Sustainability reports are key for evaluating companies’ environmental, social and governance (ESG) performance. To analyze these reports, NLP approaches can efficiently extract ESG insights at scale. However, even the most advanced NLP methods lack robustness against ESG content that is greenwashed – i.e. sustainability claims that are misleading, exaggerated, and fabricated. Accordingly, existing NLP approaches often extract insights that reflect misleading or exaggerated sustainability claims rather than objective ESG performance. To tackle this issue, we introduce A3CG - Aspect-Action Analysis with Cross-Category Generalization, as a novel dataset to improve the robustness of ESG analysis amid the prevalence of greenwashing. By explicitly linking sustainability aspects with their associated actions, A3CG facilitates a more fine-grained and transparent evaluation of sustainability claims, ensuring that insights are grounded in verifiable actions rather than vague or misleading rhetoric. Additionally, A3CG emphasizes cross-category generalization. This ensures robust model performance in aspect-action analysis even when companies change their reports to selectively favor certain sustainability areas. Through experiments on A3CG, we analyze state-of-the-art supervised models and LLMs, uncovering their limitations and outlining key directions for future research.

Counterfactual reasoning typically involves considering alternatives to actual events. While often applied to understand past events, a distinct form—forward counterfactual reasoning—focuses on anticipating plausible future developments. This type of reasoning is invaluable in dynamic financial markets, where anticipating market developments can powerfully unveil potential risks and opportunities for stakeholders, guiding their decision-making. However, performing this at scale is challenging due to the cognitive demands involved, underscoring the need for automated solutions. Large Language Models (LLMs) offer promise, but remain unexplored for this application. To address this gap, we introduce a novel benchmark, Fin-Force—**FIN**ancial **FOR**ward **C**ounterfactual **E**valuation. By curating financial news headlines and providing structured evaluation, Fin-Force supports LLM based forward counterfactual generation. This paves the way for scalable and automated solutions for exploring and anticipating future market developments, thereby providing structured insights for decision-making. Through experiments on Fin-Force, we evaluate state-of-the-art LLMs and counterfactual generation methods, analyzing their limitations and proposing insights for future research.

This tutorial provides an in-depth exploration of Knowledge-enhanced Dialogue Systems (KEDS), diving into their foundational aspects, methodologies, advantages, and practical applications. Topics include the distinction between internal and external knowledge integration, diverse methodologies employed in grounding dialogues, and innovative approaches to leveraging knowledge graphs for enhanced conversation quality. Furthermore, the tutorial touches upon the rise of biomedical text mining, the advent of domain-specific language models, and the challenges and strategies specific to medical dialogue generation. The primary objective is to give attendees a comprehensive understanding of KEDS. By delineating the nuances of these systems, the tutorial aims to elucidate their significance, highlight advancements made using deep learning, and pinpoint the current challenges. Special emphasis is placed on showcasing how KEDS can be fine-tuned for domain-specific requirements, with a spotlight on the healthcare sector. The tutorial is crafted for both beginners and intermediate researchers in the dialogue systems domain, with a focus on those keen on advancing research in KEDS. It will also be valuable for practitioners in sectors like healthcare, seeking to integrate advanced dialogue systems.

Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-reference is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance. We enhance the commonsense knowledge with named entity-aware structures using co-references. Our proposed model utilizes a multi-hop attention layer to preserve the most accurate and critical parts of the dialogue history and the associated knowledge. In addition, we employ a Commonsense and Named Entity Enhanced Attention Module, which starts with the extracted triples from various sources and gradually finds the relevant supporting set of triples using multi-hop attention with the query vector obtained from the interactive dialogue-knowledge module. Empirical results on two benchmark datasets demonstrate that our model significantly outperforms the state-of-the-art methods in terms of both automatic evaluation metrics and human judgment. Our code is publicly available at https://github.com/deekshaVarshney/CNTF; https://www.iitp.ac.in/-ai-nlp-ml/resources/codes/CNTF.zip.

A recent topic of research in natural language generation has been the development of automatic response generation modules that can automatically respond to a user’s utterance in an empathetic manner. Previous research has tackled this task using neural generative methods by augmenting emotion classes with the input sequences. However, the outputs by these models may be inconsistent. We employ multi-task learning to predict the emotion label and to generate a viable response for a given utterance using a common encoder with multiple decoders. Our proposed encoder-decoder model consists of a self-attention based encoder and a decoder with dot product attention mechanism to generate response with a specified emotion. We use the focal loss to handle imbalanced data distribution, and utilize the consistency loss to allow coherent decoding by the decoders. Human evaluation reveals that our model produces more emotionally pertinent responses. In addition, our model outperforms multiple strong baselines on automatic evaluation measures such as F1 and BLEU scores, thus resulting in more fluent and adequate responses.

Automatic extraction of disaster-related events and their arguments from natural language text is vital for building a decision support system for crisis management. Event extraction from various news sources is a well-explored area for this objective. However, extracting events alone, without any context, provides only partial help for this purpose. Extracting related arguments like Time, Place, Casualties, etc., provides a complete picture of the disaster event. In this paper, we create a disaster domain dataset in Hindi by annotating disaster-related event and arguments. We also obtain equivalent datasets for Bengali and English from a collaboration. We build a multi-lingual deep learning model for argument extraction in all the three languages. We also compare our multi-lingual system with a similar baseline mono-lingual system trained for each language separately. It is observed that a single multi-lingual system is able to compensate for lack of training data, by using joint training of dataset from different languages in shared space, thus giving a better overall result.