Papers by Gülşen Eryiğit

8 papers
Towards Automatic Grammatical Error Type Classification for Turkish (2023.eacl-srw)

Copied to clipboard

Challenge: Existing error types are not universal, resulting in many language specific variants.
Approach: They propose to use a rule-based error type classification pipeline to classify edits into predefined error categories for Turkish . they propose to change existing error categories to suit the inflectional and derivational properties of the language .
Outcome: The proposed system is evaluated on 106 annotated sentences and its performance is measured as 77.04% F0.5 score.
Extracting Complex Relations from Banking Documents (D19-51)

Copied to clipboard

Challenge: Existing methods to extract complex relations from banking orders are limited . formal letters, petitions, demands or complaints are still a major communication medium in corporate banking.
Approach: They propose a relation extraction method that extracts intersentential, nested and complex relations from banking orders.
Outcome: The proposed method shows 11% error reduction over previous methods.
Typology-Aware Multilingual Morphosyntactic Parsing with Joint Abstract Node Modeling (2026.acl-long)

Copied to clipboard

Challenge: UniDive 2025 Morphosyntactic Parsing (MSP) shared task unifies dependency structure, morphological features, and unrealized arguments.
Approach: They propose a multilingual, typology-aware joint system that integrates word-type prediction, content-only parsing, morphological tagging, and an abstract-node component within a single architecture.
Outcome: The proposed model outperforms the leading submission by 3.23 percentage points in MSLAS, 3.35 in LAS, and 1.78 in FEATS macro F1.
CorefInst: Leveraging LLMs for Multilingual Coreference Resolution (2026.tacl-1)

Copied to clipboard

Challenge: Existing methods for CR are encoder-only, decoder-based and asynchronous models.
Approach: They propose a multilingual CR methodology which leverages decoder-only LLMs to handle overt and zero mentions.
Outcome: The proposed model outperforms the leading multilingual CR model by 2 percentage points across all languages in the CorefUD v1.2 dataset.
Constructing Multimodal Language Learner Texts Using LARA: Experiences with Nine Languages (2020.lrec-1)

Copied to clipboard

Challenge: LARA is an open source project that aims to support easy conversion of plain texts into online versions suitable for use by language learners.
Approach: They propose to support easy conversion of plain texts into online versions suitable for use by language learners.
Outcome: The proposed platform is suitable for creating texts in multiple languages via crowdsourcing techniques that can be used for teaching a language via reading and listening.
AMR Alignment for Morphologically-rich and Pro-drop Languages (2022.acl-srw)

Copied to clipboard

Challenge: Existing AMR aligners for English are not well suited for many languages where many concepts appear from morphologically-semantic elements.
Approach: They propose to use a tree traversal approach to align AMR concepts from morphemes in a Turkish language.
Outcome: The proposed aligner outperforms the existing aligners for English and Portuguese in terms of precision, recall and F1 score.
Incorporating Dropped Pronouns into Coreference Resolution: The case for Turkish (2023.eacl-srw)

Copied to clipboard

Challenge: PD-MRLs are pro-drop and morphologically rich languages due to dropped pronouns . a representation & evaluation scheme is proposed to incorporate dropped pronomins into coreference resolution .
Approach: They propose a representation & evaluation scheme to incorporate dropped pronouns into coreference resolution and validate it on the Turkish language.
Outcome: The proposed representation & evaluation scheme extends on the Turkish coreference dataset . it includes pre and post processors to enhance the prominent CoNLL coreference scorer .
Towards Turkish Abstract Meaning Representation (P19-2)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) abstracts away from syntactic features such as word order and does not annotate every constituent in a sentence.
Approach: They have built a first Turkish AMR corpus by hand-annotating 100 sentences from the novel "The Little Prince" they will use the results to prepare a Turkish AML annotation specification for future annotators.
Outcome: The results of the study compare Turkish AMRs with English AMR annotations . the proposed framework is expected to be used in training future annotators.

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