EMNLP Findings2023
Generating Extractive Answers: Gated Recurrent Memory Reader for Conversational Question Answering
Abstract
Conversational question answering (CQA) is a more complicated task than traditional singleturn machine reading comprehension (MRC). Different from large language models (LLMs) like ChatGPT, the models of CQA need to extract answers from given contents to answer follow-up questions according to conversation history. In this paper, we propose a novel architecture, i.e., Gated Recurrent Memory Reader (GRMR), which integrates traditional extractive MRC models into a generalized sequence-to-sequence framework. After the passage is encoded, the decoder will generate the extractive answers turn by turn. Different from previous models that concatenate the previous questions and answers as context superficially and redundantly, our model can use less storage space and consider historical memory deeply and selectively. Experiments on the Conversational Question Answering (CoQA) dataset show that our model achieves comparable results to most models with the least space occupancy.
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
Builds on2
Related papers
- Recurrent Chunking Mechanisms for Long-Text Machine Reading ComprehensionHongyu Gong, Yelong Shen, Dian Yu, Jianshu Chen et al.ACL 2020 · 39 citations
- Conversational Question Answering with Language Models Generated Reformulations over Knowledge GraphLihui Liu, Blaine Hill, Boxin Du, Fei Wang et al.ACL Findings 2024 · 12 citations
- Machine Reading Comprehension using Case-based ReasoningDung Thai, Dhruv Agarwal, Mudit Chaudhary, Wenlong Zhao et al.EMNLP Findings 2023
- monoQA: Multi-Task Learning of Reranking and Answer Extraction for Open-Retrieval Conversational Question AnsweringSarawoot Kongyoung, Craig Macdonald, Iadh OunisEMNLP 2022 · 6 citations
- History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue SystemTong Zhang, Yong Liu, Boyang Li, Zhiwei Zeng et al.EMNLP Findings 2022 · 14 citations
