# Graph-Based Tri-Attention Network for Answer Ranking in CQA

arXiv: https://arxiv.org/abs/2103.03583 · HTML: https://mlsanity.com/paper/2103.03583/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [A Convolutional Neural Network for Modelling Sentences](https://mlsanity.com/paper/1404.2188/) (2014)
- [Dual Attention Networks for Multimodal Reasoning and Matching](https://mlsanity.com/paper/1611.00471/) (2016)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs](https://mlsanity.com/paper/1905.07374/) (2019)
- [Global Thread-Level Inference for Comment Classification in Community Question Answering](https://mlsanity.com/paper/1911.08755/) (2019)

## Built on by (most cited first, 8 of 8)

- [Question-Answer Sentence Graph for Joint Modeling Answer Selection](https://mlsanity.com/paper/2203.03549/) (2022)
- [UIT-ViCoV19QA: A Dataset for COVID-19 Community-based Question Answering on Vietnamese Language](https://mlsanity.com/paper/2209.06668/) (2022)
- [Beyond Semantics: Learning a Behavior Augmented Relevance Model with Self-supervised Learning](https://mlsanity.com/paper/2308.05379/) (2023)
- [Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models](https://mlsanity.com/paper/2311.17502/) (2023)
- [Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering](https://mlsanity.com/paper/2310.14602/) (2023)
- [Attention-based graph neural networks: a survey](https://mlsanity.com/paper/2605.08679/) (2026)
- [Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning](https://mlsanity.com/paper/2112.01110/) (2021)
- [Neighbour-level Message Interaction Encoding for Improved Representation Learning on Graphs](https://mlsanity.com/paper/2404.09809/) (2024)

## Abstract (arXiv)

In community-based question answering (CQA) platforms, automatic answer ranking for a given question is critical for finding potentially popular answers in early times. The mainstream approaches learn to generate answer ranking scores based on the matching degree between question and answer representations as well as the influence of respondents. However, they encounter two main limitations: (1) Correlations between answers in the same question are often overlooked. (2) Question and respondent representations are built independently of specific answers before affecting answer representations. To address the limitations, we devise a novel graph-based tri-attention network, namely GTAN, which has two innovations. First, GTAN proposes to construct a graph for each question and learn answer correlations from each graph through graph neural networks (GNNs). Second, based on the representations learned from GNNs, an alternating tri-attention method is developed to alternatively build target-aware respondent representations, answer-specific question representations, and context-aware answer representations by attention computation. GTAN finally integrates the above representations to generate answer ranking scores. Experiments on three real-world CQA datasets demonstrate GTAN significantly outperforms state-of-the-art answer ranking methods, validating the rationality of the network architecture.