Spain

This poster describes BUT-FIT&#39;s submission at SemEval-2020 Task 5: Modelling Causal Reasoning in Language: Detecting Counterfactuals. The challenge focused on detecting whether a given statement contains a counterfactual (Subtask 1) and extracting both antecedent and consequent parts of the counterfactual from the text (Subtask 2). We experimented with various state-of-the-art language representation models (LRMs). We found RoBERTa LRM to perform the best in both subtasks. We achieved the first place in both exact match and F1 for Subtask 2 and ranked second for Subtask 1.

COLING 2020

Automatic detection of counterfactual statements with deep pre-trained language representation models

counterfactual roberta bert causal-reasoning

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.

This poster describes BUT-FIT's submission at SemEval-2020 Task 5: Modelling Causal Reasoning in Language: Detecting Counterfactuals. The challenge focused on detecting whether a given statement contains a counterfactual (Subtask 1) and extracting both antecedent and consequent parts of the counterfactual from the text (Subtask 2). We experimented with various state-of-the-art language representation models (LRMs). We found RoBERTa LRM to perform the best in both subtasks. We achieved the first place in both exact match and F1 for Subtask 2 and ranked second for Subtask 1.

poster

This paper describes our system submission Hasyarasa for the SemEval-2020 Task-7: Assessing Humor in Edited News Headlines. This task has two subtasks. The goal of Subtask 1 is to predict the mean funniness of the edited headline given the original and the edited headline. In Subtask 2, given two edits on the original headline, the goal is to predict the funnier of the two. We observed that the departure from expected state/ actions of situations/ individuals is the cause of
humor in the edited headlines. We propose two novel features: Contextual Semantic Distance and Contextual Neighborhood Distance to estimate this departure and thus capture the contextual absurdity and hence the humor in the edited headlines. We have used these features together with a Bi-LSTM Attention-based model and have achieved 0.53310 RMSE for Subtask 1 and 60.19% accuracy for Subtask 2.

Quantifying Humor as departure from Expectedness

This poster describes SChME(Semantic Change Detection with Model Ensemble), a method used in SemEval-2020 Task 1 on unsupervised detection of lexical semantic change. SChME uses a model ensemble combining signals of distributional models (word embeddings) and word frequency models where each model casts a vote indicating the probability that a word suffered semantic change according to that feature. More specifically, we combine cosine distance of word vectors combined with a neighborhood-based metric we named Mapped Neighborhood Distance (MAP), and a word frequency differential metric as input signals to our model. Additionally, we explore alignment-based methods to investigate the importance of the landmarks used in this process. Our results show evidence that the number of landmarks used for alignment has a direct impact on the predictive performance of the model. Moreover, we show that languages that suffer less semantic change tend to benefit from using a large number of landmarks, whereas languages with more semantic change benefit from a more careful choice of landmark number for alignment.

A Model Ensemble for DetectingLexical Semantic Change

The “Sentiment Analysis for Code-Mixed Social Media Text” task at the SemEval 2020 competition focuses on sentiment analysis in code-mixed social media text , specifically, on the combination of English with Spanish (Spanglish) and Hindi (Hinglish). We present a system able to classify tweets, from Spanish and English languages, into positive, negative and neutral. Firstly, we built a classifier able to provide corresponding sentiment labels. Besides the sentiment labels, we provide the language labels at the word level. Secondly, we generate a word-level representation, using Convolutional Neural Network (CNN) architecture. Our solution indicates promising results for the Sentimix Spanglish-English task (0.744), the team, occupied the 9th place. However, for the Sentimix Hindi-English task (0.324) the results have to be improved.

Sentiment Analysis for CodeMixed Social Media Text using CNN

The Poster summarizes our studies on propaganda detection techniques for news articles in the SemEval-2020 task 11. This task is divided into the SI and TC subtasks. We implemented the GloVe word representation, the BERT pretraining model, and the LSTM model architecture to accomplish this task.

LSTM Network for Detection of Propaganda Techniques in News Articles

We (Team Skurt) propose a simple method to detect lexical semantic change by clustering contextualized embeddings produced by XLM-R, using K-Means++. The basic idea is that contextualized embeddings that encode the same sense are located in close proximity in the embedding space. Our approach is both simple and generic, but yet performs relatively well in both sub-tasks of SemEval-2020 Task 1. We hypothesize that the main shortcoming of our method lies in the simplicity of the clustering method used.


