Spain

We present a transfer learning system to perform a mixed Spanish-English sentiment classification task. Our proposal uses the state-of-the-art language model BERT and embed it within a ULMFiT transfer learning pipeline. This combination allows us to predict the polarity detection of code-mixed (English-Spanish) tweets. Thus, among 29 submitted systems, our approach (referred to as dplominop) is ranked 4th on the Sentimix Spanglish test set of SemEval 2020 Task 9. In fact, our system yields the weighted-F1 score value of 0.755 which can be easily reproduced --- the source code and implementation details are made available.

COLING 2020

Robust System based on Transformer for Code-Mixed Sentiment Classification

sentiment analysis

transfer learning

transformer

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.

poster

Fine-tuning of pre-trained transformer networks such as BERT yield state-of-the-art results for text classification tasks. Typically, fine-tuning is performed on task-specific training datasets in a supervised manner. One can also fine-tune in unsupervised manner beforehand by further pretraining the masked language modeling (MLM) task. Hereby, in-domain data for unsupervised MLM resembling the actual classification target dataset allows for domain adaptation of the model. In this paper, we compare current pre-trained transformer networks with and without MLM fine-tuning on their performance for offensive language detection. Our MLM fine-tuned RoBERTa-based classifier officially ranks 1st in the SemEval 2020 Shared Task 12 for the English language. Further experiments with the ALBERT model even surpass this result.

Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection

This paper describes our system to assess humour intensity in edited news headlines as part of a participation in the 7th task of SemEval-2020 on ``Humor, Emphasis and Sentiment". Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task.

Assessing Humour in Edited News Headlines Using Hand-crafted Features and Online Knowledge Bases

We introduce an approach to multilingual Offensive Language Detection based on the mBERT transformer model. We download extra training data from Twitter in English, Danish, and Turkish, and use it to re-train the model. We then fine-tuned the model on the provided training data and, in some configurations, implement transfer learning approach exploiting the typological relatedness between English and Danish. Our systems obtained good results across the three languages (.9036 for EN, .7619 for DA, and .7789 for TR).

Retraining mBERT on Social Media and Fine-tuned Offensive Language Models

We apply contextualised word embeddings to lexical semantic change detection in the SemEval-2020 Shared Task 1. This paper focuses on Subtask 2, ranking words by the degree of their semantic drift over time. We analyse the performance of two contextualising architectures (BERT and ELMo) and three change detection algorithms. We find that the most effective algorithms rely on the cosine similarity between averaged token embeddings and the pairwise distances between token embeddings. They outperform strong baselines by a large margin (in the post-evaluation phase, we have the best Subtask 2 submission for SemEval-2020 Task 1), but interestingly, the choice of a particular algorithm depends on the distribution of gold scores in the test set.

Contextualised Embeddings for Lexical Semantic Change Detection

This paper describes the approaches used by the Discovery Team to solve SemEval-2020 Task 1 -Unsupervised Lexical Semantic Change Detection. The proposed method is based on clusteringof BERT contextual embeddings, followed by a comparison of cluster distributions across time.The best results were obtained by an ensemble of this method and static Word2Vec embeddings.According to the official results, our approach proved the best for Latin in Subtask 2.

Static Embeddings better than Contextualised for Semantic Change Detection?

This poster describes an ensemble model designed for SemEval2020-Task 7. The task is based on the Humicroedit datasets that is comprised of news titles and one-word substitutions to make them humorous. We use BERT, FastText, Elmo, and Word2Vec to encode these titles then pass them to a Bidirectional GRU with attention. Finally, we use XGBoost on the concatenation of the results to predict the humor rating.

BiGRU Ensemble for Evaluating Humor in Edited News Headlines

We participate in both subtasks of the SemEval-2020 task Detection of Propaganda Techniques in News Articles: Span Identification (SI) and Technique Classification (TC). We use a bi-LSTM architecture in the SI subtask and train a complex ensemble model for the TC subtask. Our architectures are built using embeddings from BERT in combination with additional lexical features and extensive label post-processing. Our systems achieve a rank of 8 out of 35 teams in the SI subtask (F1-score: 43.86%) and 8 out of 31 teams in the TC subtask (F1-score: 57.37%).

An Analysis of Feature Engineering for Ensemble Models for Propaganda Detection

We present an approach for sentiment analysis in code mixed
language on twitter defined in SemEval 2020 Task 9.Our team
(referred as LiangZhao ) employ different multilingual models with
weighted loss focused on complexity of code mixing in sentence, in
which the best model achieved f1 score of 0.806 and ranked 1 st of
subtask Sentimix Spanglish. The performance of method is analyzed

Cross lingual Models
with Focal Loss for Sentiment Analysis of Code Mixing Language

We present our submission to subtask A at SemEval 2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval2). For Danish, Turkish, Arabic and Greek, we develop an architecture based on transfer learning and relying on a two-channel BERT model, in which the English BERT and the multilingual one are combined after creating a machine-translated parallel corpus for each language in the task. For English, instead, we adopt a more standard, single-channel approach. 
We find that, in a multilingual scenario, with some languages having small training data, using parallel BERT models with machine translated data can give systems more stability, especially when dealing with noisy data. The fact that machine translation on social media data may not be perfect does not hurt the overall classification performance.

Using Multi-Channel BERT for Multilingual Offensive Language Detection

SemEval 2020 Task 12 focusses on the challenge of detecting offensive language present in social media. To tackle the subtask A (Offensive language identification) and the subtask C (Identifying the targets of offensive language) of SemEval 2020 Task 12, we developed ensembles of classifiers based on DistilBERT pre-trained language model. Our ensemble models achieved F1 scores of 0.906 for the subtask A, and 0.623 for the subtask C


Robust System based on Transformer for Code-Mixed Sentiment Classification

Downloads

Next from COLING 2020

Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection

Similar lecture

Aggregation of Transformer-based models’ features for offensive language recognition

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Robust System based on Transformer for Code-Mixed Sentiment Classification

.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

Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection

Similar lecture

Aggregation of Transformer-based models’ features for offensive language recognition

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads