Papers by Kairit Sirts
Enhancing Sequence-to-Sequence Neural Lemmatization with External Resources (2021.eacl-main)
Copied to clipboard
| Challenge: | a hybrid approach to lemmatization enhances the seq2seq neural model with additional lemmas extracted from an external lexicon or a rule-based system. |
| Approach: | They propose a hybrid approach that enhances a seq2seq neural model with additional lemmas extracted from an external lexicon or a rule-based system. |
| Outcome: | The proposed model achieves statistically significant improvements on 23 UD languages, compared to baseline models not utilizing additional lemma information. |
On Narrative Question Answering Skills (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing task-level skill views oversimplify multidimensional nature of tasks, while question-level taxonomies face issues in evaluation and methodology. |
| Approach: | a new skill taxonomy synthesizes and redefines narrative understanding skills from previous taxonomies . the new taxomy includes a generation skill dimension from the answering perspective . |
| Outcome: | a new skill taxonomy synthesizes and redefines narrative understanding skills from previous taxonomies and includes a generation skill dimension from the answering perspective. |
Sõnajaht: Definition Embeddings and Semantic Search for Reverse Dictionary Creation (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing systems that use exact term matching to find words are based on information retrieval. |
| Approach: | They propose to use pre-trained language models and approximate nearest neighbors search algorithms to enhance and enrich an Estonian lexicon resource by introducing cross-lingual reverse dictionary functionality powered by semantic search. |
| Outcome: | The proposed system produces a 1 and 2 routs in the monolingual and cross-lingual settings using the unlabeled evaluation approach. |