AMR-based network for aspect-based sentiment analysis
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 …
Many recent works have used dependency trees to extract the relation between aspects and …
DEAM: Dialogue coherence evaluation using AMR-based semantic manipulations
Automatic evaluation metrics are essential for the rapid development of open-domain
dialogue systems as they facilitate hyper-parameter tuning and comparison between …
dialogue systems as they facilitate hyper-parameter tuning and comparison between …
It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk
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 …
learning system based not on the output with the highest probability, but the output with the …
Maximum Bayes Smatch ensemble distillation for AMR parsing
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 …
years, due to a mixture of effects including architecture improvements and transfer learning …
Interpretable AMR-based question decomposition for multi-hop question answering
Effective multi-hop question answering (QA) requires reasoning over multiple scattered
paragraphs and providing explanations for answers. Most existing approaches cannot …
paragraphs and providing explanations for answers. Most existing approaches cannot …
SMATCH++: Standardized and extended evaluation of semantic graphs
J Opitz - arXiv preprint arXiv:2305.06993, 2023 - arxiv.org
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 …
instance, to assess the performance of semantic graph parsing systems. However, we …
Incorporating graph information in transformer-based AMR parsing
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 …
semantic graph abstraction representing a given text. Current approaches are based on …
Meaning representations for natural languages: Design, models and applications
This tutorial reviews the design of common meaning representations, SoTA models for
predicting meaning representations, and the applications of meaning representations in a …
predicting meaning representations, and the applications of meaning representations in a …
AMRs assemble! learning to ensemble with autoregressive models for AMR parsing
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 …
ensemble strategies by merging multiple graph predictions. Our analysis reveals that the …
Amr parsing with instruction fine-tuned pre-trained language models
Instruction fine-tuned language models on a collection of instruction annotated datasets
(FLAN) have shown highly effective to improve model performance and generalization to …
(FLAN) have shown highly effective to improve model performance and generalization to …