RESIDE: Improving Distantly-Supervised Neural Relation Extraction
using Side Information
Shikhar Vashishth
1
Rishabh Joshi
2 ∗
Sai Suman Prayaga
1
Chiranjib Bhattacharyya
1
Partha Talukdar
1
1
Indian Institute of Science
2
Birla Institute of Technology and Science, Pilani
{shikhar,chiru,ppt}@iisc.ac.in
f2014102@pilani.bits-pilani.ac.in, suman.sai14@gmail.com
Abstract
Distantly-supervised Relation Extraction (RE)
methods train an extractor by automatically
aligning relation instances in a Knowledge
Base (KB) with unstructured text. In addi-
tion to relation instances, KBs often contain
other relevant side information, such as aliases
of relations (e.g., founded and co-founded are
aliases for the relation founderOfCompany).
RE models usually ignore such readily avail-
able side information. In this paper, we pro-
pose RESIDE, a distantly-supervised neural
relation extraction method which utilizes ad-
ditional side information from KBs for im-
proved relation extraction. It uses entity type
and relation alias information for imposing
soft constraints while predicting relations. RE-
SIDE employs Graph Convolution Networks
(GCN) to encode syntactic information from
text and improves performance even when
limited side information is available. Through
extensive experiments on benchmark datasets,
we demonstrate RESIDE’s effectiveness. We
have made RESIDE’s source code available to
encourage reproducible research.
1 Introduction
The construction of large-scale Knowledge Bases
(KBs) like Freebase (Bollacker et al., 2008) and
Wikidata (Vrande
ˇ
ci
´
c and Kr
¨
otzsch, 2014) has
proven to be useful in many natural language pro-
cessing (NLP) tasks like question-answering, web
search, etc. However, these KBs are not exhaus-
tive. Relation Extraction (RE) attempts to fill this
gap by extracting semantic relationships between
entity pairs from plain text. This task can be mod-
eled as a simple classification problem after the
entity pairs are specified. Formally, given an en-
tity pair (e
1
,e
2
) from the KB and an entity anno-
tated sentence (or instance), we aim to predict the
∗
This research was conducted during the author’s intern-
ship at Indian Institute of Science.
relation r, from a predefined relation set, that ex-
ists between e
1
and e
2
. If no relation exists, we
simply label it NA.
Most supervised relation extraction methods re-
quire large labeled training data which is expen-
sive to construct. Distant Supervision (DS) (Mintz
et al., 2009) helps with the construction of this
dataset automatically, under the assumption that
if two entities have a relationship in a KB, then
all sentences mentioning those entities express the
same relation. While this approach works well in
generating large amounts of training instances, the
DS assumption does not hold in all cases. Riedel
et al. (2010); Hoffmann et al. (2011); Surdeanu
et al. (2012) propose multi-instance based learn-
ing to relax this assumption. However, they use
NLP tools to extract features, which can be noisy.
Recently, neural models have demonstrated
promising performance on RE. Zeng et al. (2014,
2015) employ Convolutional Neural Networks
(CNN) to learn representations of instances. For
alleviating noise in distant supervised datasets, at-
tention has been utilized by (Lin et al., 2016; Jat
et al., 2018). Syntactic information from depen-
dency parses has been used by (Mintz et al., 2009;
He et al., 2018) for capturing long-range depen-
dencies between tokens. Recently proposed Graph
Convolution Networks (GCN) (Defferrard et al.,
2016) have been effectively employed for en-
coding this information (Marcheggiani and Titov,
2017; Bastings et al., 2017). However, all the
above models rely only on the noisy instances
from distant supervision for RE.
Relevant side information can be effective for
improving RE. For instance, in the sentence, Mi-
crosoft was started by Bill Gates., the type infor-
mation of Bill Gates (person) and Microsoft (or-
ganization) can be helpful in predicting the cor-
rect relation founderOfCompany. This is because
every relation constrains the type of its target en-
arXiv:1812.04361v1 [cs.CL] 11 Dec 2018