# Improving the Question Answering Quality using Answer Candidate Filtering based on Natural-Language Features

arXiv: https://arxiv.org/abs/2112.05452 · HTML: https://mlsanity.com/paper/2112.05452/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 10 Dec 2021.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [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)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [Read + Verify: Machine Reading Comprehension with Unanswerable Questions](https://mlsanity.com/paper/1808.05759/) (2018)
- [Towards a Question Answering System over the Semantic Web](https://mlsanity.com/paper/1803.00832/) (2018)
- [RuBQ: A Russian Dataset for Question Answering over Wikidata](https://mlsanity.com/paper/2005.10659/) (2020)
- [ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation](https://mlsanity.com/paper/2103.07771/) (2021)
- [SemEval-2015 Task 3: Answer Selection in Community Question Answering](https://mlsanity.com/paper/1911.11403/) (2019)
- [A Holistic Natural Language Generation Framework for the Semantic Web](https://mlsanity.com/paper/1911.01248/) (2019)
- [VANiLLa : Verbalized Answers in Natural Language at Large Scale](https://mlsanity.com/paper/2105.11407/) (2021)

## Abstract (arXiv)

Software with natural-language user interfaces has an ever-increasing importance. However, the quality of the included Question Answering (QA) functionality is still not sufficient regarding the number of questions that are answered correctly. In our work, we address the research problem of how the QA quality of a given system can be improved just by evaluating the natural-language input (i.e., the user's question) and output (i.e., the system's answer). Our main contribution is an approach capable of identifying wrong answers provided by a QA system. Hence, filtering incorrect answers from a list of answer candidates is leading to a highly improved QA quality. In particular, our approach has shown its potential while removing in many cases the majority of incorrect answers, which increases the QA quality significantly in comparison to the non-filtered output of a system.