Enamul Hoque


pdf bib
BenLLM-Eval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP
Mohsinul Kabir | Mohammed Saidul Islam | Md Tahmid Rahman Laskar | Mir Tafseer Nayeem | M Saiful Bari | Enamul Hoque
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Large Language Models (LLMs) have emerged as one of the most important breakthroughs in natural language processing (NLP) for their impressive skills in language generation and other language-specific tasks. Though LLMs have been evaluated in various tasks, mostly in English, they have not yet undergone thorough evaluation in under-resourced languages such as Bengali (Bangla). To this end, this paper introduces BenLLM-Eval, which consists of a comprehensive evaluation of LLMs to benchmark their performance in the low-resourced Bangla language. In this regard, we select various important and diverse Bangla NLP tasks, such as text summarization, question answering, paraphrasing, natural language inference, text classification, and sentiment analysis for zero-shot evaluation of popular LLMs, namely, ChatGPT, LLaMA-2, and Claude-2. Our experimental results demonstrate that while in some Bangla NLP tasks, zero-shot LLMs could achieve performance on par, or even better than current SOTA fine-tuned models; in most tasks, their performance is quite poor (with the performance of open-source LLMs like LLaMA-2 being significantly bad) in comparison to the current SOTA results. Therefore, it calls for further efforts to develop a better understanding of LLMs in low-resource languages like Bangla.


pdf bib
Can Large Language Models Fix Data Annotation Errors? An Empirical Study Using Debatepedia for Query-Focused Text Summarization
Md Tahmid Rahman Laskar | Mizanur Rahman | Israt Jahan | Enamul Hoque | Jimmy Huang
Findings of the Association for Computational Linguistics: EMNLP 2023

Debatepedia is a publicly available dataset consisting of arguments and counter-arguments on controversial topics that has been widely used for the single-document query-focused abstractive summarization task in recent years. However, it has been recently found that this dataset is limited by noise and even most queries in this dataset do not have any relevance to the respective document. In this paper, we study whether large language models (LLMs) can be utilized to clean the Debatepedia dataset to make it suitable for query-focused abstractive summarization. More specifically, we harness the language generation capabilities of two LLMs, namely, ChatGPT and PaLM to regenerate its queries. Based on our experiments, we find that solely depending on large language models for query correction may not be very useful for data cleaning. However, we observe that leveraging a rule-based approach for data sampling followed by query regeneration using LLMs (especially ChatGPT) for the sampled instances may ensure a higher quality version of this dataset suitable for the development of more generalized query-focused text summarization models.

pdf bib
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
Ahmed Masry | Parsa Kavehzadeh | Xuan Long Do | Enamul Hoque | Shafiq Joty
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Charts are widely used for data analysis, providing visual representations and insights into complex data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced recently such as chart question answering and chart summarization. However, existing methods for these tasks often rely on pretraining on language or vision-language tasks, neglecting the explicit modeling of chart structures (e.g., how chart elements are related to each other). To address this, we first build a large corpus of charts covering diverse topics and visual styles. We then present UniChart, a pretrained model for chart comprehension and reasoning. UniChart encodes the relevant text, data, and visual elements of charts and then uses a chart-grounded text decoder for text generation. We propose several chart-specific pretraining tasks that include: (i) low-level tasks to extract the visual elements (e.g., bars, lines) and data from charts, and (ii) high-level tasks to acquire chart understanding and reasoning skills. Our experiments demonstrate that pretraining UniChart on a large corpus with chart-specific objectives, followed by fine-tuning, yields state-of-the-art performance on four downstream tasks. Moreover, our model exhibits superior generalizability to unseen chart corpus, surpassing previous approaches that lack chart-specific objectives and utilize limited chart resources.

pdf bib
NLP+Vis: NLP Meets Visualization
Shafiq Joty | Enamul Hoque | Jesse Vig
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts

Natural language and visualization (Vis) are two powerful modalities of human communication. The goal of this tutorial is to push forward the agenda of tightly integrating these two modalities. To this end, the tutorial will introduce NLP+Vis with a focus on two main threads of work: (i) NLP for Vis: How to develop and adapt state-of-the-art NLP models for solving various visualization tasks? and (ii) Vis for NLP: How to leverage visualization techniques to interpret and explain complex NLP models effectively? The tutorial will first motivate why NLP+Vis is an important area of research and provide an overview of research topics on combining NLP and Vis techniques. Then an overview of state-of-the-art deep learning models for NLP will be covered. Next, we will provide an overview of applying visualization techniques to help make NLP models more interpretable and explainable. In the final part, we will focus on various application tasks at the intersection of NLP and Vis. We will conclude with an interactive discussion of future challenges for NLP+Vis applications. The audience will include researchers interested in applying NLP for visualizations as well as others who focus more generally at the intersection of machine learning and visualization.


