| Abstract | Several tasks in argumentation mining and debating, question-answering, and natural language inference involve classifying a sequence in the context of another sequence (referred as bi-sequence classification). For several single sequence classification tasks, the current state-of-the-art approaches are based on recurrent and convolutional neural networks. On the other hand, for bi-sequence classification problems, there is not much understanding as to the best deep learning architecture. In this paper, we attempt to get an understanding of this category of problems by extensive empirical evaluation of 19 different deep learning architectures (specifically on different ways of handling context) for various problems originating in natural language processing like debating, textual entailment and question-answering. Following the empirical evaluation, we offer our insights and conclusions regarding the architectures we have considered. We also establish the first deep learning baselines for three argumentation mining tasks. | ||
| Research Area | cs.CL (Computation and | cs.IR (Information | cs.CR (Cryptography and |
| Language) | Retrieval) | Security) | |
| Classification | Accept | Accept | Reject |
| Message | <UNK> christmas and happy holidays from my family to yours. wishing special <UNK> to those first responders and military personnel working to ensure our safety who are unable to be with their families this holiday season. we are all thank you for your service and dedication. | ||
| Political Bias | Neutral | Partisan | |
| Classification | Personal | Support | |
| Abstract | Several tasks in argumentation mining and debating, question-answering, and natural language inference involve classifying a sequence in the context of another sequence (referred as bi-sequence classification). For several single sequence classification tasks, the current state-of-the-art approaches are based on recurrent and convolutional neural networks. On the other hand, for bi-sequence classification problems, there is not much understanding as to the best deep learning architecture. In this paper, we attempt to get an understanding of this category of problems by extensive empirical evaluation of 19 different deep learning architectures (specifically on different ways of handling context) for various problems originating in natural language processing like debating, textual entailment and question-answering. Following the empirical evaluation, we offer our insights and conclusions regarding the architectures we have considered. We also establish the first deep learning baselines for three argumentation mining tasks. | ||
| Research Area | cs.CL (Computation and | cs.IR (Information | cs.CR (Cryptography and |
| Language) | Retrieval) | Security) | |
| Classification | Accept | Accept | Reject |
| Message | <UNK> christmas and happy holidays from my family to yours. wishing special <UNK> to those first responders and military personnel working to ensure our safety who are unable to be with their families this holiday season. we are all thank you for your service and dedication. | ||
| Political Bias | Neutral | Partisan | |
| Classification | Personal | Support | |