Adversarial Training for Relation Extraction
نویسندگان
چکیده
Adversarial training is a mean of regularizing classification algorithms by generating adversarial noise to the training data. We apply adversarial training in relation extraction within the multi-instance multi-label learning framework. We evaluate various neural network architectures on two different datasets. Experimental results demonstrate that adversarial training is generally effective for both CNN and RNN models and significantly improves the precision of predicted relations.
منابع مشابه
Adversarial Sequence Tagging
Providing sequence tagging that minimize Hamming loss is a challenging, but important, task. Directly minimizing this loss over a training sample is generally an NP-hard problem. Instead, existing sequence tagging methods minimize a convex upper bound that upper bounds the Hamming loss. Unfortunately, this often either leads to inconsistent predictors (e.g., max-margin methods) or predictions t...
متن کاملTowards Stable Adversarial Feature Learning for LiDAR based Loop Closure Detection
Stable feature extraction is the key for the Loop closure detection (LCD) task in the simultaneously localization and mapping (SLAM) framework. In our paper, the feature extraction is operated by using a generative adversarial networks (GANs) based unsupervised learning. GANs are powerful generative models, however, GANs based adversarial learning suffers from training instability. We find that...
متن کاملDomain Adaptation for Relation Extraction with Domain Adversarial Neural Network
Relations are expressed in many domains such as newswire, weblogs and phone conversations. Trained on a source domain, a relation extractor’s performance degrades when applied to target domains other than the source. A common yet labor-intensive method for domain adaptation is to construct a target-domainspecific labeled dataset for adapting the extractor. In response, we present an unsupervise...
متن کاملA DIRT-T Approach to Unsupervised Domain Adaptation
Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two domains is via domain adversarial training (Ganin & Lempitsky, 2015), which attempts to induce a feature extractor that matches the source and target feature di...
متن کاملUnsupervised Pre-training With Seq2Seq Reconstruction Loss for Deep Relation Extraction Models
Relation extraction models based on deep learning have been attracting a lot of attention recently. Little research is carried out to reduce their need of labeled training data. In this work, we propose an unsupervised pre-training method based on the sequence-to-sequence model for deep relation extraction models. The pre-trained models need only half or even less training data to achieve equiv...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017