# Improved and Efficient Conversational Slot Labeling through Question Answering

arXiv: https://arxiv.org/abs/2204.02123 · HTML: https://mlsanity.com/paper/2204.02123/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 5 Apr 2022.

## Builds on (most cited first, 30 of 40)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [BERT for Joint Intent Classification and Slot Filling](https://mlsanity.com/paper/1902.10909/) (2019)
- [MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension](https://mlsanity.com/paper/1910.09753/) (2019)
- [TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking](https://mlsanity.com/paper/2005.02877/) (2020)
- [DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue](https://mlsanity.com/paper/2009.13570/) (2020)
- [Retrospective Reader for Machine Reading Comprehension](https://mlsanity.com/paper/2001.09694/) (2020)
- [Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network](https://mlsanity.com/paper/2006.05702/) (2020)
- [Dialog State Tracking: A Neural Reading Comprehension Approach](https://mlsanity.com/paper/1908.01946/) (2019)
- [Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey](https://mlsanity.com/paper/2011.00564/) (2020)
- [Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations](https://mlsanity.com/paper/2005.08866/) (2020)
- [Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2008.06239/) (2020)

## Built on by (most cited first, 10 of 10)

- [gTBLS: Generating Tables from Text by Conditional Question Answering](https://mlsanity.com/paper/2403.14457/) (2024)
- [Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?](https://mlsanity.com/paper/2403.01929/) (2024)
- [NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue](https://mlsanity.com/paper/2204.13021/) (2022)
- [ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler](https://mlsanity.com/paper/2403.17536/) (2024)
- [Transfer-Free Data-Efficient Multilingual Slot Labeling](https://mlsanity.com/paper/2305.13528/) (2023)
- [TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities](https://mlsanity.com/paper/2407.21693/) (2024)
- [A Unified Framework for Multi-intent Spoken Language Understanding with prompting](https://mlsanity.com/paper/2210.03337/) (2022)
- [Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data](https://mlsanity.com/paper/2307.01764/) (2023)
- [Speech-based Slot Filling using Large Language Models](https://mlsanity.com/paper/2311.07418/) (2023)
- [SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU](https://mlsanity.com/paper/2311.09502/) (2023)

## Abstract (arXiv)

Transformer-based pretrained language models (PLMs) offer unmatched performance across the majority of natural language understanding (NLU) tasks, including a body of question answering (QA) tasks. We hypothesize that improvements in QA methodology can also be directly exploited in dialog NLU; however, dialog tasks must be textitreformatted into QA tasks. In particular, we focus on modeling and studying textitslot labeling (SL), a crucial component of NLU for dialog, through the QA optics, aiming to improve both its performance and efficiency, and make it more effective and resilient to working with limited task data. To this end, we make a series of contributions: 1) We demonstrate how QA-tuned PLMs can be applied to the SL task, reaching new state-of-the-art performance, with large gains especially pronounced in such low-data regimes. 2) We propose to leverage contextual information, required to tackle ambiguous values, simply through natural language. 3) Efficiency and compactness of QA-oriented fine-tuning are boosted through the use of lightweight yet effective adapter modules. 4) Trading-off some of the quality of QA datasets for their size, we experiment with larger automatically generated QA datasets for QA-tuning, arriving at even higher performance. Finally, our analysis suggests that our novel QA-based slot labeling models, supported by the PLMs, reach a performance ceiling in high-data regimes, calling for more challenging and more nuanced benchmarks in future work.