相关论文: Class-Adaptive Self-Training for Relation Extracti…

Relational fact extraction aims to extract semantic triplets from unstructured text. In this work, we show that all of the relational fact extraction models can be organized according to a graph-oriented analytical perspective. An efficient…

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set. Co-training methods exploit predicted labels on the unlabeled data and select samples based on…

Zero-shot Relation Triplet Extraction (ZeroRTE) aims to extract relation triplets from texts containing unseen relation types. This capability benefits various downstream information retrieval (IR) tasks. The primary challenge lies in…

Data scarcity has been the main factor that hinders the progress of event extraction. To overcome this issue, we propose a Self-Training with Feedback (STF) framework that leverages the large-scale unlabeled data and acquires feedback for…

Few-shot relation extraction aims to learn to identify the relation between two entities based on very limited training examples. Recent efforts found that textual labels (i.e., relation names and relation descriptions) could be extremely…

Practical natural language processing (NLP) tasks are commonly long-tailed with noisy labels. Those problems challenge the generalization and robustness of complex models such as Deep Neural Networks (DNNs). Some commonly used resampling…

We present a neural semi-supervised learning model termed Self-Pretraining. Our model is inspired by the classic self-training algorithm. However, as opposed to self-training, Self-Pretraining is threshold-free, it can potentially update…

Document-level relation extraction (DocRE) is the task of identifying all relations between each entity pair in a document. Evidence, defined as sentences containing clues for the relationship between an entity pair, has been shown to help…

Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these approaches rely on a cross-entropy loss function (CE), recent…

Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels, where one positive document is compared against several…

Open Relation Extraction (OpenRE) aims to discover novel relations from open domains. Previous OpenRE methods mainly suffer from two problems: (1) Insufficient capacity to discriminate between known and novel relations. When extending…

Open-world Relation Extraction (OpenRE) has recently garnered significant attention. However, existing approaches tend to oversimplify the problem by assuming that all unlabeled texts belong to novel classes, thereby limiting the…

Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations…

In order to train robust deep learning models, large amounts of labelled data is required. However, in the absence of such large repositories of labelled data, unlabeled data can be exploited for the same. Semi-Supervised learning aims to…

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo…

Extracting structured information from HTML documents is a long-studied problem with a broad range of applications, including knowledge base construction, faceted search, and personalized recommendation. Prior works rely on a few…

Unsupervised person re-identification (re-ID) aims at closing the performance gap to supervised methods. These methods build reliable relationship between data points while learning representations. However, we empirically show that the…

While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and…

Detecting negatives (such as non-entailment relationships, unanswerable questions, and false claims) is an important and challenging aspect of many natural language understanding tasks. Though manually collecting challenging negative…