Search

Automatic question generation is a critical task that involves evaluating question quality by considering factors such as engagement, pedagogical value, and the ability to stimulate critical thinking. These aspects require human-like understanding and judgment, which automated systems currently lack. However, human evaluations are costly and impractical for large-scale samples of generated questions. Therefore, we propose a novel system, MIRROR (Multi-LLM Iterative Review and Response for Optimized Rating), which leverages large language models (LLMs) to automate the evaluation process for questions generated by automated question generation systems. We experimented with several state-of-the-art LLMs, such as GPT-4, Gemini, and Llama2-70b. We observed that the scores of human evaluation metrics, namely relevance, appropriateness, novelty, complexity, and grammaticality, improved when using the feedback-based approach called MIRROR, tending to be closer to the human baseline scores. Furthermore, we observed that Pearson's correlation coefficient between GPT-4 and human experts improved when using our proposed feedback-based approach, MIRROR, compared to direct prompting for evaluation. Error analysis shows that our proposed approach, MIRROR, significantly helps to improve relevance and appropriateness., Comment: Accepted at FM-Eduassess @ NEURIPS 2024 (ORAL Paper)

Neural Machine Translation (NMT) remains a formidable challenge, especially when dealing with low-resource languages. Pre-trained sequence-to-sequence (seq2seq) multi-lingual models, such as mBART-50, have demonstrated impressive performance in various low-resource NMT tasks. However, their pre-training has been confined to 50 languages, leaving out support for numerous low-resource languages, particularly those spoken in the Indian subcontinent. Expanding mBART-50's language support requires complex pre-training, risking performance decline due to catastrophic forgetting. Considering these expanding challenges, this paper explores a framework that leverages the benefits of a pre-trained language model along with knowledge distillation in a seq2seq architecture to facilitate translation for low-resource languages, including those not covered by mBART-50. The proposed framework employs a multilingual encoder-based seq2seq model as the foundational architecture and subsequently uses complementary knowledge distillation techniques to mitigate the impact of imbalanced training. Our framework is evaluated on three low-resource Indic languages in four Indic-to-Indic directions, yielding significant BLEU-4 and chrF improvements over baselines. Further, we conduct human evaluation to confirm effectiveness of our approach. Our code is publicly available at https://github.com/raypretam/Two-step-low-res-NMT., Comment: Published at Seventh LoResMT Workshop at ACL 2024

We evaluate the effectiveness of GPT-4 Turbo in generating educational questions from NCERT textbooks in zero-shot mode. Our study highlights GPT-4 Turbo's ability to generate questions that require higher-order thinking skills, especially at the "understanding" level according to Bloom's Revised Taxonomy. While we find a notable consistency between questions generated by GPT-4 Turbo and those assessed by humans in terms of complexity, there are occasional differences. Our evaluation also uncovers variations in how humans and machines evaluate question quality, with a trend inversely related to Bloom's Revised Taxonomy levels. These findings suggest that while GPT-4 Turbo is a promising tool for educational question generation, its efficacy varies across different cognitive levels, indicating a need for further refinement to fully meet educational standards., Comment: Accepted at Learnersourcing: Student-Generated Content @ Scale 2024

Grammatical error correction (GEC) tools, powered by advanced generative artificial intelligence (AI), competently correct linguistic inaccuracies in user input. However, they often fall short in providing essential natural language explanations, which are crucial for learning languages and gaining a deeper understanding of the grammatical rules. There is limited exploration of these tools in low-resource languages such as Bengali. In such languages, grammatical error explanation (GEE) systems should not only correct sentences but also provide explanations for errors. This comprehensive approach can help language learners in their quest for proficiency. Our work introduces a real-world, multi-domain dataset sourced from Bengali speakers of varying proficiency levels and linguistic complexities. This dataset serves as an evaluation benchmark for GEE systems, allowing them to use context information to generate meaningful explanations and high-quality corrections. Various generative pre-trained large language models (LLMs), including GPT-4 Turbo, GPT-3.5 Turbo, Text-davinci-003, Text-babbage-001, Text-curie-001, Text-ada-001, Llama-2-7b, Llama-2-13b, and Llama-2-70b, are assessed against human experts for performance comparison. Our research underscores the limitations in the automatic deployment of current state-of-the-art generative pre-trained LLMs for Bengali GEE. Advocating for human intervention, our findings propose incorporating manual checks to address grammatical errors and improve feedback quality. This approach presents a more suitable strategy to refine the GEC tools in Bengali, emphasizing the educational aspect of language learning., Comment: Accepted at Educational Data Mining 2024

