Spain

We study the ability of large fine-tuned transformer models to solve a binary classification task of dialect identification, with a special interest in comparing the performance of multilingual to monolingual ones. The corpus analyzed contains Romanian and Moldavian samples from the news domain, as well as tweets for assessing the performance. We find that the monolingual models are superior to the multilingual ones and the best results are obtained using an SVM ensemble of 5 different transformer-based models. We provide our experimental results and an analysis of the attention mechanisms of the best-performing individual classifiers to explain their decisions. The code we used was released under an open-source license.

COLING 2020

Applying Multilingual and Monolingual Transformer-Based Models for Dialect Identification

moldavian

romanian

dialect identification

ensemble

attention analysis

natural language processing

classification

transformers

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

poster

This paper describes the Helsinki--Ljubljana contribution to the VarDial shared task on social media variety geolocation. Our solutions are based on the BERT Transformer models, the constrained versions of our models reaching 1st place in two subtasks and 3rd place in one subtask, while our unconstrained models outperform all the constrained systems by a large margin. We show in our analyses that Transformer-based models outperform traditional models by far, and that improvements obtained by pre-training models on large quantities of (mostly standard) text are significant, but not drastic, with single-language models also outperforming multilingual models. Our manual analysis shows that two types of signals are the most crucial for a (mis)prediction: named entities and dialectal features, both of which are handled well by our models.

Social Media Variety Geolocation with BERT Models

This poster presents the ensemble model built by our team for the Romanian Dialect Classification task of VarDial 2020 Evaluation Campaign.

A dual-encoding system for dialect classification

In this poster we describe the systems we used when participating in the VarDial Evaluation Campaign organized as part of the 7th workshop on NLP for similar languages, varieties and dialects. The shared tasks we participated in were the second edition of the Romanian Dialect Identification (RDI) and the first edition of the Social Media Variety Geolocation (SMG). The submissions of our SUKI team used generative language models based on Naive Bayes and character n-grams.

Experiments in Language Variety Geolocation and Dialect Identification

In this work we address the prediction of Swiss users’ geolocation, based on short messages collected from social media platforms such asTwitter and Jodel. The premise is that the language used varies with location. Thus, we acknowledge this as a dialect identification task, and choose the features based on linguistic rationalizations. At the same time, with the machine learning algorithms employed, we approach the regression problem posed from both a shallow and a deep learning perspective.

Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets

We describe our approaches for the Social Media Geolocation (SMG) task at the VarDial Eval-uation Campaign 2020. The goal was to predict geographical location (latitudes and longitudes)given an input text. There were three subtasks corresponding to German-speaking Switzerland(CH), Germany and Austria (DE-AT), and Croatia, Bosnia and Herzegovina, Montenegro andSerbia (BCMS). We submitted solutions to all subtasks but focused our development efforts onthe CH subtask, where we achieved third place out of 16 submissions with a median distance of15.93 km and had the best result of 14 unconstrained systems. In the DE-AT subtask, we rankedsixth out of ten submissions (fourth of 8 unconstrained systems) and for BCMS we achievedfourth place out of 13 submissions (second of 11 unconstrained systems).

ZHAW-InIT - Social Media Geolocation at VarDial 2020

We applied word unigram models, character ngram models, and CNNs to the task of distinguishing tweets of two related dialects of Romanian (standard Romanian and Moldavian) for the VarDial 2020 RDI shared task. The main challenge of the task was to perform cross-genre text classification: specifically, the models must be trained using text from news articles, and be used to predict tweets. Our best model was a Naive Bayes model trained on character ngrams, with the most common ngrams filtered out. We also applied SVMs and CNNs, but while they yielded the best performance on an evaluation dataset of news article, their accuracy significantly dropped when they were used to predict tweets. Our best model reached an F1 score of 0.715 on the evaluation dataset of tweets, and 0.667 on the held-out test dataset. The model ended up in the third place in the shared task.

Discriminating between standard Romanian and Moldavian tweets using filtered character ngrams 


We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2020 VarDial evaluation campaign. Although our official results were well below the baseline, we show in this poster that this was not due to the neural approach to language identification in general, but to a flaw in the function we used to sample data for training and evaluation purposes. Preliminary experiments conducted after the evaluation period suggest that our neural approach to language identification can achieve state-of-the-art results on this task, although further experimentation is required.

Challenges in Neural Language Identification: NRC at VarDial 2020

Analyzing a tweet can provide a general estimation of a tweet location while giving insight into the dialect of the user and other linguistic markers. Such linguistic attributes can be used to provide a regional approximation of tweet origins. In this paper, we present a neural regression model that can identify the linguistic intricacies of a tweet to predict the location of the user. The final model identifies the dialect embedded in the tweet and predicts the location of the tweet.

Geolocation of Tweets with a BiLSTM Regression Model

We participate in the FNS-Summarisation 2020 shared task to be held at FNP 2020 workshop at COLING 2020. Based on Determinantal Point Processes (DPPs), we build an extractive automatic financial summarisation system for the specific task. In this system, we first analyze the long report data to select the important narrative parts and generate an intermediate document. Next, we build the kernel Matrix L for the intermediate document, which represents the quality of its sentences. On the basis of L, we then can use the DPPs sampling algorithm to choose those sentences with high quality and diversity as the final summary sentences.

Extractive Financial Narrative Summarisation based on DPPs

The work proposes a combination of linguistic features with features derived from pre-trained BERT for training a supervised classifier for the task of Causality Detection. The Linguistic features help to inject knowledge about the semantic and syntactic structure of the input sentences. Experiments on the FinCausal Shared Task1 datasets indicate that the combination of Linguistic features with BERT improves overall performance for causality detection. The proposed system achieves a weighted average F1 score of 0.952 on the post-evaluation dataset.

Applying Multilingual and Monolingual Transformer-Based Models for Dialect Identification

Downloads

Next from COLING 2020

Social Media Variety Geolocation with BERT Models

Similar lecture

Dialect Identification under Domain Shift: Experiments with Discriminating Romanian and Moldavian

Applying Multilingual and Monolingual Transformer-Based Models for Dialect Identification

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Social Media Variety Geolocation with BERT Models

Similar lecture

Dialect Identification under Domain Shift: Experiments with Discriminating Romanian and Moldavian

Downloads