Large language models (LLMs) show amazing proficiency and fluency in the use of
language. Does this mean that they have also acquired insightful linguistic knowledge about …

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 …

Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word
alignments. These alignments are learned separately from parser training and require a …

At the heart of the Pyramid evaluation method for text summarization lie human written
summary content units (SCUs). These SCUs are concise sentences that decompose a …

Current open-domain neural semantics parsers show impressive performance. However,
closer inspection of the symbolic meaning representations they produce reveals significant …

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 …

Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are
emerging as an important re-search direction. However, most KBQA systems struggle …

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

Semantic representations capture the meaning of a text. Abstract Meaning Representation
(AMR), a type of semantic representation, focuses on predicate-argument structure and …

Text-based reinforcement learning agents have predominantly been neural network-based
models with embeddings-based representation, learning uninterpretable policies that often …