Compositional generalization in multilingual semantic parsing over Wikidata
Semantic parsing (SP) allows humans to leverage vast knowledge resources through
natural interaction. However, parsers are mostly designed for and evaluated on English …
natural interaction. However, parsers are mostly designed for and evaluated on English …
Rule-based semantic interpretation for Universal Dependencies
JY Findlay, S Salimifar, A Yıldırım… - Proceedings of the Sixth …, 2023 - aclanthology.org
In this paper, we present a system for generating semantic representations from Universal
Dependencies syntactic parses. The foundation of our pipeline is a rule-based interpretation …
Dependencies syntactic parses. The foundation of our pipeline is a rule-based interpretation …
[PDF][PDF] An Ontology based Task Oriented Dialogue.
An ontology based task oriented dialogue as an interface to an user developing applications
using natural language instructions is presented. The dialogue system represents the …
using natural language instructions is presented. The dialogue system represents the …
The long and the short of it: DRASTIC, a semantically annotated dataset containing sentences of more natural length
This paper presents a new dataset with Discourse Representation Structures (DRSs)
annotated over naturally-occurring sentences. Importantly, these sentences are more varied …
annotated over naturally-occurring sentences. Importantly, these sentences are more varied …
An ontology-based task-oriented dialogue to create outsystems applications
An ontology-based task-oriented dialogue is presented as an interface for a user developing
applications in the OutSystems environment, using natural language instructions. The …
applications in the OutSystems environment, using natural language instructions. The …
Experiments in training transformer sequence-to-sequence DRS parsers
A Yıldırım, D Haug - … of the 15th International Conference on …, 2023 - aclanthology.org
This work experiments with various configurations of transformer-based sequence-to-
sequence neural networks in training a Discourse Representation Structure (DRS) parser …
sequence neural networks in training a Discourse Representation Structure (DRS) parser …
MACT: Model-Agnostic Cross-Lingual Training for Discourse Representation Structure Parsing
J Liu - arXiv preprint arXiv:2406.01052, 2024 - arxiv.org
Discourse Representation Structure (DRS) is an innovative semantic representation
designed to capture the meaning of texts with arbitrary lengths across languages. The …
designed to capture the meaning of texts with arbitrary lengths across languages. The …
Improving DRS Parsing with Separately Predicted Semantic Roles
Abstract This paper addresses Semantic Role Labeling (SRL) within the context of English
Discourse Representation Structure (DRS) parsing. In particular, we investigate whether …
Discourse Representation Structure (DRS) parsing. In particular, we investigate whether …
Similarity between Units of Natural Language: The Transition from Coarse to Fine Estimation
W Mu - arXiv preprint arXiv:2210.14275, 2022 - arxiv.org
Capturing the similarities between human language units is crucial for explaining how
humans associate different objects, and therefore its computation has received extensive …
humans associate different objects, and therefore its computation has received extensive …
Model-Agnostic Cross-Lingual Training for Discourse Representation Structure Parsing
J Liu - Proceedings of the 2024 Joint International Conference …, 2024 - aclanthology.org
Abstract Discourse Representation Structure (DRS) is an innovative semantic representation
designed to capture the meaning of texts with arbitrary lengths across languages. The …
designed to capture the meaning of texts with arbitrary lengths across languages. The …