Open AccessPosted Content
InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction.
TL;DR: This paper introduces two widely-existing sources in knowledge bases, namely entity descriptions, and multi-grained entity types to enrich the distantly supervised data, and sees information sources as multiple views and fusing them to construct an intact space with sufficient information.
read more
Abstract: Distant supervision makes it possible to automatically label bags of sentences for relation extraction by leveraging knowledge bases, but suffers from the sparse and noisy bag issues. Additional information sources are urgently needed to supplement the training data and overcome these issues. In this paper, we introduce two widely-existing sources in knowledge bases, namely entity descriptions, and multi-grained entity types to enrich the distantly supervised data. We see information sources as multiple views and fusing them to construct an intact space with sufficient information. An end-to-end multi-view learning framework is proposed for relation extraction via Intact Space Representation Learning (InSRL), and the representations of single views are jointly learned simultaneously. Moreover, inner-view and cross-view attention mechanisms are used to highlight important information on different levels on an entity-pair basis. The experimental results on a popular benchmark dataset demonstrate the necessity of additional information sources and the effectiveness of our framework. We will release the implementation of our model and dataset with multiple information sources after the anonymized review phase.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing.
Yi Chen (陈奕),Haiyun Jiang,Lemao Liu,Shuming Shi,Chuang Fan,Min Yang,Ruifeng Xu +6 more
- 01 Nov 2021
TL;DR: This article propose a multi-source fusion model (MSF) targeting three kinds of auxiliary information: context consistency, type hierarchy and background knowledge (e.g., prototypes and descriptions) of types, and obtain up to 11.42% and 22.84% absolute gains over state-of-the-art baselines on BBN and Wiki respectively.
9
Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances
Zhendong Chu,Ruiyi Zhang,Tong Yu,Rajiv Jain,Vlad I. Morariu,Jiuxiang Gu,Ani Nenkova +6 more
TL;DR: Researchers propose a method to improve named entity recognition (NER) performance on noisy data by training a discriminator model to detect errors and recalibrate sample weights with a small set of clean instances, achieving consistent improvements on public datasets.
1
Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision
01 Jan 2022
TL;DR: This paper proposed a hierarchical type-sentence alignment module to enrich a sentence with the triple fact's basic attributes to support long-tail relations. But their model is limited to a coarse-grained relation, making it hard to discriminate relations based solely on sentence semantics.
1
•Posted Content
Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision.
TL;DR: This article proposed a hierarchical type-sentence alignment module to enrich a sentence with the triple fact's basic attributes to support long-tail relations. But their model is limited to a coarse-grained relation, making it hard to discriminate relations based solely on sentence semantics.
A Benchmark for Text Expansion: Datasets, Metrics, and Baselines
Yi Chen,Haiyun Jiang,Wei Bi,Rui Wang,Longyue Wang,Shuming Shi,Rui-Hua Xu +6 more
TL;DR: This work presents a new task of Text Expansion, which aims to insert fine-grained modifiers into proper locations of the plain text to concretize or vivify human writings, and proposes Info-Gain to effectively measure the informativeness of expansions, which is an important quality dimension in TE.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
- 12 Jun 2017
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
•Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
Tomas Mikolov,Ilya Sutskever,Kai Chen,Greg S. Corrado,Jeffrey Dean +4 more
- 05 Dec 2013
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
•Posted Content
Layer Normalization
TL;DR: In this paper, layer normalization is applied to recurrent neural networks by computing the mean and variance used for normalization from all of the summed inputs to the neurons in a layer on a single training case.
7.1K
Combining labeled and unlabeled data with co-training
Avrim Blum,Tom M. Mitchell +1 more
- 24 Jul 1998
TL;DR: A PAC-style analysis is provided for a problem setting motivated by the task of learning to classify web pages, in which the description of each example can be partitioned into two distinct views, to allow inexpensive unlabeled data to augment, a much smaller set of labeled examples.
6.4K