Abstract
Multihop question answering has attracted extensive studies in recent years because of the emergence of human annotated datasets and associated leaderboards. Recent studies have revealed that question answering systems learn to exploit annotation artifacts and other biases in current datasets. Therefore, a model with strong interpretability should not only predict the final answer, but more importantly find the supporting facts’ sentences necessary to answer complex questions, also known as evidence sentences. Most existing methods predict the final answer and evidence sentences in sequence or simultaneously, which inhibits the ability of models to predict the path of reasoning. In this paper, we propose a dual-channel reasoning architecture, where two reasoning channels predict the final answer and supporting facts’ sentences, respectively, while sharing the contextual embedding layer. The two reasoning channels can simply use the same reasoning structure without additional network designs. Through experimental analysis based on public question answering datasets, we demonstrate the effectiveness of our proposed method
Highlights
One of the long-standing goals of natural language processing (NLP) is to enable machines to have the ability to understand natural language and make inferences in textual data
There are a lot of complex questions that need to be answered through multiple steps of reasoning by aggregating information distributed in multiple paragraphs, named multihop QA [12]
Our contributions can be summarized as follows: (1) We propose the dual-channel reasoning architecture, which is a novel architecture for the complex question answering task. e results of the experiment show that the dual-channel reasoning architecture is suitable for many kinds of existing neural network models, such as graph-based models
Summary
One of the long-standing goals of natural language processing (NLP) is to enable machines to have the ability to understand natural language and make inferences in textual data. There are a lot of complex questions that need to be answered through multiple steps of reasoning by aggregating information distributed in multiple paragraphs, named multihop QA [12]. E first sentence of P6 and P2 are evidence sentences, which lead to the next-hop paragraph and the predicted answer, respectively We propose a novel dual-channel reasoning architecture for complex question answering. (1) We propose the dual-channel reasoning architecture, which is a novel architecture for the complex question answering task. We conducted a detailed visual analysis of the baseline model and two channels in the dual-channel architecture and further explored the differences in the distribution of attention heat maps of several models
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
