Papers by Tim French

4 papers
SConE: Simplified Cone Embeddings with Symbolic Operators for Complex Logical Queries (2023.findings-acl)

Copied to clipboard

Challenge: Current geometric-based methods depend on the neural approach to model FOL operators . empirical evidence for explainability is challenging .
Approach: They propose to model conjunction operators using a symbolic modeling approach . they propose to emphasize the essential role of relation projection operator .
Outcome: The proposed method improves answering complex logical queries over previous models.
MaintIE: A Fine-Grained Annotation Schema and Benchmark for Information Extraction from Maintenance Short Texts (2024.lrec-main)

Copied to clipboard

Challenge: Maintenance short texts (MSTs) provide crucial insights into the state and maintenance activities of machines, infrastructure, and other engineered assets.
Approach: They propose a multi-level fine-grained annotation scheme for entity recognition and relation extraction that includes 5 top-level classes and 6 relations tailored to MSTs.
Outcome: The proposed scheme provides high-quality, fine-grained annotations and a coarse-grain corpus of 7,000 texts.
LexiClean: An annotation tool for rapid multi-task lexical normalisation (2021.emnlp-demo)

Copied to clipboard

Challenge: Lexical normalisation is the task of identifying and normalising non-canonical tokens (e.g. erroneous spelling, acronyms, etc.) in noisy, non-standard, corpora.
Approach: They propose to use LexiClean to annotate multiple tasks in noisy corpora using in situ token modification and annotation that can be rapidly applied corpus wide.
Outcome: The proposed tool can be rapidly applied corpus wide and can identify and normalise noisy, non-standard, and domain specific corpora.
CylE: Cylinder Embeddings for Multi-hop Reasoning over Knowledge Graphs (2023.eacl-main)

Copied to clipboard

Challenge: Existing geometric-based models cannot handle the logical negation operation . Existing models using cones embeddings are limited to representing queries by two-dimensional shapes . Empirical results show that the performance of multi-hop reasoning task using CylE significantly increases over state-of-the-art geometric- based models for queries without negation.
Approach: They propose a geometric-based model based on three-dimensional shapes with unbounded cylinder embeddings that can handle a complete set of first-order logic operations.
Outcome: Empirical results show that CylE outperforms state-of-the-art models for queries without negation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations