# Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling

arXiv: https://arxiv.org/abs/1601.01530 · HTML: https://mlsanity.com/paper/1601.01530/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2016.

## Built on by (most cited first, 25 of 25)

- [A Survey on Spoken Language Understanding: Recent Advances and New Frontiers](https://mlsanity.com/paper/2103.03095/) (2021)
- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [Automatic Intent-Slot Induction for Dialogue Systems](https://mlsanity.com/paper/2103.08886/) (2021)
- [Linguistically-Enriched and Context-Aware Zero-shot Slot Filling](https://mlsanity.com/paper/2101.06514/) (2021)
- [GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Filling](https://mlsanity.com/paper/2106.07055/) (2021)
- [Few-shot Learning for Slot Tagging with Attentive Relational Network](https://mlsanity.com/paper/2103.02333/) (2021)
- [Multimodal Dialogue State Tracking](https://mlsanity.com/paper/2206.07898/) (2022)
- [An Effective Non-Autoregressive Model for Spoken Language Understanding](https://mlsanity.com/paper/2108.07005/) (2021)
- [A Result based Portable Framework for Spoken Language Understanding](https://mlsanity.com/paper/2103.06010/) (2021)
- [mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling](https://mlsanity.com/paper/2203.12940/) (2022)
- [A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding](https://mlsanity.com/paper/2211.12220/) (2022)
- [Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-turn Spoken Language Understanding](https://mlsanity.com/paper/2206.12209/) (2022)
- [Toward Open-domain Slot Filling via Self-supervised Co-training](https://mlsanity.com/paper/2303.13801/) (2023)
- [Joint model for intent and entity recognition](https://mlsanity.com/paper/2109.03221/) (2021)
- [Traffic Event Detection as a Slot Filling Problem](https://mlsanity.com/paper/2109.06035/) (2021)
- [LSTM-RASA Based Agri Farm Assistant for Farmers](https://mlsanity.com/paper/2204.09717/) (2022)
- [Multilingual Name Entity Recognition and Intent Classification Employing Deep Learning Architectures](https://mlsanity.com/paper/2211.02415/) (2022)
- [ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling](https://mlsanity.com/paper/2211.14829/) (2022)
- [Zero-Shot Learning for Joint Intent and Slot Labeling](https://mlsanity.com/paper/2212.07922/) (2022)
- [Introducing "Forecast Utterance" for Conversational Data Science](https://mlsanity.com/paper/2309.03877/) (2023)
- [HierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling](https://mlsanity.com/paper/2310.09135/) (2023)
- [Transforming NLU with Babylon: A Case Study in Development of Real-time, Edge-Efficient, Multi-Intent Translation System for Automated Drive-Thru Ordering](https://mlsanity.com/paper/2411.15372/) (2024)
- [A survey of joint intent detection and slot-filling models in natural language understanding](https://mlsanity.com/paper/2101.08091/) (2021)
- [Enhancing Slot Tagging with Intent Features for Task Oriented Natural Language Understanding using BERT](https://mlsanity.com/paper/2205.09732/) (2022)
- [A Generative Model for Joint Multiple Intent Detection and Slot Filling](https://mlsanity.com/paper/2602.08322/) (2026)

## Abstract (arXiv)

Recurrent Neural Network (RNN) and one of its specific architectures, Long Short-Term Memory (LSTM), have been widely used for sequence labeling. In this paper, we first enhance LSTM-based sequence labeling to explicitly model label dependencies. Then we propose another enhancement to incorporate the global information spanning over the whole input sequence. The latter proposed method, encoder-labeler LSTM, first encodes the whole input sequence into a fixed length vector with the encoder LSTM, and then uses this encoded vector as the initial state of another LSTM for sequence labeling. Combining these methods, we can predict the label sequence with considering label dependencies and information of whole input sequence. In the experiments of a slot filling task, which is an essential component of natural language understanding, with using the standard ATIS corpus, we achieved the state-of-the-art F1-score of 95.66%.