# KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering

arXiv: https://arxiv.org/abs/2305.08347 · HTML: https://mlsanity.com/paper/2305.08347/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 20 of 20)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [CommonsenseQA 2.0: Exposing the Limits of AI through Gamification](https://mlsanity.com/paper/2201.05320/) (2022)
- [Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation](https://mlsanity.com/paper/2204.01171/) (2022)
- [KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning](https://mlsanity.com/paper/2009.12677/) (2020)
- [ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning](https://mlsanity.com/paper/2005.00771/) (2020)
- [Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention](https://mlsanity.com/paper/2112.03254/) (2021)
- [CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues](https://mlsanity.com/paper/2203.13926/) (2022)
- [Careful Selection of Knowledge to solve Open Book Question Answering](https://mlsanity.com/paper/1907.10738/) (2019)
- [Fusing Context Into Knowledge Graph for Commonsense Question Answering](https://mlsanity.com/paper/2012.04808/) (2020)
- [An Enhanced Knowledge Injection Model for Commonsense Generation](https://mlsanity.com/paper/2012.00366/) (2020)
- [Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources](https://mlsanity.com/paper/2011.02705/) (2020)
- [Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models](https://mlsanity.com/paper/2109.02837/) (2021)
- [Joint Generator-Ranker Learning for Natural Language Generation](https://mlsanity.com/paper/2206.13974/) (2022)

## Built on by (most cited first, 2 of 2)

- [Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models](https://mlsanity.com/paper/2311.17502/) (2023)
- [Large Language Models Are Also Good Prototypical Commonsense Reasoners](https://mlsanity.com/paper/2309.13165/) (2023)

## Abstract (arXiv)

Generative commonsense question answering (GenCQA) is a task of automatically generating a list of answers given a question. The answer list is required to cover all reasonable answers. This presents the considerable challenges of producing diverse answers and ranking them properly. Incorporating a variety of closely-related background knowledge into the encoding of questions enables the generation of different answers. Meanwhile, learning to distinguish positive answers from negative ones potentially enhances the probabilistic estimation of plausibility, and accordingly, the plausibility-based ranking. Therefore, we propose a Knowledge Enhancement and Plausibility Ranking (KEPR) approach grounded on the Generate-Then-Rank pipeline architecture. Specifically, we expand questions in terms of Wiktionary commonsense knowledge of keywords, and reformulate them with normalized patterns. Dense passage retrieval is utilized for capturing relevant knowledge, and different PLM-based (BART, GPT2 and T5) networks are used for generating answers. On the other hand, we develop an ELECTRA-based answer ranking model, where logistic regression is conducted during training, with the aim of approximating different levels of plausibility in a polar classification scenario. Extensive experiments on the benchmark ProtoQA show that KEPR obtains substantial improvements, compared to the strong baselines. Within the experimental models, the T5-based GenCQA with KEPR obtains the best performance, which is up to 60.91% at the primary canonical metric Inc@3. It outperforms the existing GenCQA models on the current leaderboard of ProtoQA.