# Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks

arXiv: https://arxiv.org/abs/1709.10191 · HTML: https://mlsanity.com/paper/1709.10191/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2017.

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

- [Detect and Classify -- Joint Span Detection and Classification for Health Outcomes](https://mlsanity.com/paper/2104.07789/) (2021)
- [Multi-Task Learning of Query Intent and Named Entities using Transfer Learning](https://mlsanity.com/paper/2105.03316/) (2021)
- [Joint model for intent and entity recognition](https://mlsanity.com/paper/2109.03221/) (2021)
- [A survey of joint intent detection and slot-filling models in natural language understanding](https://mlsanity.com/paper/2101.08091/) (2021)
- [Spoken Language Understanding for Conversational AI: Recent Advances and Future Direction](https://mlsanity.com/paper/2212.10728/) (2022)

## Abstract (arXiv)

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and slot filling, or in topic classification and named-entity recognition. In order to utilize the potential benefits from their correlations, we propose a jointly trained model for learning the two tasks simultaneously via Long Short-Term Memory (LSTM) networks. This model predicts the sentence-level category and the word-level label sequence from the stepwise output hidden representations of LSTM. We also introduce a novel mechanism of "sparse attention" to weigh words differently based on their semantic relevance to sentence-level classification. The proposed method outperforms baseline models on ATIS and TREC datasets.