Related papers: DetIE: Multilingual Open Information Extraction In…
Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely…
Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for segment…
Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challenges in efficiently learning word representations in the…
Conventional object detection models are usually limited by the data on which they were trained and by the category logic they define. With the recent rise of Language-Visual Models, new methods have emerged that are not restricted to these…
Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts. Common IE solutions, including Relation Extraction (RE) and open IE systems, can hardly handle cross-sentence tuples, and are…
Substantial progress has been made in various techniques for open-world recognition. Out-of-distribution (OOD) detection methods can effectively distinguish between known and unknown classes in the data, while incremental learning enables…
Traditional semi-supervised object detection methods assume a fixed set of object classes (in-distribution or ID classes) during training and deployment, which limits performance in real-world scenarios where unseen classes…
Extracting entities and their relations from text is an important task for understanding massive text corpora. Open information extraction (IE) systems mine relation tuples (i.e., entity arguments and a predicate string to describe their…
Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This…
Open Information Extraction (OIE) aims to extract factual relational tuples from open-domain sentences. Downstream tasks use the extracted OIE tuples as facts, without examining the certainty of these facts. However, uncertainty/speculation…
Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affects downstream tasks. We conduct the first analysis of the…
We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…
We present the first open-set language identification experiments using one-class classification. We first highlight the shortcomings of traditional feature extraction methods and propose a hashing-based feature vectorization approach as a…
We introduce a novel universal soft-decision decoding algorithm for binary block codes called ordered reliability direct error pattern testing (ORDEPT). Our results, obtained for a variety of popular short high-rate codes, demonstrate that…
Beam search decoding is the de-facto method for decoding auto-regressive Neural Machine Translation (NMT) models, including multilingual NMT where the target language is specified as an input. However, decoding multilingual NMT models…
In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes…
In the present work we propose an unsupervised ensemble method consisting of oblique trees that can address the task of auto-encoding, namely Oblique Forest AutoEncoders (briefly OF-AE). Our method is a natural extension of the eForest…
Recently, numbers of works shows that the performance of neural machine translation (NMT) can be improved to a certain extent with using visual information. However, most of these conclusions are drawn from the analysis of experimental…
In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes. It is a two-stage training approach that first uses a…
Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…