FlowQA: Grasping Flow in History for Conversational Machine Comprehension

By Hsin-Yuan Huang, Eunsol Choi, Wen-tau Yih. 2018

102 citations recorded by the source corpus.

Conversational machine comprehension requires the understanding of the conversation history, such as previous question/answer pairs, the document context, and the current question. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a mechanism that can incorporate intermediate representations generated during the process of answering previous questions, through an alternating parallel processing structure. Compared to approaches that concatenate previous questions/answers as input, Flow integrates the latent semantics of the conversation history more deeply. Our model, FlowQA, shows superior performance on two recently proposed conversational challenges (+7.2% F1 on CoQA and +4.0% on QuAC). The effectiveness of Flow also shows in other tasks. By reducing sequential instruction understanding to conversational machine comprehension, FlowQA outperforms the best models on all three domains in SCONE, with +1.8% to +4.4% improvement in accuracy.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Technical report on Conversational Question Answering (2019, methodology): “FlowQA proposed an alternating parallel processing structure and incorporated intermediate representations generated during the process of answering previous questions.”
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge (2019, methodology): “We augment B I DAF (Seo et al., 2016) with a self-attention layer and ELMo representations (Peters et al., 2018; Huang et al., 2018).”
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions (2019, background): “…approaches achieve promising results (Dong and Lapata, 2016; Su and Yan, 2017; Iyer et al., 2017; Xu et al., 2017; Finegan-Dollak et al., 2018; Yu et al., 2018a; Huang et al., 2018; Dong and Lapata, 2018; Sun et al., 2018; Gur et al., 2018; Guo et al., 2018; Yavuz et al., 2018; Shi et al., 2018).”
Can You Unpack That? Learning to Rewrite Questions-in-Context (2019, methodology): “, 2018), sequential neural models (Huang et al., 2019), and transformers (Qu et al.”
Large Language Models: A Survey (2024, unknown): “Human equivalence score (HEQ) on the other hand, is an alternative to F1 score [203].”