Papers by Özlem Çetinoğlu
CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing (L18-1)
Copied to clipboard
Amir More, Özlem Çetinoğlu, Çağrı Çöltekin, Nizar Habash, Benoît Sagot, Djamé Seddah, Dima Taji, Reut Tsarfaty
| Challenge: | Using the universal dependencies framework, we address the need for a universal representation of morphological analysis that can capture alternative morphology of surface tokens and is compatible with the segmentation and morphologic annotation guidelines prescribed for UD treebanks. |
| Approach: | They propose a new annotation format for word lattices that represent morphological analyses and a resource that obeys this format for a range of typologically different languages. |
| Outcome: | The proposed model can capture alternative morphological analyses of surface tokens and is compatible with the segmentation and morphology guidelines prescribed for UD treebanks. |
Lexical Normalization for Code-switched Data and its Effect on POS Tagging (2021.eacl-main)
Copied to clipboard
| Challenge: | Social media data can be used to improve natural language processing performance, but it is often overlooked by lexical normalization systems. |
| Approach: | They propose three lexical normalization models specifically designed to handle code-switched data and evaluate their performance on POS tags. |
| Outcome: | The proposed models outperform monolingual models and lead to 5.4% performance increase for POS tagging compared to unnormalized input. |
Subword-Level Language Identification for Intra-Word Code-Switching (N19-1)
Copied to clipboard
| Challenge: | Code-switching (CS) is a phenomenon of alternating between two or more languages in conversations . if at least one language is morphologically rich, a large number of words can be composed of morphemes from more than one language. |
| Approach: | They propose to extend the language identification task to the subword level by splitting mixed words while tagging each part with a language ID. |
| Outcome: | The proposed model outperforms the baseline on a Spanish–Wixarika and adapted German–Turkish datasets. |
Tackling the Low-resource Challenge for Canonical Segmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | morphological segmentation is a task of dividing words into their constituting morphemes . we compare two new approaches for the task when training data is limited . |
| Approach: | They propose to use an LSTM pointer-generator and a sequence-to-sequence model to perform canonical segmentation when training data is limited. |
| Outcome: | The proposed models outperform existing models on German, English, and Indonesian in low-resource scenarios by 11.4% accuracy. |
Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks (2022.findings-naacl)
Copied to clipboard
| Challenge: | Code-switching dependency parsing is a challenging task due to the scarcity of necessary resources and structural difficulties embedded in code-switch languages. |
| Approach: | They propose to use sequence labeling models as auxiliary tasks for code-switched dependency parsing in a semi-supervised scheme and acquire state-of-the-art scores on all studied languages. |
| Outcome: | The proposed model outperforms the previous model by 7.4 LAS points on average on all of the studied languages. |
Cairo Student Code-Switch (CSCS) Corpus: An Annotated Egyptian Arabic-English Corpus (2020.lrec-1)
Copied to clipboard
| Challenge: | Code-switching is a phenomenon commonly observed in the Arabicspeaking world . there is still a huge gap in the available resources and NLP applications . |
| Approach: | They propose a corpus of Egyptian- Arabic code-switch speech data that is fully tokenized, lemmatized and annotated for part-of-speech tags. |
| Outcome: | The proposed corpus of Egyptian- Arabic code-switch speech data is fully tokenized, lemmatized and annotated for part-of-speech tags. |
Anonymising the SAGT Speech Corpus and Treebank (2022.lrec-1)
Copied to clipboard
| Challenge: | Anonymisation is crucial for dataset creation, authors say . sensitive references can be direct or indirect, but data must be kept as intact . |
| Approach: | They describe the anonymisation process of a Turkish-German code-switching corpus . they used a selective pseudonymisation approach to manually identify sensitive references . |
| Outcome: | The proposed method identifies and neutralises sensitive references and replaces them with surrogate values on the treebank side. |
Treebanking User-Generated Content: A Proposal for a Unified Representation in Universal Dependencies (2020.lrec-1)
Copied to clipboard
Manuela Sanguinetti, Cristina Bosco, Lauren Cassidy, Özlem Çetinoğlu, Alessandra Teresa Cignarella, Teresa Lynn, Ines Rehbein, Josef Ruppenhofer, Djamé Seddah, Amir Zeldes
| Challenge: | Despite the increasing number of contributions on Part-of-Speech tagging and parsing, automatic processing of user-generated content (UGC) still represents a challenging task. |
| Approach: | They propose a set of guidelines for the annotation of user-generated texts within the Universal Dependencies framework. |
| Outcome: | The proposed annotation guidelines promote cross-linguistic consistency, which has always been in the spirit of UD. |