prof. dr. Els Lefever
- ORCID iD
- 0000-0002-7755-0591
Show
Sort by
-
- Journal Article
- A2
- open access
Benchmarking zero-shot text classification for Dutch
-
At the Crossroad of Cuneiform and NLP: Challenges for Fine-grained Part-of-Speech Tagging
(2024) -
Linguistic annotation of Byzantine book epigrams
-
- Journal Article
- A1
- open access
The limitations of irony detection in Dutch social media
-
- Conference Paper
- C1
- open access
Misery loves complexity : exploring linguistic complexity in the context of emotion detection
-
- Miscellaneous
- open access
Annotation guidelines for labeling emotion in multilingual tweets
(2023) In LT3 Technical Report -
- Conference Paper
- C1
- open access
DBBErt : part-of-speech tagging of pre-modern Greek text
-
- Conference Paper
- C1
- open access
Evaluating existing lemmatisers on unedited Byzantine Greek poetry
-
Who's afraid of false friends? Cognate ratios in translated and non-translated Dutch
-
A comparison of ChatGPT and fine-tuned BERT with regard to ABSA in the domain of literary criticism - Aspect-Based Sentiment Analysis for Literary Criticism: Experts vs. Social Critics on Literary Prizes
(2023) -
- Conference Paper
- C1
- open access
A fine line between irony and sincerity : identifying bias in transformer models for irony detection
-
- Conference Paper
- C1
- open access
Medieval social media : manual and automatic annotation of Byzantine Greek marginal writing
-
- Journal Article
- A2
- open access
The Database of Byzantine Book Epigrams project : principles, challenges, opportunities
-
- Miscellaneous
- open access
Annotation guidelines for labeling aspect-based sentiment analysis en aspect-based emotion analysis in the SentEMO project : version 1.0
(2023) In LT3 Technical Report -
- Conference Paper
- C1
- open access
Too many cooks spoil the model : are bilingual models for Slovene better than a large multilingual model?
-
- Journal Article
- A1
- open access
Distilling monolingual models from large multilingual transformers
-
- Journal Article
- A2
- open access
Improving domain-specific cross-lingual embeddings with automatically generated bilingual dictionaries
-
- Conference Paper
- C1
- open access
How language-dependent is emotion detection? Evidence from multilingual BERT
-
- Conference Paper
- C1
- open access
When the student becomes the master : learning better and smaller monolingual models from mBERT
-
- Conference Paper
- C1
- open access
Investigating the quality of static anchor embeddings from transformers for under-resourced languages
-
- Conference Paper
- C1
- open access
D-terminer : online demo for monolingual and bilingual automatic term extraction
-
- Conference Paper
- P1
- open access
Combining language models and linguistic information to label entities in memes
-
- Conference Paper
- P1
- open access
Irony detection for Dutch : a venture into the implicit
-
- Conference Paper
- P1
- open access
SentEMO : a multilingual adaptive platform for aspect-based sentiment and emotion analysis
-
- Miscellaneous
- open access
Annotation guidelines for labeling topics, aspects, stance, argumentativeness and claims in Dutch social media comments : version 1.0 : LT3 technical report – LT3 22-01
(2022) -
- Journal Article
- A1
- open access
Tagging terms in text : a supervised sequential labelling approach to automatic term extraction
-
- Journal Article
- A2
- open access
Aspect-based sentiment analysis for German : analyzing 'talk of literature' surrounding literary prizes on social media
-
- Conference Paper
- C1
- open access
A pilot study for BERT language modelling and morphological analysis for ancient and medieval Greek
-
- Journal Article
- A1
- open access
HAMLET : Hybrid Adaptable Machine Learning approach to Extract Terminology
-
- Conference Paper
- C1
- open access
LT3 at SemEval-2021 Task 6 : using multi-modal compact bilinear pooling to combine visual and textual understanding in memes
-
Aspect-based sentiment analysis for German : analyzing 'talk of literature' surrounding literary prizes on social media
-
- Journal Article
- A1
- open access
Current limitations in cyberbullying detection : on evaluation criteria, reproducibility, and data scarcity
-
- Conference Paper
- C1
- open access
LT3 at SemEval-2020 Task 8 : multi-modal multi-task learning for memotion analysis
-
- Conference Paper
- C1
- open access
LT3 at SemEval-2020 Task 9 : cross-lingual embeddings for sentiment analysis of Hinglish social media text
-
- Conference Paper
- C1
- open access
LT3 at SemEval-2020 Task 7 : comparing feature-based and transformer-based approaches to detect funny headlines
-
- Conference Paper
- C1
- open access
Annotating topics, stance, argumentativeness and claims in Dutch social media comments : a pilot study
-
- Conference Paper
- P1
- open access
Identifying cognates in English-Dutch and French-Dutch by means of orthographic information and cross-lingual word embeddings
-
- Conference Paper
- C1
- open access
Sentiment analysis for Hinglish code-mixed tweets by means of cross-lingual word embeddings
-
- Conference Paper
- C1
- open access
TermEval 2020 : shared task on automatic term extraction using the Annotated Corpora for term Extraction Research (ACTER) dataset
-
Annotated Corpora for Term Extraction Research (ACTER)
(2020) -
- Journal Article
- A1
- open access
In no uncertain terms : a dataset for monolingual and multilingual automatic term extraction from comparable corpora
-
- Journal Article
- A1
- open access
Uncovering the language of wine experts
-
- Conference Paper
- C1
- open access
Pilot study on medical translations in lay language : post-editing by language specialists, domain specialists or both?
-
Analysing the impact of supervised machine learning on automatic term extraction : HAMLET vs TermoStat
-
A classification-based approach to cognate detection combining orthographic and semantic similarity information
-
Proceedings of HUSO 2019, The fifth international conference on human and social analytics
Dennis Folds, Els Lefever (UGent) , Ralucca Gera and Veronique Hoste (UGent) -
Sentiment analysis of French political tweets : #MacronPrésident
-
Measuring the impact of sentiment for hate speech detection on Twitter
-
- Miscellaneous
- open access
Annotation guidelines for labeling English-Dutch cognate pairs (version 1.0)
-
- Journal Article
- A2
- open access
Improving the translation environment for professional translators