In the era of generative artificial intelligence (AI), the fusion of large language models (LLMs) offers unprecedented opportunities for innovation in the field of modern education. We embark on an exploration of prompted LLMs within the context of educational and assessment applications to uncover their potential. Through a series of carefully crafted research questions, we investigate the effectiveness of prompt-based techniques in generating open-ended questions from school-level textbooks, assess their efficiency in generating open-ended questions from undergraduate-level technical textbooks, and explore the feasibility of employing a chain-of-thought inspired multi-stage prompting approach for language-agnostic multiple-choice question (MCQ) generation. Additionally, we evaluate the ability of prompted LLMs for language learning, exemplified through a case study in the low-resource Indian language Bengali, to explain Bengali grammatical errors. We also evaluate the potential of prompted LLMs to assess human resource (HR) spoken interview transcripts. By juxtaposing the capabilities of LLMs with those of human experts across various educational tasks and domains, our aim is to shed light on the potential and limitations of LLMs in reshaping educational practices., Comment: Accepted at EDM 2024

Navigating the complex landscape of news articles involves understanding the various actors or entities involved, referred to as news stakeholders. These stakeholders, ranging from policymakers to opposition figures, citizens, and more, play pivotal roles in shaping news narratives. Recognizing their stakeholder types, reflecting their roles, political alignments, social standing, and more, is paramount for a nuanced comprehension of news content. Despite existing works focusing on salient entity extraction, coverage variations, and political affiliations through social media data, the automated detection of stakeholder roles within news content remains an underexplored domain. In this paper, we bridge this gap by introducing an effective approach to classify stakeholder types in news articles. Our method involves transforming the stakeholder classification problem into a natural language inference task, utilizing contextual information from news articles and external knowledge to enhance the accuracy of stakeholder type detection. Moreover, our proposed model showcases efficacy in zero-shot settings, further extending its applicability to diverse news contexts., Comment: Accepted in SIGIR 2024

Sentiment analysis plays a pivotal role in understanding public opinion, particularly in the political domain where the portrayal of entities in news articles influences public perception. In this paper, we investigate the effectiveness of Large Language Models (LLMs) in predicting entity-specific sentiment from political news articles. Leveraging zero-shot and few-shot strategies, we explore the capability of LLMs to discern sentiment towards political entities in news content. Employing a chain-of-thought (COT) approach augmented with rationale in few-shot in-context learning, we assess whether this method enhances sentiment prediction accuracy. Our evaluation on sentiment-labeled datasets demonstrates that LLMs, outperform fine-tuned BERT models in capturing entity-specific sentiment. We find that learning in-context significantly improves model performance, while the self-consistency mechanism enhances consistency in sentiment prediction. Despite the promising results, we observe inconsistencies in the effectiveness of the COT prompting method. Overall, our findings underscore the potential of LLMs in entity-centric sentiment analysis within the political news domain and highlight the importance of suitable prompting strategies and model architectures., Comment: Accepted in PoliticalNLP workshop co-located with LREC-COLING 2024

In today's media landscape, where news outlets play a pivotal role in shaping public opinion, it is imperative to address the issue of sentiment manipulation within news text. News writers often inject their own biases and emotional language, which can distort the objectivity of reporting. This paper introduces a novel approach to tackle this problem by reducing the polarity of latent sentiments in news content. Drawing inspiration from adversarial attack-based sentence perturbation techniques and a prompt based method using ChatGPT, we employ transformation constraints to modify sentences while preserving their core semantics. Using three perturbation methods: replacement, insertion, and deletion coupled with a context-aware masked language model, we aim to maximize the desired sentiment score for targeted news aspects through a beam search algorithm. Our experiments and human evaluations demonstrate the effectiveness of these two models in achieving reduced sentiment polarity with minimal modifications while maintaining textual similarity, fluency, and grammatical correctness. Comparative analysis confirms the competitive performance of the adversarial attack based perturbation methods and prompt-based methods, offering a promising solution to foster more objective news reporting and combat emotional language bias in the media., Comment: Accepted in ICON 2023

