Related papers: Learning Robust Negation Text Representations
Sentence embeddings encode sentences in fixed dense vectors and have played an important role in various NLP tasks and systems. Methods for building sentence embeddings include unsupervised learning such as Quick-Thoughts and supervised…
Despite the impressive performance of large language models across various tasks, they often struggle with reasoning under negated statements. Negations are important in real-world applications as they encode negative polarity in verb…
One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages. In this work, we investigate the robustness of the mention detection systems, one of the fundamental tasks…
Homographs, words with the same spelling but different meanings, remain challenging in Neural Machine Translation (NMT). While recent works leverage various word embedding approaches to differentiate word sense in NMT, they do not focus on…
Evaluating model robustness is critical when developing trustworthy models not only to gain deeper understanding of model behavior, strengths, and weaknesses, but also to develop future models that are generalizable and robust across…
Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks. To alleviate this…
Can we combine heterogenous graph structure with text to learn high-quality semantic and behavioural representations? Graph neural networks (GNN)s encode numerical node attributes and graph structure to achieve impressive performance in a…
Recent developments in adversarial attacks on deep learning leave many mission-critical natural language processing (NLP) systems at risk of exploitation. To address the lack of computationally efficient adversarial defense methods, this…
Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network…
Retrieval Augmented Generation (RAG) systems have emerged as a powerful method for enhancing large language models (LLMs) with up-to-date information. However, the retrieval step in RAG can sometimes surface documents containing…
Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer…
Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging,…
Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect…
Machine based text comprehension has always been a significant research field in natural language processing. Once a full understanding of the text context and semantics is achieved, a deep learning model can be trained to solve a large…
Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems. Large language models are now the standard to develop state-of-the-art solutions for text detection…
Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large versions, and investigate how faithful…
In modern e-commerce search systems, dense retrieval has become an indispensable component. By computing similarities between query and item (product) embeddings, it efficiently selects candidate products from large-scale repositories. With…
Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…
This study aims to demonstrate the methods for detecting negations in a sentence by uniquely evaluating the lexical structure of the text via word-sense disambiguation. The proposed framework examines all the unique features in the various…