Papers by Jana Straková

4 papers
OOVs in the Spotlight: How to Inflect Them? (2024.lrec-main)

Copied to clipboard

Challenge: Inflection is a process of word formation in which a base word form (lemma) is modified to express grammatical categories.
Approach: They develop a retrograde model and two sequence-to-sequence models based on LSTM and Transformer.
Outcome: The proposed systems outperform the existing systems on 9 out of 16 languages in the OOV evaluation.
Neural Architectures for Nested NER through Linearization (P19-1)

Copied to clipboard

Challenge: a nested named entity recognition (NER) is a set of entities that can overlap and be labeled with more than one label.
Approach: They propose two neural network architectures for nested named entity recognition . they propose to model nesting entities as multilabels and predict a sequence-to-sequence problem .
Outcome: The proposed methods outperform the state-of-the-art on four corpora . the proposed models also improve on the recently published contextual embeddings .
NameTag 3: A Tool and a Service for Multilingual/Multitagset NER (2025.acl-demo)

Copied to clipboard

Challenge: NameTag 3 is an open-source tool and cloud-based web service for named entity recognition.
Approach: NameTag 3 is an open-source tool and cloud-based web service for named entity recognition.
Outcome: NameTag 3 achieves state-of-the-art on 21 test datasets in 15 languages . available as command-line tool and as cloud-based service, enabling use without local installation .
Czech Grammar Error Correction with a Large and Diverse Corpus (2022.tacl-1)

Copied to clipboard

Challenge: a large and diverse corpus of Czech grammar error correction corpora is available for other languages . despite efforts to mitigate the notorious shortage of national GEC-annotated corpors, the lack of adequate data is even more acute in languages other than English.
Approach: They propose to annotate a large and diverse Czech corpus for grammar error correction . they compare several Czech GEC systems and meta-evaluate common GEC metrics against human judgments on data.
Outcome: The proposed corpus is annotated for grammar error correction (GEC) in Czech.

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