Simple Attention-Based Representation Learning for Ranking Short Social Media Posts

11/02/2018
by   Peng Shi, et al.
0

This paper explores the problem of ranking short social media posts with respect to user queries using neural networks. Instead of starting with a complex architecture, we proceed from the bottom up and examine the effectiveness of a simple, word-level Siamese architecture augmented with attention-based mechanisms for capturing semantic soft matches between query and post terms. Extensive experiments on datasets from the TREC Microblog Tracks show that our simple models not only demonstrate better effectiveness than existing approaches that are far more complex or exploit a more diverse set of relevance signals, but also achieve 4 times speedup in model training and inference.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/21/2018

Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search

Despite substantial interest in applications of neural networks to infor...
research
04/20/2017

Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection

The proliferation of social media in communication and information disse...
research
07/25/2017

Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams

Time is an important relevance signal when searching streams of social m...
research
09/18/2023

How to Generate Popular Post Headlines on Social Media?

Posts, as important containers of user-generated-content pieces on socia...
research
04/14/2022

Anti-Asian Hate Speech Detection via Data Augmented Semantic Relation Inference

With the spreading of hate speech on social media in recent years, autom...
research
12/23/2021

Bi-Directional Recurrent Neural Ordinary Differential Equations for Social Media Text Classification

Classification of posts in social media such as Twitter is difficult due...
research
07/02/2022

An End-to-End Set Transformer for User-Level Classification of Depression and Gambling Disorder

This work proposes a transformer architecture for user-level classificat...

Please sign up or login with your details

Forgot password? Click here to reset