English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Conversational machine comprehension (CMC) requires understanding the contextof multi-turn dialogue. Using BERT, a pre-training language model, has beensuccessful for single-turn machine comprehension, while modeling multiple turnsof question answering with BERT has not been established because BERT has alimit on the number and the length of input sequences. In this paper, wepropose a simple but effective method with BERT for CMC. Our method uses BERTto encode a paragraph independently conditioned with each question and eachanswer in a multi-turn context. Then, the method predicts an answer on thebasis of the paragraph representations encoded with BERT. The experiments withrepresentative CMC datasets, QuAC and CoQA, show that our method outperformedrecently published methods (+0.8 F1 on QuAC and +2.1 F1 on CoQA). In addition,we conducted a detailed analysis of the effects of the number and types ofdialogue history on the accuracy of CMC, and we found that the gold answerhistory, which may not be given in an actual conversation, contributed to themodel performance most on both datasets.

A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension