub Chowdhury | Nandana Mihindukulasooriya
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations

The Knowledge Graph Induction Service (KGIS) is an end-to-end knowledge induction system. One of its main capabilities is to automatically induce taxonomies from input documents using a hybrid approach that takes advantage of linguistic patterns, semantic web and neural networks. KGIS allows the user to semi-automatically curate and expand the induced taxonomy through a component called Smart SpreadSheet by exploiting distributional semantics. In this paper, we describe these taxonomy induction and expansion features of KGIS. A screencast video demonstrating the system is available in https://ibm.box.com/v/emnlp-2019-demo .

2013

pdf
FBK-irst : A Multi-Phase Kernel Based Approach for Drug-Drug Interaction Detection and Classification that Exploits Linguistic Information
Md. Faisal Mahbub Chowdhury | Alberto Lavelli
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)

pdf
FBK: Sentiment Analysis in Twitter with Tweetsted
Md. Faisal Mahbub Chowdhury | Marco Guerini | Sara Tonelli | Alberto Lavelli
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)

pdf
Exploiting the Scope of Negations and Heterogeneous Features for Relation Extraction: A Case Study for Drug-Drug Interaction Extraction
Md. Faisal Mahbub Chowdhury | Alberto Lavelli
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2012

pdf
An Evaluation of the Effect of Automatic Preprocessing on Syntactic Parsing for Biomedical Relation Extraction
Md. Faisal Mahbub Chowdhury | Alberto Lavelli
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

Relation extraction (RE) is an important text mining task which is the basis for further complex and advanced tasks. In state-of-the-art RE approaches, syntactic information obtained through parsing plays a crucial role. In the context of biomedical RE previous studies report usage of various automatic preprocessing techniques applied before parsing the input text. However, these studies do not specify to what extent such techniques improve RE results and to what extent they are corpus specific as well as parser specific. In this paper, we aim at addressing these issues by using various preprocessing techniques, two syntactic tree kernel based RE approaches and two different parsers on 5 widely used benchmark biomedical corpora of the protein-protein interaction (PPI) extraction task. We also provide analyses of various corpus characteristics to verify whether there are correlations between these characteristics and the RE results obtained. These analyses of corpus characteristics can be exploited to compare the 5 PPI corpora.

pdf
FBK: Exploiting Phrasal and Contextual Clues for Negation Scope Detection
Md. Faisal Mahbub Chowdhury
*SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012)

pdf
Impact of Less Skewed Distributions on Efficiency and Effectiveness of Biomedical Relation Extraction
Md. Faisal Mahbub Chowdhury | Alberto Lavelli
Proceedings of COLING 2012: Posters

pdf
Combining Tree Structures, Flat Features and Patterns for Biomedical Relation Extraction
Md. Faisal Mahbub Chowdhury | Alberto Lavelli
Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

2011

pdf
Assessing the practical usability of an automatically annotated corpus
Md. Faisal Mahbub Chowdhury | Alberto Lavelli
Proceedings of the 5th Linguistic Annotation Workshop

2010

pdf
Disease Mention Recognition with Specific Features
Md. Faisal Mahbub Chowdhury | Alberto Lavelli
Proceedings of the 2010 Workshop on Biomedical Natural Language Processing

2009

pdf
Using Treebanking Discriminants as Parse Disambiguation Features
Md. Faisal Mahbub Chowdhury | Yi Zhang | Valia Kordoni
Proceedings of the 11th International Conference on Parsing Technologies (IWPT’09)