Papers with multitask learning architecture
Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models (2020.coling-main)
Copied to clipboard
| Challenge: | a novel character-level sequence-to-sequence lemmatization model uses generic n-gram embeddings to map word/lemma pairs . semitic languages, like Arabic and Hebrew, add other challenges to handle unseen words . |
| Approach: | They propose a character-level sequence-to-sequence lemmatization model . they use generic n-gram embeddings, concatenative (stems) and templatic (roots and patterns) morphological subwords. |
| Outcome: | The proposed model outperforms other linguistically-driven models with generic n-gram embeddings . the best system handles word/lemma pairs that are both unseen in the training data . |
Training a Swedish Constituency Parser on Six Incompatible Treebanks (2020.lrec-1)
Copied to clipboard
| Challenge: | Syntactic parsing is a widely used intermediate step in several natural language processing tasks. |
| Approach: | They propose to use a function-tagged constituent treebank for Swedish which includes discontinuous constituents to improve the accuracy. |
| Outcome: | The proposed parser can be trained on additional treebanks that use other annotation models. |