pdf bib
Domain Adaptation with Pre-trained Transformers for Query-Focused Abstractive Text Summarization
Md Tahmid Rahman Laskar | Enamul Hoque | Jimmy Xiangji Huang
Computational Linguistics, Volume 48, Issue 2 - June 2022

The Query-Focused Text Summarization (QFTS) task aims at building systems that generate the summary of the text document(s) based on the given query. A key challenge in addressing this task is the lack of large labeled data for training the summarization model. In this article, we address this challenge by exploring a series of domain adaptation techniques. Given the recent success of pre-trained transformer models in a wide range of natural language processing tasks, we utilize such models to generate abstractive summaries for the QFTS task for both single-document and multi-document scenarios. For domain adaptation, we apply a variety of techniques using pre-trained transformer-based summarization models including transfer learning, weakly supervised learning, and distant supervision. Extensive experiments on six datasets show that our proposed approach is very effective in generating abstractive summaries for the QFTS task while setting a new state-of-the-art result in several datasets across a set of automatic and human evaluation metrics.

pdf bib
OpenCQA: Open-ended Question Answering with Charts
Shankar Kantharaj | Xuan Long Do | Rixie Tiffany Leong | Jia Qing Tan | Enamul Hoque | Shafiq Joty
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Charts are very popular to analyze data and convey important insights. People often analyze visualizations to answer open-ended questions that require explanatory answers. Answering such questions are often difficult and time-consuming as it requires a lot of cognitive and perceptual efforts. To address this challenge, we introduce a new task called OpenCQA, where the goal is to answer an open-ended question about a chart with descriptive texts. We present the annotation process and an in-depth analysis of our dataset. We implement and evaluate a set of baselines under three practical settings. In the first setting, a chart and the accompanying article is provided as input to the model. The second setting provides only the relevant paragraph(s) to the chart instead of the entire article, whereas the third setting requires the model to generate an answer solely based on the chart. Our analysis of the results show that the top performing models generally produce fluent and coherent text while they struggle to perform complex logical and arithmetic reasoning.

pdf bib
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
Ahmed Masry | Xuan Long Do | Jia Qing Tan | Shafiq Joty | Enamul Hoque
Findings of the Association for Computational Linguistics: ACL 2022

Charts are very popular for analyzing data. When exploring charts, people often ask a variety of complex reasoning questions that involve several logical and arithmetic operations. They also commonly refer to visual features of a chart in their questions. However, most existing datasets do not focus on such complex reasoning questions as their questions are template-based and answers come from a fixed-vocabulary. In this work, we present a large-scale benchmark covering 9.6K human-written questions as well as 23.1K questions generated from human-written chart summaries. To address the unique challenges in our benchmark involving visual and logical reasoning over charts, we present two transformer-based models that combine visual features and the data table of the chart in a unified way to answer questions. While our models achieve the state-of-the-art results on the previous datasets as well as on our benchmark, the evaluation also reveals several challenges in answering complex reasoning questions.

pdf bib
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
Shankar Kantharaj | Rixie Tiffany Leong | Xiang Lin | Ahmed Masry | Megh Thakkar | Enamul Hoque | Shafiq Joty
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights that would otherwise require a lot of cognitive and perceptual efforts. We present Chart-to-text, a large-scale benchmark with two datasets and a total of 44,096 charts covering a wide range of topics and chart types. We explain the dataset construction process and analyze the datasets. We also introduce a number of state-of-the-art neural models as baselines that utilize image captioning and data-to-text generation techniques to tackle two problem variations: one assumes the underlying data table of the chart is available while the other needs to extract data from chart images. Our analysis with automatic and human evaluation shows that while our best models usually generate fluent summaries and yield reasonable BLEU scores, they also suffer from hallucinations and factual errors as well as difficulties in correctly explaining complex patterns and trends in charts.


pdf bib
Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task
Md Tahmid Rahman Laskar | Jimmy Xiangji Huang | Enamul Hoque
Proceedings of the Twelfth Language Resources and Evaluation Conference

