Leveraging abstract meaning representation for knowledge base question answering

P Kapanipathi, I Abdelaziz, S Ravishankar… - arxiv preprint arxiv …, 2020 - arxiv.org
Knowledge base question answering (KBQA) is an important task in Natural Language
Processing. Existing approaches face significant challenges including complex question …

MRP 2020: The second shared task on cross-framework and cross-lingual meaning representation parsing

S Oepen, O Abend, L Abzianidze, J Bos… - Proceedings of the …, 2020 - aclanthology.org
Abstract The 2020 Shared Task at the Conference for Computational Language Learning
(CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks and …

Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing

J Zhou, T Naseem, RF Astudillo, YS Lee… - arxiv preprint arxiv …, 2021 - arxiv.org
Predicting linearized Abstract Meaning Representation (AMR) graphs using pre-trained
sequence-to-sequence Transformer models has recently led to large improvements on AMR …

Ensembling graph predictions for amr parsing

TL Hoang, G Picco, Y Hou, YS Lee… - Advances in …, 2021 - proceedings.neurips.cc
In many machine learning tasks, models are trained to predict structure data such as graphs.
For example, in natural language processing, it is very common to parse texts into …

Maximum Bayes Smatch ensemble distillation for AMR parsing

YS Lee, RF Astudillo, TL Hoang, T Naseem… - arxiv preprint arxiv …, 2021 - arxiv.org
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 …

Inducing and using alignments for transition-based AMR parsing

A Drozdov, J Zhou, R Florian, A McCallum… - arxiv preprint arxiv …, 2022 - arxiv.org
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 …

A semantics-aware transformer model of relation linking for knowledge base question answering

T Naseem, S Ravishankar… - Proceedings of the …, 2021 - aclanthology.org
Relation linking is a crucial component of Knowledge Base Question Answering systems.
Existing systems use a wide variety of heuristics, or ensembles of multiple systems, heavily …

Widely interpretable semantic representation: Frameless meaning representation for broader applicability

L Feng, G Williamson, H He, JD Choi - arxiv preprint arxiv:2309.06460, 2023 - arxiv.org
This paper presents a novel semantic representation, WISeR, that overcomes challenges for
Abstract Meaning Representation (AMR). Despite its strengths, AMR is not easily applied to …

Meaning representations for natural languages: Design, models and applications

J Flanigan, I **dal, Y Li, T O'Gorman… - Proceedings of the …, 2022 - aclanthology.org
This tutorial reviews the design of common meaning representations, SoTA models for
predicting meaning representations, and the applications of meaning representations in a …

Sygma: System for generalizable modular question answering overknowledge bases

S Neelam, U Sharma, H Karanam, S Ikbal… - arxiv preprint arxiv …, 2021 - arxiv.org
Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are
emerging as an important re-search direction. However, most KBQA systems struggle …