# Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures

arXiv: https://arxiv.org/abs/1707.01075 · HTML: https://mlsanity.com/paper/1707.01075/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2017.

## Built on by (most cited first, 7 of 7)

- [Extracting Temporal Event Relation with Syntax-guided Graph Transformer](https://mlsanity.com/paper/2104.09570/) (2021)
- [End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting](https://mlsanity.com/paper/2207.08179/) (2022)
- [Textual Entailment for Effective Triple Validation in Object Prediction](https://mlsanity.com/paper/2401.16293/) (2024)
- [Enriched Attention for Robust Relation Extraction](https://mlsanity.com/paper/2104.10899/) (2021)
- [Transfer Learning for Multi-lingual Tasks -- a Survey](https://mlsanity.com/paper/2110.02052/) (2021)
- [Low-Resource Named Entity Recognition Based on Multi-hop Dependency Trigger](https://mlsanity.com/paper/2109.07118/) (2021)
- [Spoken Dialogue System for Medical Prescription Acquisition on Smartphone: Development, Corpus and Evaluation](https://mlsanity.com/paper/2311.03510/) (2023)

## Abstract (arXiv)

Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:citiesofresidence) for a given entity from a large collection of source documents. In this paper we propose an effective DNN architecture for SF with the following new strategies: (1). Take a regularized dependency graph instead of a raw sentence as input to DNN, to compress the wide contexts between query and candidate filler; (2). Incorporate two attention mechanisms: local attention learned from query and candidate filler, and global attention learned from external knowledge bases, to guide the model to better select indicative contexts to determine slot type. Experiments show that this framework outperforms state-of-the-art on both relation extraction (16% absolute F-score gain) and slot filling validation for each individual system (up to 8.5% absolute F-score gain).