Enhancing the Input Representation: From Complexity to Simplicity

08/01/2017
by   Nafise Sadat Moosavi, et al.
0

We introduce an efficient algorithm for mining informative combinations of attribute-values for a given task. We use informative attribute-values to enhance the input representation of data. We apply our approach to coreference resolution using a simple set of attributes like syntactic roles and string match. With the enhanced representation, a simple coreference model outperforms more complex state-of-the-art models by a large margin. The use of the enhanced representation results in robust improvements in both in-domain and out-of-domain evaluations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/12/2021

Scalable Approach for Normalizing E-commerce Text Attributes (SANTA)

In this paper, we present SANTA, a scalable framework to automatically n...
research
03/13/2020

Inducing Optimal Attribute Representations for Conditional GANs

Conditional GANs are widely used in translating an image from one catego...
research
01/13/2022

Supporting Domain Data Selection in Data-Enhanced Process Models

Process mining bridges the gap between process management and data scien...
research
06/01/2017

Fader Networks: Manipulating Images by Sliding Attributes

This paper introduces a new encoder-decoder architecture that is trained...
research
10/28/2015

Flexibly Mining Better Subgroups

In subgroup discovery, also known as supervised pattern mining, discover...
research
12/31/2019

Learning to Infer User Interface Attributes from Images

We explore a new domain of learning to infer user interface attributes t...
research
07/08/2019

Knowledge-aware Pronoun Coreference Resolution

Resolving pronoun coreference requires knowledge support, especially for...

Please sign up or login with your details

Forgot password? Click here to reset