# Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching

Source: [Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching](<https://www.sota2.com/research/paper/68fa65121e209131cea07f98>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:17:53.140Z

Authors: Xiao Yang, Madian Khabsa, Miaosen Wang, Wei Wang, Madian Khabsa, Ahmed Awadallah, Daniel Kifer, C. Lee Giles

Published: 2018-04-22T02:24:54.000Z

## Abstract

Community-based question answering (CQA) websites represent an important source of information. As a result, the problem of matching the most valuable answers to their corresponding questions has become an increasingly popular research topic. We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue. We employ a generative model to iteratively sample a subset of challenging negative samples to fool our classification model. Both models are alternatively optimized using REINFORCE algorithm. The proposed method is completely different from previous ones, where negative samples in training set are directly used or uniformly down-sampled. Further, we propose using Multi-scale Matching which explicitly inspects the correlation between words and ngrams of different levels of granularity. We evaluate the proposed method on SemEval 2016 and SemEval 2017 datasets and achieves state-of-the-art or similar performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.08058>)

[PDF](<https://arxiv.org/pdf/1804.08058.pdf>)
