Careful Selection of Knowledge to Solve Open Book Question Answering

By Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra, Chitta Baral. 2019

74 citations recorded by the source corpus.

Open book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such QA, OpenBookQA, has been proposed. Unlike most other NLQA that focus on linguistic understanding, OpenBookQA requires deeper reasoning involving linguistic understanding as well as reasoning with common knowledge. In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

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. Chitta Baral
2. Pratyay Banerjee
3. Swaroop Mishra
4. Tat-seng Chua
5. Deng Cai
6. Steven Bethard
7. Man Luo
8. Yang Deng

In Information Systems

1. Chitta Baral
2. Pratyay Banerjee
3. Wenqiang Lei
4. Steven Bethard
5. Tat-seng Chua
6. Wai Lam
7. Man Luo
8. Deng Cai

In Natural Language Processing

1. Chitta Baral
2. Pratyay Banerjee
3. Swaroop Mishra
4. Arindam Mitra
5. Steven Bethard
6. Man Luo
7. Deng Cai
8. Mihai Surdeanu

Citations in the corpus

• Explainable Multi-hop Verbal Reasoning Through Internal Monologue (2021, methodology): “, 2019) have been successfully used in multi-hop reasoning problems (Banerjee et al., 2020; Asai et al., 2019; Yadav et al., 2019).”
• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering (2021, background): “In the past few yeas, this module has been explored with much interest [27], [32], [33], [78], [94], [95].”
• Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks (2020, methodology): “Noting that this model does not take into account external knowledge, we created an new enhanced architecture that first uses knowledge hunting (searching for the missing knowledge) [ Banerjee et al. , 2019; Mitra et al. , 2019 ] with respect to a cheat sheet to identify the needed knowledge.”
• Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering (2020, methodology): “The current systems (Devlin et al., 2019; Liu et al., 2019; Banerjee et al., 2019; Khot et al., 2019a) use the following way of defining the input to the BERT-based models.”
• How Additional Knowledge can Improve Natural Language Commonsense Question Answering (2019, methodology): “Re-Ranking: We perform Information Gain based Re-ranking using Spacy as described in (Banerjee et al., 2019).”
• Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering (2021, methodology): “The advanced reading comprehension model (Chen et al., 2017a; Banerjee et al., 2019) split this complex task into two steps: a retriever selects some most relevant documents from a corpus to a question, and a reader produces answer according to the documents from retriever.”
• Exploiting Reasoning Chains for Multi-hop Science Question Answering (2021, background): “Banerjee et al. (2019); Yadav et al. (2020) reformulate their queries with unused words in the last iteration.”
• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering (2021, unknown): “Careful Selection (Banerjee et al., 2019) 72.”