Non Pre-Trained Models

AbstractMany recent studies have shown that for models trained on datasets for natural language inference (NLI), it is possible to make correct predictions by merely looking at the hypothesis while …...

AbstractCurrent dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are …...

AbstractMuch research has reported the training data of summarization models are noisy; summaries often do not reflect what is written in the source texts. We propose an effective method of …...