Designing high-quality educational questions is a challenging and time-consuming task. In this work, we propose a novel approach that utilizes prompt-based techniques to generate descriptive and reasoning-based questions. However, current question-answering (QA) datasets are inadequate for conducting our experiments on prompt-based question generation (QG) in an educational setting. Therefore, we curate a new QG dataset called EduProbe for school-level subjects, by leveraging the rich content of NCERT textbooks. We carefully annotate this dataset as quadruples of 1) Context: a segment upon which the question is formed; 2) Long Prompt: a long textual cue for the question (i.e., a longer sequence of words or phrases, covering the main theme of the context); 3) Short Prompt: a short textual cue for the question (i.e., a condensed representation of the key information or focus of the context); 4) Question: a deep question that aligns with the context and is coherent with the prompts. We investigate several prompt-based QG methods by fine-tuning pre-trained transformer-based large language models (LLMs), namely PEGASUS, T5, MBART, and BART. Moreover, we explore the performance of two general-purpose pre-trained LLMs such as Text-Davinci-003 and GPT-3.5-Turbo without any further training. By performing automatic evaluation, we show that T5 (with long prompt) outperforms all other models, but still falls short of the human baseline. Under human evaluation criteria, TextDavinci-003 usually shows better results than other models under various prompt settings. Even in the case of human evaluation criteria, QG models mostly fall short of the human baseline. Our code and dataset are available at: https://github.com/my625/PromptQG

This paper presents a novel probabilistic data-driven approach to trip-level energy consumption estimation of battery electric vehicles (BEVs). As there are very few electric vehicle (EV) charging stations, EV trip energy consumption estimation can make EV routing and charging planning easier for drivers. In this research article, we propose a new driver behaviour-centric EV energy consumption estimation model using probabilistic neural networks with model uncertainty. By incorporating model uncertainty into neural networks, we have created an ensemble of neural networks using Monte Carlo approximation. Our method comprehensively considers various vehicle dynamics, driver behaviour and environmental factors to estimate EV energy consumption for a given trip. We propose relative positive acceleration (RPA), average acceleration and average deceleration as driver behaviour factors in EV energy consumption estimation and this paper shows that the use of these driver behaviour features improves the accuracy of the EV energy consumption model significantly. Instead of predicting a single-point estimate for EV trip energy consumption, this proposed method predicts a probability distribution for the EV trip energy consumption. The experimental results of our approach show that our proposed probabilistic neural network with weight uncertainty achieves a mean absolute percentage error of 9.3% and outperforms other existing EV energy consumption models in terms of accuracy., Comment: This paper is under review at the International Journal of Green Energy

The coverage of different stakeholders mentioned in the news articles significantly impacts the slant or polarity detection of the concerned news publishers. For instance, the pro-government media outlets would give more coverage to the government stakeholders to increase their accessibility to the news audiences. In contrast, the anti-government news agencies would focus more on the views of the opponent stakeholders to inform the readers about the shortcomings of government policies. In this paper, we address the problem of stakeholder extraction from news articles and thereby determine the inherent bias present in news reporting. Identifying potential stakeholders in multi-topic news scenarios is challenging because each news topic has different stakeholders. The research presented in this paper utilizes both contextual information and external knowledge to identify the topic-specific stakeholders from news articles. We also apply a sequential incremental clustering algorithm to group the entities with similar stakeholder types. We carried out all our experiments on news articles on four Indian government policies published by numerous national and international news agencies. We also further generalize our system, and the experimental results show that the proposed model can be extended to other news topics., Comment: Accepted in AAAI-2023 Workshop, AI for Credible Elections

