EMNLP Findings2021
Winnowing Knowledge for Multi-choice Question Answering
Yeqiu Li, Bowei Zou, Zhifeng Li, Ai Ti Aw, Yu Hong, Qiaoming Zhu
Abstract
We tackle multi-choice question answering. Acquiring related commonsense knowledge to the question and options facilitates the recognition of the correct answer. However, the current reasoning models suffer from the noises in the retrieved knowledge. In this paper, we propose a novel encoding method which is able to conduct interception and soft filtering. This contributes to the harvesting and absorption of representative information with less interference from noises. We experiment on Com-monsenseQA. Experimental results illustrate that our method yields substantial and consistent improvements compared to the strong Bert, RoBERTa and Albert-based baselines. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation cites Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
- Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering cites FreeLB: Enhanced Adversarial Training for Natural Language Understanding
- Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering cites Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
- Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering cites UnifiedQA: Crossing Format Boundaries With a Single QA System
- UnifiedQA: Crossing Format Boundaries With a Single QA System cites FreeLB: Enhanced Adversarial Training for Natural Language Understanding
Builds on5
- UnifiedQA: Crossing Format Boundaries With a Single QA SystemDaniel Khashabi, Sewon Min, Tushar Khot, Ashish Sabharwal et al.EMNLP Findings 2020 · 514 citations
- FreeLB: Enhanced Adversarial Training for Natural Language UnderstandingChen Zhu, Yu Cheng, Zhe Gan, Siqi Sun et al.ICLR 2020 · 502 citations
- Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question AnsweringShangwen Lv, Daya Guo, Jingjing Xu, Duyu Tang et al.AAAI 2020 · 224 citations
- Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question AnsweringPeifeng Wang, Nanyun Peng, Filip Ilievski, Pedro A. Szekely et al.EMNLP Findings 2020 · 69 citations
- Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text TransformationNing Bian, Xianpei Han, Bo Chen, Le SunAAAI 2021 · 49 citations
Related papers
- LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense ReasoningJiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin et al.EMNLP Findings 2024 · 12 citations
- MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense ReasoningYongfeng Huang, Yanyang Li, Yichong Xu, Lin Zhang et al.ACL 2023 · 13 citations
- MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge RepresentationYing Su, Zihao Wang, Tianqing Fang, Hongming Zhang et al.EMNLP Findings 2022 · 13 citations
- ACENet: Attention Guided Commonsense Reasoning on Hybrid Knowledge GraphChuzhan Hao, Minghui Xie, Peng ZhangEMNLP 2022 · 5 citations
- Social Commonsense Reasoning with Multi-Head Knowledge AttentionDebjit Paul, Anette FrankEMNLP Findings 2020 · 16 citations
