Related papers: Comparing Feature-based and Context-aware Approach…

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…

Meta-learning approaches have addressed few-shot problems by finding initialisations suited for fine-tuning to target tasks. Often there are additional properties within training data (which we refer to as context), not relevant to the…

For many business applications that require the processing, indexing, and retrieval of professional documents such as legal briefs (in PDF format etc.), it is often essential to classify the pages of any given document into their…

Language is a cornerstone of cultural identity, yet globalization and the dominance of major languages have placed nearly 3,000 languages at risk of extinction. Existing AI-driven translation models prioritize efficiency but often fail to…

We study the settings for which deep contextual embeddings (e.g., BERT) give large improvements in performance relative to classic pretrained embeddings (e.g., GloVe), and an even simpler baseline---random word embeddings---focusing on the…

Conversational AI has become an increasingly prominent and practical application of machine learning. However, existing conversational AI techniques still suffer from various limitations. One such limitation is a lack of well-developed…

Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…

Linguistic bias in online news and social media is widespread but difficult to measure. Yet, its identification and quantification remain difficult due to subjectivity, context dependence, and the scarcity of high-quality gold-label…

BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently. In the mean time, the importance and usefulness to…

Person Search is a relevant task that aims to jointly solve Person Detection and Person Re-identification(re-ID). Though most previous methods focus on learning robust individual features for retrieval, it's still hard to distinguish…

Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult…

Qualitative research often contains personal, contextual, and organizational details that pose privacy risks if not handled appropriately. Manual anonymization is time-consuming, inconsistent, and frequently omits critical identifiers.…

We demonstrate how publicly available social-media data and generative AI (GenAI) can be misused to automate and scale highly personalized, context-aware spear-phishing campaigns. With minimal attacker effort, a small amount of public…

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

This paper examines how estimates of AI use in scientific writing can be biased when evaluation methods ignore contextual differences across countries and fields. Using large-scale data on journal publications from Dimensions, we construct…

Context-aware neural machine translation involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, and has given rise to a number of…

While composing a new document, anything from a news article to an email or essay, authors often utilize direct quotes from a variety of sources. Although an author may know what point they would like to make, selecting an appropriate quote…

Text-based person retrieval aims to identify a target individual from an image gallery using a natural language description. Existing methods primarily focus on appearance-driven cross-modal retrieval, yet face significant challenges due to…

Despite the widely reported success of embedding-based machine learning methods on natural language processing tasks, the use of more easily interpreted engineered features remains common in fields such as cognitive impairment (CI)…

Point-of-interest (POI) recommender systems help users discover relevant locations, but their effectiveness is often compromised by popularity bias, which disadvantages less popular, yet potentially meaningful places. This paper addresses…