SenseCluster at SemEval-2020

The growing popularity and applications of sentiment analysis of social media posts has naturally led to sentiment analysis of posts written in multiple languages, a practice known as code-switching. While recent research into code-switched posts has focused on the use of multilingual word embeddings, these embeddings were not trained on code-switched data. In this work, we present word-embeddings trained on code-switched tweets, specifically those that make use of Spanish and English, known as Spanglish. We explore the embedding space to discover how they capture the meanings of words in both languages. We test the effectiveness of these embeddings by participating in SemEval 2020 Task 9: ~\emph{Sentiment Analysis on Code-Mixed Social Media Text}. We utilised them to train a sentiment classifier that achieves an F-1 score of 0.722. This is higher than the baseline for the competition of 0.656, with our team (codalab username \emph{francesita}) ranking 14 out of 29 participating teams, beating the baseline.

Code-switched word embeddings for sentiment analysis

In this paper, we present language model system submitted to SemEval-2020 Task 4 competition: ”Commonsense Validation and Explanation”. We participate in two subtasks for subtask A: validation and subtask B: Explanation. We implemented with transfer learning using pretrained language models (BERT, XLNet, RoBERTa, and ALBERT) and fine-tune them on this task. Then we compared their characteristics in this task to help future researchers understand and use these models more properly. The ensembled model better solves this problem, making the model’s accuracy reached 95.9% on subtask A, which just worse than human’s by only 3% accuracy.

Commonsense Validation and Explanation system based on ensemble of language model

We present the results of our system for SemEval-2020 Task 1 that exploits a commonly used lexical semantic change detection model based on Skip-Gram with Negative Sampling. Our system focuses on Vector Initialization (VI) alignment, compares VI to the currently top-ranking models for Subtask 2 and demonstrates that these can be outperformed if we optimize VI dimensionality. We demonstrate that differences in performance can largely be attributed to model-specific sources of noise, and we reveal a strong relationship between dimensionality and frequency-induced noise in VI alignment. Our results suggest that lexical semantic change models integrating vector space alignment should pay more attention to the role of the dimensionality parameter.

How low can you go? Dimensionality in Lexical Semantic Change Detection

In this work, we tackled seamEval-2020 Task A, B, and C of Offensive Language Challenge at SemEval2020. We handled offensive language in five languages: English, Greek, Danish, Arabic, and Turkish. Specifically, we pre-processed all
provided datasets and developed an appropriate strategy to handle Tasks (A, B, & C) for identifying the presence/absence, type, and the target of
offensive language in social media. For this purpose, we used OLID2019 [1], OLID2020 [2] datasets, and generated new datasets using Google translation API (Fig. 1), which we made publicly available. We discussed the limitations
and the success of our machine learning-based approach for all five different languages. Our results for identifying offensive posts (Task A)
yielded satisfactory accuracy of 0.92 for English, 0.81 for Danish, 0.84 for Turkish, 0.85 for Greek, and 0.89 for Arabic. For the type detection (Task
B), the results are significantly higher (.87 accuracy) compared to target detection (Task C), which yields .81 accuracy. Moreover, after using automated Google translation, the overall efficiency improved by 2% for Greek, Turkish, and Danish.

Multilingual Identification of Offensive Language, Type, and Target of Twitter Post Using Translated Datasets.

We describe our contribution to two of the subtasks of SemEval 2020 Task 6, DeftEval: Extracting term-definition pairs in free text. The system for Subtask 1: Sentence Classification is based on a transformer architecture where we use transfer learning to fine-tune a pretrained model on the downstream task, and the one for Subtask 3: Relation Classification uses a Random Forest classifier with handcrafted dedicated features. Our systems respectively achieve 0.830 and 0.994 F1-scores on the official test set, and we believe that the insights derived from our study are potentially relevant to help advance the research on definition extraction.

Downloads

Next from COLING 2020

Quantifying Humor as departure from Expectedness

Similar lecture

Convolutional humor

.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

Quantifying Humor as departure from Expectedness

Similar lecture

Convolutional humor

Downloads