Related papers: Comparing Feature-based and Context-aware Approach…
The proliferation of artificial intelligence (AI) in financial services has prompted growing demand for tools that can systematically detect AI-related disclosures in corporate filings. While prior approaches often rely on keyword expansion…
Context-aware neural machine translation aims to use the document-level context to improve translation quality. However, not all words in the context are helpful. The irrelevant or trivial words may bring some noise and distract the model…
Person search aims to jointly localize and identify a query person from natural, uncropped images, which has been actively studied over the past few years. In this paper, we delve into the rich context information globally and locally…
Bias in predictive machine learning (ML) models is a fundamental challenge due to the skewed or unfair outcomes produced by biased models. Existing mitigation strategies rely on either post-hoc corrections or rigid constraints. However,…
Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keypoint locations. In this paper, we go beyond the local detail…
A recommender system is an information filtering technology which can be used to predict preference ratings of items (products, services, movies, etc) and/or to output a ranking of items that are likely to be of interest to the user.…
We curated WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction. Although automatic annotation can lead to a high degree of label noise, it is an inexpensive process…
We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models.…
Traditional security scanners fail when facing new attack patterns they haven't seen before. They rely on fixed rules and predetermined signatures, making them blind to novel threats. We present a fundamentally different approach: instead…
Despite increasing instances of machine translation (MT) systems including contextual information, the evidence for translation quality improvement is sparse, especially for discourse phenomena. Popular metrics like BLEU are not expressive…
Recent advancements in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. However, their reliability and trustworthiness are still in doubt, especially for concerns regarding…
Feature attribution is a fundamental task in both machine learning and data analysis, which involves determining the contribution of individual features or variables to a model's output. This process helps identify the most important…
Pre-training on large models is prevalent and emerging with the ever-growing user-generated content in many machine learning application categories. It has been recognized that learning contextual knowledge from the datasets depicting…
Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware evaluation, such as contrastive methods, only measure…
Accurate recognition of specific categories, such as persons' names, dates or other identifiers is critical in many Automatic Speech Recognition (ASR) applications. As these categories represent personal information, ethical use of this…
Complex word identification (CWI) is a cornerstone process towards proper text simplification. CWI is highly dependent on context, whereas its difficulty is augmented by the scarcity of available datasets which vary greatly in terms of…
In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from…
Defining privacy and related notions such as Personal Identifiable Information (PII) is a central notion in computer science and other fields. The theoretical, technological, and application aspects of PII require a framework that provides…
De-identification is the task of identifying protected health information (PHI) in the clinical text. Existing neural de-identification models often fail to generalize to a new dataset. We propose a simple yet effective data augmentation…
Recognizing how objects interact with each other is a crucial task in visual recognition. If we define the context of the interaction to be the objects involved, then most current methods can be categorized as either: (i) training a single…