Word embeddings that consider context have attracted great attention for various natural language processing tasks in recent years. In this paper, we utilize contextualized word embeddings with the transformer encoder for sentence similarity modeling in the answer selection task. We present two different approaches (feature-based and fine-tuning-based) for answer selection. In the feature-based approach, we utilize two types of contextualized embeddings, namely the Embeddings from Language Models (ELMo) and the Bidirectional Encoder Representations from Transformers (BERT) and integrate each of them with the transformer encoder. We find that integrating these contextual embeddings with the transformer encoder is effective to improve the performance of sentence similarity modeling. In the second approach, we fine-tune two pre-trained transformer encoder models for the answer selection task. Based on our experiments on six datasets, we find that the fine-tuning approach outperforms the feature-based approach on all of them. Among our fine-tuning-based models, the Robustly Optimized BERT Pretraining Approach (RoBERTa) model results in new state-of-the-art performance across five datasets.

pdf bib
Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model
Jason Obeid | Enamul Hoque
Proceedings of the 13th International Conference on Natural Language Generation

Information visualizations such as bar charts and line charts are very popular for exploring data and communicating insights. Interpreting and making sense of such visualizations can be challenging for some people, such as those who are visually impaired or have low visualization literacy. In this work, we introduce a new dataset and present a neural model for automatically generating natural language summaries for charts. The generated summaries provide an interpretation of the chart and convey the key insights found within that chart. Our neural model is developed by extending the state-of-the-art model for the data-to-text generation task, which utilizes a transformer-based encoder-decoder architecture. We found that our approach outperforms the base model on a content selection metric by a wide margin (55.42% vs. 8.49%) and generates more informative, concise, and coherent summaries.

pdf bib
WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization
Md Tahmid Rahman Laskar | Enamul Hoque | Jimmy Xiangji Huang
Proceedings of the 28th International Conference on Computational Linguistics

In the Query Focused Multi-Document Summarization (QF-MDS) task, a set of documents and a query are given where the goal is to generate a summary from these documents based on the given query. However, one major challenge for this task is the lack of availability of labeled training datasets. To overcome this issue, in this paper, we propose a novel weakly supervised learning approach via utilizing distant supervision. In particular, we use datasets similar to the target dataset as the training data where we leverage pre-trained sentence similarity models to generate the weak reference summary of each individual document in a document set from the multi-document gold reference summaries. Then, we iteratively train our summarization model on each single-document to alleviate the computational complexity issue that occurs while training neural summarization models in multiple documents (i.e., long sequences) at once. Experimental results on the Document Understanding Conferences (DUC) datasets show that our proposed approach sets a new state-of-the-art result in terms of various evaluation metrics.


pdf bib
Multimedia Summary Generation from Online Conversations: Current Approaches and Future Directions
Enamul Hoque | Giuseppe Carenini
Proceedings of the Workshop on New Frontiers in Summarization

With the proliferation of Web-based social media, asynchronous conversations have become very common for supporting online communication and collaboration. Yet the increasing volume and complexity of conversational data often make it very difficult to get insights about the discussions. We consider combining textual summary with visual representation of conversational data as a promising way of supporting the user in exploring conversations. In this paper, we report our current work on developing visual interfaces that present multimedia summary combining text and visualization for online conversations and how our solutions have been tailored for a variety of domain problems. We then discuss the key challenges and opportunities for future work in this research space.


pdf bib
An Interactive System for Exploring Community Question Answering Forums
Enamul Hoque | Shafiq Joty | Lluís Màrquez | Alberto Barrón-Cedeño | Giovanni Da San Martino | Alessandro Moschitti | Preslav Nakov | Salvatore Romeo | Giuseppe Carenini
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

We present an interactive system to provide effective and efficient search capabilities in Community Question Answering (cQA) forums. The system integrates state-of-the-art technology for answer search with a Web-based user interface specifically tailored to support the cQA forum readers. The answer search module automatically finds relevant answers for a new question by exploring related questions and the comments within their threads. The graphical user interface presents the search results and supports the exploration of related information. The system is running live at http://www.qatarliving.com/betasearch/.

pdf bib
Speech Act Modeling of Written Asynchronous Conversations with Task-Specific Embeddings and Conditional Structured Models
Shafiq Joty | Enamul Hoque
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
Interactive Exploration of Asynchronous Conversations: Applying a User-centered Approach to Design a Visual Text Analytic System
Enamul Hoque | Giuseppe Carenini | Shafiq Joty
Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces