Neural Network Models for Implicit Discourse Relation Classification in English and Chinese without Surface Features
This addresses the problem of discourse parsing for languages lacking semantic lexicons, offering a cross-linguistic solution, though it is incremental as it builds on existing neural architectures.
The authors tackled implicit discourse relation classification in English and Chinese by proposing neural network models without surface features, achieving performance that matches or exceeds systems using hand-crafted features across fine-grained label sets and cross-linguistic settings.
Inferring implicit discourse relations in natural language text is the most difficult subtask in discourse parsing. Surface features achieve good performance, but they are not readily applicable to other languages without semantic lexicons. Previous neural models require parses, surface features, or a small label set to work well. Here, we propose neural network models that are based on feedforward and long-short term memory architecture without any surface features. To our surprise, our best configured feedforward architecture outperforms LSTM-based model in most cases despite thorough tuning. Under various fine-grained label sets and a cross-linguistic setting, our feedforward models perform consistently better or at least just as well as systems that require hand-crafted surface features. Our models present the first neural Chinese discourse parser in the style of Chinese Discourse Treebank, showing that our results hold cross-linguistically.