# How to Build Robust FAQ Chatbot with Controllable Question Generator?

arXiv: https://arxiv.org/abs/2112.03007 · HTML: https://mlsanity.com/paper/2112.03007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 18 Nov 2021.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Multilingual Universal Sentence Encoder for Semantic Retrieval](https://mlsanity.com/paper/1907.04307/) (2019)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Deep Text Classification Can be Fooled](https://mlsanity.com/paper/1704.08006/) (2017)
- [Neural Question Generation from Text: A Preliminary Study](https://mlsanity.com/paper/1704.01792/) (2017)
- [MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension](https://mlsanity.com/paper/1905.13453/) (2019)
- [Generating Natural Questions About an Image](https://mlsanity.com/paper/1603.06059/) (2016)
- [Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia](https://mlsanity.com/paper/1805.05942/) (2018)
- [A Controllable Model of Grounded Response Generation](https://mlsanity.com/paper/2005.00613/) (2020)
- [Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model](https://mlsanity.com/paper/1810.12836/) (2018)
- [What do Models Learn from Question Answering Datasets?](https://mlsanity.com/paper/2004.03490/) (2020)
- [Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus](https://mlsanity.com/paper/2002.00748/) (2020)
- [Question Answering and Question Generation as Dual Tasks](https://mlsanity.com/paper/1706.02027/) (2017)
- [Improving Neural Question Generation using Answer Separation](https://mlsanity.com/paper/1809.02393/) (2018)
- [A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC](https://mlsanity.com/paper/1809.10735/) (2018)
- [Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds](https://mlsanity.com/paper/1911.02365/) (2019)
- [Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types](https://mlsanity.com/paper/1802.06842/) (2018)
- [Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation](https://mlsanity.com/paper/2004.03238/) (2020)
- [QnAMaker: Data to Bot in 2 Minutes](https://mlsanity.com/paper/2003.08553/) (2020)

## Abstract (arXiv)

Many unanswerable adversarial questions fool the question-answer (QA) system with some plausible answers. Building a robust, frequently asked questions (FAQ) chatbot needs a large amount of diverse adversarial examples. Recent question generation methods are ineffective at generating many high-quality and diverse adversarial question-answer pairs from unstructured text. We propose the diversity controllable semantically valid adversarial attacker (DCSA), a high-quality, diverse, controllable method to generate standard and adversarial samples with a semantic graph. The fluent and semantically generated QA pairs fool our passage retrieval model successfully. After that, we conduct a study on the robustness and generalization of the QA model with generated QA pairs among different domains. We find that the generated data set improves the generalizability of the QA model to the new target domain and the robustness of the QA model to detect unanswerable adversarial questions.