Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering

By Pratyay Banerjee, Chitta Baral. 2020

24 citations recorded by the source corpus.

Open Domain Question Answering requires systems to retrieve external knowledge and perform multi-hop reasoning by composing knowledge spread over multiple sentences. In the recently introduced open domain question answering challenge datasets, QASC and OpenBookQA, we need to perform retrieval of facts and compose facts to correctly answer questions. In our work, we learn a semantic knowledge ranking model to re-rank knowledge retrieved through Lucene based information retrieval systems. We further propose a "knowledge fusion model" which leverages knowledge in BERT-based language models with externally retrieved knowledge and improves the knowledge understanding of the BERT-based language models. On both OpenBookQA and QASC datasets, the knowledge fusion model with semantically re-ranked knowledge outperforms previous attempts.

Subfields: Artificial Intelligence, Information Retrieval & Search, Question Answering & Reading Comprehension, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yang Deng
2. Wai Lam
3. Deng Cai
4. Huihui Zhang
5. Weiwen Xu
6. Jiawei Han

In Information Retrieval & Search

1. Wai Lam
2. Yang Deng
3. Deng Cai

In Question Answering & Reading Comprehension

1. Deng Cai

Citations in the corpus

• UnifiedQA: Crossing Format Boundaries With a Single QA System (2020, neutral): “, 2019c) (on OBQA and ARC), KF+SIR (Banerjee and Baral, 2020) (on OBQA and QASC), FreeLB+RoBERTa (Zhu et al.”
• Exploiting Reasoning Chains for Multi-hop Science Question Answering (2021, methodology): “Comparison Methods: For fair comparison, we compare CGR with recently published methods that use similar power of pretrained models, including five textual knowledge based methods: AristoRoBERTa (AllenAI, 2019), KF-SIR (Banerjee and Baral, 2020), FreeLB (Zhu et al., 2020), DPR (Karpukhin et al., 202”
• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering (2021, unknown): “Methods Test Careful Selection (Banerjee et al., 2019) 72.0 AristoRoBERTa 77.8 KF + SIR (Banerjee and Baral, 2020) 80.0 AristoRoBERTa + PG (Wang et al., 2020b) 80.2 AristoRoBERTa + MHGRN (Feng et al., 2020) 80.6 Albert + KB 81.0 T5* (Raffel et al., 2020) 83.2 UnifiedQA* (Khashabi et al., 2020)…”