no code implementations • EMNLP 2020 • Anne Lauscher, Vinit Ravishankar, Ivan Vuli{\'c}, Goran Glava{\v{s}}
Massively multilingual transformers (MMTs) pretrained via language modeling (e. g., mBERT, XLM-R) have become a default paradigm for zero-shot language transfer in NLP, offering unmatched transfer performance.
no code implementations • ACL 2021 • Ivan Vuli{\'c}, Edoardo Maria Ponti, Anna Korhonen, Goran Glava{\v{s}}
Inspired by prior work on semantic specialization of static word embedding (WE) models, we show that it is possible to expose and enrich lexical knowledge from the LMs, that is, to specialize them to serve as effective and universal {``}decontextualized{''} word encoders even when fed input words {``}in isolation{''} (i. e., without any context).
no code implementations • EACL 2021 • Goran Glava{\v{s}}, Ivan Vuli{\'c}
Traditional NLP has long held (supervised) syntactic parsing necessary for successful higher-level semantic language understanding (LU).
no code implementations • COLING 2020 • Goran Glava{\v{s}}, Mladen Karan, Ivan Vuli{\'c}
We present XHate-999, a multi-domain and multilingual evaluation data set for abusive language detection.
no code implementations • SEMEVAL 2020 • Goran Glava{\v{s}}, Ivan Vuli{\'c}, Anna Korhonen, Simone Paolo Ponzetto
The shared task spans three dimensions: (1) monolingual vs. cross-lingual LE, (2) binary vs. graded LE, and (3) a set of 6 diverse languages (and 15 corresponding language pairs).
no code implementations • ACL 2020 • Goran Glava{\v{s}}, Ivan Vuli{\'c}
We present InstaMap, an instance-based method for learning projection-based cross-lingual word embeddings.
Bilingual Lexicon Induction
Cross-Lingual Word Embeddings
+2
no code implementations • WS 2020 • Ivan Vuli{\'c}, Anna Korhonen, Goran Glava{\v{s}}
Work on projection-based induction of cross-lingual word embedding spaces (CLWEs) predominantly focuses on the improvement of the projection (i. e., mapping) mechanisms.
no code implementations • ACL 2020 • Mladen Karan, Ivan Vuli{\'c}, Anna Korhonen, Goran Glava{\v{s}}
Effective projection-based cross-lingual word embedding (CLWE) induction critically relies on the iterative self-learning procedure.
no code implementations • IJCNLP 2019 • Edoardo Maria Ponti, Ivan Vuli{\'c}, Goran Glava{\v{s}}, Roi Reichart, Anna Korhonen
Semantic specialization integrates structured linguistic knowledge from external resources (such as lexical relations in WordNet) into pretrained distributional vectors in the form of constraints.
no code implementations • IJCNLP 2019 • Fabian David Schmidt, Markus Dietsche, Simone Paolo Ponzetto, Goran Glava{\v{s}}
We introduce Seagle, a platform for comparative evaluation of semantic text encoding models on information retrieval (IR) tasks.
no code implementations • RANLP 2019 • Taha Tobaili, Fern, Miriam ez, Harith Alani, Sanaa Sharafeddine, Hazem Hajj, Goran Glava{\v{s}}
As such, texts written in Arabizi are often disregarded in sentiment analysis tasks for Arabic.
no code implementations • WS 2019 • Aishwarya Kamath, Jonas Pfeiffer, Edoardo Maria Ponti, Goran Glava{\v{s}}, Ivan Vuli{\'c}
Semantic specialization methods fine-tune distributional word vectors using lexical knowledge from external resources (e. g. WordNet) to accentuate a particular relation between words.
no code implementations • ACL 2019 • Ivan Vuli{\'c}, Simone Paolo Ponzetto, Goran Glava{\v{s}}
Starting from HyperLex, the only available GR-LE dataset in English, we construct new monolingual GR-LE datasets for three other languages, and combine those to create a set of six cross-lingual GR-LE datasets termed CL-HYPERLEX.
no code implementations • ACL 2019 • Goran Glava{\v{s}}, Federico Nanni, Simone Paolo Ponzetto
Political scientists created resources and used available NLP methods to process textual data largely in isolation from the NLP community.
1 code implementation • ACL 2019 • Goran Glava{\v{s}}, Ivan Vuli{\'c}
Lexical entailment (LE; also known as hyponymy-hypernymy or is-a relation) is a core asymmetric lexical relation that supports tasks like taxonomy induction and text generation.
1 code implementation • WS 2018 • Anne Lauscher, Goran Glava{\v{s}}, Kai Eckert
Argumentation is arguably one of the central features of scientific language.
no code implementations • WS 2018 • Anne Lauscher, Goran Glava{\v{s}}, Simone Paolo Ponzetto
We analyze the annotated argumentative structures and investigate the relations between argumentation and other rhetorical aspects of scientific writing, such as discourse roles and citation contexts.
no code implementations • EMNLP 2018 • Anne Lauscher, Goran Glava{\v{s}}, Simone Paolo Ponzetto, Kai Eckert
Exponential growth in the number of scientific publications yields the need for effective automatic analysis of rhetorical aspects of scientific writing.
no code implementations • ACL 2018 • Goran Glava{\v{s}}, Ivan Vuli{\'c}
The ER model allows us to learn a global specialization function and specialize the vectors of words unobserved in the training data as well.
1 code implementation • NAACL 2018 • Goran Glava{\v{s}}, Ivan Vuli{\'c}
We present a simple and effective feed-forward neural architecture for discriminating between lexico-semantic relations (synonymy, antonymy, hypernymy, and meronymy).
no code implementations • EMNLP 2017 • Goran Glava{\v{s}}, Simone Paolo Ponzetto
Detection of lexico-semantic relations is one of the central tasks of computational semantics.
no code implementations • WS 2017 • Maria Pia di Buono, Jan {\v{S}}najder, Bojana Dalbelo Ba{\v{s}}i{\'c}, Goran Glava{\v{s}}, Martin Tutek, Natasa Milic-Frayling
We present a preliminary study on predicting news values from headline text and emotions.
no code implementations • WS 2017 • Goran Glava{\v{s}}, Federico Nanni, Simone Paolo Ponzetto
In this paper, we propose an approach for cross-lingual topical coding of sentences from electoral manifestos of political parties in different languages.
no code implementations • WS 2017 • Maria Pia di Buono, Martin Tutek, Jan {\v{S}}najder, Goran Glava{\v{s}}, Bojana Dalbelo Ba{\v{s}}i{\'c}, Nata{\v{s}}a Mili{\'c}-Frayling
In this paper, we describe our preliminary study on annotating event mention as a part of our research on high-precision news event extraction models.
1 code implementation • EACL 2017 • Goran Glava{\v{s}}, Federico Nanni, Simone Paolo Ponzetto
Political text scaling aims to linearly order parties and politicians across political dimensions (e. g., left-to-right ideology) based on textual content (e. g., politician speeches or party manifestos).
no code implementations • EACL 2017 • Patrick Klein, Simone Paolo Ponzetto, Goran Glava{\v{s}}
We exploit multilingual synsets from BabelNet to translate English triples to other languages and then augment the reference knowledge base with cross-lingual triples.
no code implementations • LREC 2014 • Goran Glava{\v{s}}, Jan {\v{S}}najder, Marie-Francine Moens, Parisa Kordjamshidi
In this work, we present HiEve, a corpus for recognizing relations of spatiotemporal containment between events.