George-Andrei Dima


pdf bib
EENLP: Cross-lingual Eastern European NLP Index
Alexey Tikhonov | Alex Malkhasov | Andrey Manoshin | George-Andrei Dima | Réka Cserháti | Md.Sadek Hossain Asif | Matt Sárdi
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Motivated by the sparsity of NLP resources for Eastern European languages, we present a broad index of existing Eastern European language resources (90+ datasets and 45+ models) published as a github repository open for updates from the community. Furthermore, to support the evaluation of commonsense reasoning tasks, we provide hand-crafted cross-lingual datasets for five different semantic tasks (namely news categorization, paraphrase detection, Natural Language Inference (NLI) task, tweet sentiment detection, and news sentiment detection) for some of the Eastern European languages. We perform several experiments with the existing multilingual models on these datasets to define the performance baselines and compare them to the existing results for other languages.


pdf bib
Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets
George-Andrei Dima | Dumitru-Clementin Cercel | Mihai Dascalu
Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task

This paper presents our contribution to the Social Media Mining for Health Applications Shared Task 2021. We addressed all the three subtasks of Task 1: Subtask A (classification of tweets containing adverse effects), Subtask B (extraction of text spans containing adverse effects) and Subtask C (adverse effects resolution). We explored various pre-trained transformer-based language models and we focused on a multi-task training architecture. For the first subtask, we also applied adversarial augmentation techniques and we formed model ensembles in order to improve the robustness of the prediction. Our system ranked first at Subtask B with 0.51 F1 score, 0.514 precision and 0.514 recall. For Subtask A we obtained 0.44 F1 score, 0.49 precision and 0.39 recall and for Subtask C we obtained 0.16 F1 score with 0.16 precision and 0.17 recall.


pdf bib
Approaching SMM4H 2020 with Ensembles of BERT Flavours
George-Andrei Dima | Andrei-Marius Avram | Dumitru-Clementin Cercel
Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task

This paper describes our solutions submitted to the Social Media Mining for Health Applications (#SMM4H) Shared Task 2020. We participated in the following tasks: Task 1 aimed at classifying if a tweet reports medications or not, Task 2 (only for the English dataset) aimed at discriminating if a tweet mentions adverse effects or not, and Task 5 aimed at recognizing if a tweet mentions birth defects or not. Our work focused on studying different neural network architectures based on various flavors of bidirectional Transformers (i.e., BERT), in the context of the previously mentioned classification tasks. For Task 1, we achieved an F1-score (70.5%) above the mean performance of the best scores made by all teams, whereas for Task 2, we obtained an F1-score of 37%. Also, we achieved a micro-averaged F1-score of 62% for Task 5.

pdf bib
UPB at FinCausal-2020, Tasks 1 & 2: Causality Analysis in Financial Documents using Pretrained Language Models
Marius Ionescu | Andrei-Marius Avram | George-Andrei Dima | Dumitru-Clementin Cercel | Mihai Dascalu
Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation

Financial causality detection is centered on identifying connections between different assets from financial news in order to improve trading strategies. FinCausal 2020 - Causality Identification in Financial Documents – is a competition targeting to boost results in financial causality by obtaining an explanation of how different individual events or chain of events interact and generate subsequent events in a financial environment. The competition is divided into two tasks: (a) a binary classification task for determining whether sentences are causal or not, and (b) a sequence labeling task aimed at identifying elements related to cause and effect. Various Transformer-based language models were fine-tuned for the first task and we obtained the second place in the competition with an F1-score of 97.55% using an ensemble of five such language models. Subsequently, a BERT model was fine-tuned for the second task and a Conditional Random Field model was used on top of the generated language features; the system managed to identify the cause and effect relationships with an F1-score of 73.10%. We open-sourced the code and made it available at: