<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chan-king-2018-thread">
    <titleInfo>
        <title>Thread Popularity Prediction and Tracking with a Permutation-invariant Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hou</namePart>
        <namePart type="given">Pong</namePart>
        <namePart type="family">Chan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Irwin</namePart>
        <namePart type="family">King</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct&quot;-&quot;nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The task of thread popularity prediction and tracking aims to recommend a few popular comments to subscribed users when a batch of new comments arrive in a discussion thread. This task has been formulated as a reinforcement learning problem, in which the reward of the agent is the sum of positive responses received by the recommended comments. In this work, we propose a novel approach to tackle this problem. First, we propose a deep neural network architecture to model the expected cumulative reward (Q-value) of a recommendation (action). Unlike the state-of-the-art approach, which treats an action as a sequence, our model uses an attention mechanism to integrate information from a set of comments. Thus, the prediction of Q-value is invariant to the permutation of the comments, which leads to a more consistent agent behavior. Second, we employ a greedy procedure to approximate the action that maximizes the predicted Q-value from a combinatorial action space. Different from the state-of-the-art approach, this procedure does not require an additional pre-trained model to generate candidate actions. Experiments on five real-world datasets show that our approach outperforms the state-of-the-art.</abstract>
    <identifier type="citekey">chan-king-2018-thread</identifier>
    <identifier type="doi">10.18653/v1/D18-1376</identifier>
    <location>
        <url>https://aclanthology.org/D18-1376</url>
    </location>
    <part>
        <date>2018-oct&quot;-&quot;nov</date>
        <extent unit="page">
            <start>3392</start>
            <end>3401</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Thread Popularity Prediction and Tracking with a Permutation-invariant Model
%A Chan, Hou Pong
%A King, Irwin
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct" "nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F chan-king-2018-thread
%X The task of thread popularity prediction and tracking aims to recommend a few popular comments to subscribed users when a batch of new comments arrive in a discussion thread. This task has been formulated as a reinforcement learning problem, in which the reward of the agent is the sum of positive responses received by the recommended comments. In this work, we propose a novel approach to tackle this problem. First, we propose a deep neural network architecture to model the expected cumulative reward (Q-value) of a recommendation (action). Unlike the state-of-the-art approach, which treats an action as a sequence, our model uses an attention mechanism to integrate information from a set of comments. Thus, the prediction of Q-value is invariant to the permutation of the comments, which leads to a more consistent agent behavior. Second, we employ a greedy procedure to approximate the action that maximizes the predicted Q-value from a combinatorial action space. Different from the state-of-the-art approach, this procedure does not require an additional pre-trained model to generate candidate actions. Experiments on five real-world datasets show that our approach outperforms the state-of-the-art.
%R 10.18653/v1/D18-1376
%U https://aclanthology.org/D18-1376
%U https://doi.org/10.18653/v1/D18-1376
%P 3392-3401

Markdown (Informal)

[Thread Popularity Prediction and Tracking with a Permutation-invariant Model](https://aclanthology.org/D18-1376) (Chan & King, EMNLP 2018)

• Thread Popularity Prediction and Tracking with a Permutation-invariant Model (Chan & King, EMNLP 2018)

ACL

• Hou Pong Chan and Irwin King. 2018. Thread Popularity Prediction and Tracking with a Permutation-invariant Model. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3392–3401, Brussels, Belgium. Association for Computational Linguistics.