Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment classification task.
Many recent works have used dependency trees to extract the relation between aspects and …

Automatic evaluation metrics are essential for the rapid development of open-domain
dialogue systems as they facilitate hyper-parameter tuning and comparison between …

Minimum Bayes Risk (MBR) decoding is a method for choosing the outputs of a machine
learning system based not on the output with the highest probability, but the output with the …

AMR parsing has experienced an unprecendented increase in performance in the last three
years, due to a mixture of effects including architecture improvements and transfer learning …

Effective multi-hop question answering (QA) requires reasoning over multiple scattered
paragraphs and providing explanations for answers. Most existing approaches cannot …

The Smatch metric is a popular method for evaluating graph distances, as is necessary, for
instance, to assess the performance of semantic graph parsing systems. However, we …

Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a
semantic graph abstraction representing a given text. Current approaches are based on …

This tutorial reviews the design of common meaning representations, SoTA models for
predicting meaning representations, and the applications of meaning representations in a …

In this paper, we examine the current state-of-the-art in AMR parsing, which relies on
ensemble strategies by merging multiple graph predictions. Our analysis reveals that the …

Instruction fine-tuned language models on a collection of instruction annotated datasets
(FLAN) have shown highly effective to improve model performance and generalization to …