相关论文: Towards Confident Machine Reading Comprehension

Question-answering plays an important role in e-commerce as it allows potential customers to actively seek crucial information about products or services to help their purchase decision making. Inspired by the recent success of machine…

Understanding the confidence with which a machine learning model classifies an input datum is an important, and perhaps under-investigated, concept. In this paper, we propose a new calibration metric, the Entropic Calibration Difference…

Reading comprehension (RC)---in contrast to information retrieval---requires integrating information and reasoning about events, entities, and their relations across a full document. Question answering is conventionally used to assess RC…

Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support…

Cross-lingual Machine Reading Comprehension (xMRC) is challenging due to the lack of training data in low-resource languages. The recent approaches use training data only in a resource-rich language like English to fine-tune large-scale…

Recent advances in computer vision have made training object detectors more efficient and effective; however, assessing their performance in real-world applications still relies on costly manual annotation. To address this limitation, we…

Task requirements (TRs) writing is an important question type in Key English Test and Preliminary English Test. A TR writing question may include multiple requirements and a high-quality essay must respond to each requirement thoroughly and…

Matrix completion aims to estimate missing entries in a data matrix, using the assumption of a low-complexity structure (e.g., low rank) so that imputation is possible. While many effective estimation algorithms exist in the literature,…

Rapid advances in perception have enabled large pre-trained models to be used out of the box for transforming high-dimensional, noisy, and partial observations of the world into rich occupancy representations. However, the reliability of…

Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question. Prior work mainly focuses on designing specific methods or applying heuristic strategies to encourage…

Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from…

We propose Confidence-guided Refinement Reasoning (C2R), a novel training-free framework applicable to question-answering (QA) tasks across text, image, and video domains. C2R strategically constructs and refines sub-questions and their…

Machine reading comprehension (MRC) is a sub-field in natural language processing that aims to assist computers understand unstructured texts and then answer questions related to them. In practice, the conversation is an essential way to…

Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Most of the existing researches focus on the modeling of…

For effective collaboration between humans and intelligent agents that employ machine learning for decision-making, humans must understand what agents can and cannot do to avoid over/under-reliance. A solution to this problem is adjusting…

Reading Comprehension (RC) is a task of answering a question from a given passage or a set of passages. In the case of multiple passages, the task is to find the best possible answer to the question. Recent trials and experiments in the…

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…

Referring Expression Comprehension (REC) is a popular multimodal task that aims to accurately detect target objects within a single image based on a given textual expression. However, due to the limitations of earlier models, traditional…

Hyperdimensional computing (HDC) has become popular for light-weight and energy-efficient machine learning, suitable for wearable Internet-of-Things (IoT) devices and near-sensor or on-device processing. HDC is computationally less complex…

Commonsense reasoning is an appealing topic in natural language processing (NLP) as it plays a fundamental role in supporting the human-like actions of NLP systems. With large-scale language models as the backbone, unsupervised pre-training…