Papers by Vijini Liyanage

2 papers
Multi-lingual Mathematical Word Problem Generation using Long Short Term Memory Networks with Enhanced Input Features (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods for multi-lingual MWP generation are incapable of identifying language specific constraints, especially in morphologically rich yet low resource languages such as Sinhala and Tamil.
Approach: They propose to use a long-term memory network to generate elementary level MWPs by adding character embeddings, word embedds and Part of Speech (POS) tag embeddements to the network.
Outcome: The proposed model generates elementary level MWPs while satisfying language specific constraints while providing attention for numerical values and units.
A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications (2022.lrec-1)

Copied to clipboard

Challenge: Automated text generation has achieved performance levels that make the generated text almost indistinguishable from those written by humans.
Approach: They propose to use a completely synthetic dataset and a partial text substitution dataset to evaluate the quality of the generated research content.
Outcome: The proposed datasets compare the generated texts to aligned original texts using fluency metrics such as BLEU and ROUGE.

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