# Neural Subgraph Explorer: Reducing Noisy Information via Target-Oriented Syntax Graph Pruning

arXiv: https://arxiv.org/abs/2205.10970 · HTML: https://mlsanity.com/paper/2205.10970/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 23 May 2022.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [Interactive Attention Networks for Aspect-Level Sentiment Classification](https://mlsanity.com/paper/1709.00893/) (2017)
- [Effective LSTMs for Target-Dependent Sentiment Classification](https://mlsanity.com/paper/1512.01100/) (2015)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://mlsanity.com/paper/1909.03477/) (2019)
- [Attentional Encoder Network for Targeted Sentiment Classification](https://mlsanity.com/paper/1902.09314/) (2019)
- [Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks](https://mlsanity.com/paper/1909.02606/) (2019)
- [Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis](https://mlsanity.com/paper/1906.01213/) (2019)
- [Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network](https://mlsanity.com/paper/2108.02352/) (2021)
- [Earlier Attention? Aspect-Aware LSTM for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/1905.07719/) (2019)
- [Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2106.10816/) (2021)
- [DigNet: Digging Clues from Local-Global Interactive Graph for Aspect-level Sentiment Classification](https://mlsanity.com/paper/2201.00989/) (2022)

## Built on by (most cited first, 5 of 5)

- [Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs](https://mlsanity.com/paper/2210.10375/) (2022)
- [Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling](https://mlsanity.com/paper/2210.10369/) (2022)
- [Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding](https://mlsanity.com/paper/2306.09114/) (2023)
- [Co-evolving Graph Reasoning Network for Emotion-Cause Pair Extraction](https://mlsanity.com/paper/2306.04340/) (2023)
- [Co-guiding for Multi-intent Spoken Language Understanding](https://mlsanity.com/paper/2312.03716/) (2023)

## Abstract (arXiv)

Recent years have witnessed the emerging success of leveraging syntax graphs for the target sentiment classification task. However, we discover that existing syntax-based models suffer from two issues: noisy information aggregation and loss of distant correlations. In this paper, we propose a novel model termed Neural Subgraph Explorer, which (1) reduces the noisy information via pruning target-irrelevant nodes on the syntax graph; (2) introduces beneficial first-order connections between the target and its related words into the obtained graph. Specifically, we design a multi-hop actions score estimator to evaluate the value of each word regarding the specific target. The discrete action sequence is sampled through Gumble-Softmax and then used for both of the syntax graph and the self-attention graph. To introduce the first-order connections between the target and its relevant words, the two pruned graphs are merged. Finally, graph convolution is conducted on the obtained unified graph to update the hidden states. And this process is stacked with multiple layers. To our knowledge, this is the first attempt of target-oriented syntax graph pruning in this task. Experimental results demonstrate the superiority of our model, which achieves new state-of-the-art performance.