Most of the existing information extraction frameworks (Wadden et al., 2019; Veysehet al., 2020) focus on sentence-level tasks and are hardly able to capture the consolidated information from a given document. In our endeavour to generate precise document-level information frames from lengthy textual records, we introduce the task of Information Aggregation or Argument Aggregation. More specifically, our aim is to filter irrelevant and redundant argument mentions that were extracted at a sentence level and render a document level information frame. Majority of the existing works have been observed to resolve related tasks of document-level event argument extraction (Yang et al., 2018a; Zheng et al., 2019a) and salient entity identification (Jain et al.,2020) using supervised techniques. To remove dependency from large amounts of labelled data, we explore the task of information aggregation using weakly-supervised techniques. In particular, we present an extractive algorithm with multiple sieves which adopts active learning strategies to work efficiently in low-resource settings. For this task, we have annotated our own test dataset comprising of 131 document information frames and have released the code and dataset to further research prospects in this new domain. To the best of our knowledge, we are the first to establish baseline results for this task in English. Our data and code are publicly available at https://github.com/DebanjanaKar/ArgFuse., Comment: 11 pages, 8 figures, Accepted in Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE) @ACL-IJCNLP 2021

Event Argument extraction refers to the task of extracting structured information from unstructured text for a particular event of interest. The existing works exhibit poor capabilities to extract causal event arguments like Reason and After Effects. Furthermore, most of the existing works model this task at a sentence level, restricting the context to a local scope. While it may be effective for short spans of text, for longer bodies of text such as news articles, it has often been observed that the arguments for an event do not necessarily occur in the same sentence as that containing an event trigger. To tackle the issue of argument scattering across sentences, the use of global context becomes imperative in this task. In our work, we propose an external knowledge aided approach to infuse document-level event information to aid the extraction of complex event arguments. We develop a causal network for our event-annotated dataset by extracting relevant event causal structures from ConceptNet and phrases from Wikipedia. We use the extracted event causal features in a bi-directional transformer encoder to effectively capture long-range inter-sentence dependencies. We report the effectiveness of our proposed approach through both qualitative and quantitative analysis. In this task, we establish our findings on an event annotated dataset in 5 Indian languages. This dataset adds further complexity to the task by labelling arguments of entity type (like Time, Place) as well as more complex argument types (like Reason, After-Effect). Our approach achieves state-of-the-art performance across all the five languages. Since our work does not rely on any language-specific features, it can be easily extended to other languages., Comment: 10 pages, 6 figures, Accepted in 17th International Conference on Natural Language Processing (ICON 2020)

Entity linking (or Normalization) is an essential task in text mining that maps the entity mentions in the medical text to standard entities in a given Knowledge Base (KB). This task is of great importance in the medical domain. It can also be used for merging different medical and clinical ontologies. In this paper, we center around the problem of disease linking or normalization. This task is executed in two phases: candidate generation and candidate scoring. In this paper, we present an approach to rank the candidate Knowledge Base entries based on their similarity with disease mention. We make use of the Triplet Network for candidate ranking. While the existing methods have used carefully generated sieves and external resources for candidate generation, we introduce a robust and portable candidate generation scheme that does not make use of the hand-crafted rules. Experimental results on the standard benchmark NCBI disease dataset demonstrate that our system outperforms the prior methods by a significant margin., Comment: ClinicalNLP@NAACL 2019

We present a shallow parser guided cross-lingual model transfer approach in order to address the syntactic differences between source and target languages more effectively. In this work, we assume the chunks or phrases in a sentence as transfer units in order to address the syntactic differences between the source and target languages arising due to the differences in ordering of words in the phrases and the ordering of phrases in a sentence separately.

Cross-Language Information Retrieval (CLIR) has become an important problem to solve in the recent years due to the growth of content in multiple languages in the Web. One of the standard methods is to use query translation from source to target language. In this paper, we propose an approach based on word embeddings, a method that captures contextual clues for a particular word in the source language and gives those words as translations that occur in a similar context in the target language. Once we obtain the word embeddings of the source and target language pairs, we learn a projection from source to target word embeddings, making use of a dictionary with word translation pairs.We then propose various methods of query translation and aggregation. The advantage of this approach is that it does not require the corpora to be aligned (which is difficult to obtain for resource-scarce languages), a dictionary with word translation pairs is enough to train the word vectors for translation. We experiment with Forum for Information Retrieval and Evaluation (FIRE) 2008 and 2012 datasets for Hindi to English CLIR. The proposed word embedding based approach outperforms the basic dictionary based approach by 70% and when the word embeddings are combined with the dictionary, the hybrid approach beats the baseline dictionary based method by 77%. It outperforms the English monolingual baseline by 15%, when combined with the translations obtained from Google Translate and Dictionary., Comment: 17th International Conference on Intelligent Text Processing and Computational Linguistics