Spain

This talk describes Galileo’s performance in SemEval-2020 Task 12 on detecting and categorizing offensive language in social media. For Offensive Language Identification, we proposed a multi-lingual method using Pre-trained Language Models, ERNIE and XLM-R. For offensive language categorization, we proposed a knowledge distillation method trained on soft labels generated by several supervised models. Our team participated in all three sub-tasks. In Sub-task A - Offensive Language Identification, we ranked first in terms of average F1 scores in all languages. We are also the only team which ranked among the top three across all languages. We also took the first place in Sub-task B - Automatic Categorization of Offense Types and Sub-task C - Offense Target Identification.

COLING 2020

Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models

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.

technical paper

We describe our participation to subtask 1 in the SemEval 2020 task on Definition Extraction. We propose several BERT-based models, which differ in the fine-tuning strategy, and provide a discussion and analysis of our findings.

Fine-tuning BERT for Domain-Specific Definition Classification

Lexical Semantic Change detection, i.e., the task of identifying words that change meaning over time, is a very active research area, with applications in NLP, lexicography, and linguistics. Evaluation is currently the most pressing problem in Lexical Semantic Change detection, as no gold standards are available to the community, which hinders progress. We present the results of the first shared task that addresses this gap by providing researchers with an evaluation framework and manually annotated, high-quality datasets for English, German, Latin, and Swedish. 33 teams submitted 186 systems, which were evaluated on two subtasks.

Unsupervised Lexical Semantic Change Detection

We would like to present the Graded Word Similarity in Context (GWSC) task which asked participants to predict the effects of context on human perception of similarity in English, Croatian, Slovene and Finnish. We received 15 submissions and 11 system description papers. A new dataset (CoSimLex) was created for evaluation in this task: it contains pairs of words, each annotated within two short text passages. Systems beat the baselines by significant margins, but few did well
in more than one language or subtask. Almost every system employed a Transformer model, but with many variations in the details: WordNet sense embeddings, translation of contexts, TF-IDF weightings, and the automatic creation of datasets for fine-tuning were all used to good effect.


Graded Word Similarity in Context

Research on definition extraction has been conducted for well over a decade, largely with significant constraints on the type of definitions considered. In this work, we present DeftEval, a SemEval shared task in which participants must extract definitions from free text using a term-definition pair corpus that reflects the complex reality of definitions in natural language. Definitions and glosses in free text often appear without explicit indicators, across sentences boundaries, or in an otherwise complex linguistic manner. DeftEval involved 3 distinct subtasks: 1) Sentence classification, 2) sequence labeling, and 3) relation extraction.

DeftEval

This presentation introduces SemEval-2020 Task 5: Counterfactual Recognition (CR). Counterfactuals describe potential outcomes (consequents) produced by actions or circumstances that did not happen or cannot happen and are counter to the facts (antecedent). Our task provides a benchmark for counterfactual recognition in natural language with two subtasks. Subtask-1 aims to determine whether a given sentence is a counterfactual statement or not. Subtask-2 requires the participating systems to extract the antecedent and consequent in a given counterfactual statement.

Counterfactual Recognition

In this talk, we present the main findings and compare the results of SemEval-2020 Task 10, Emphasis Selection for Written Text in Visual Media. The goal of this shared task is to design automatic methods for emphasis selection, i.e. choosing candidates for emphasis in textual content to enable automated design assistance in authoring. The main focus is on short text instances for social media, with a variety of examples, from social media posts to inspirational quotes.
Participants were asked to model emphasis using plain text with no additional context from the user or other design considerations. SemEval-2020 Emphasis Selection shared task attracted 197 participants in the early phase and a total of 31 teams made submissions to this task. The highest-ranked submission achieved 0.823 Matchm score. The analysis of systems submitted to the task indicates that BERT and RoBERTa were the most common choice of pre-trained models used, and part of speech tag (POS) was the most useful feature.

Emphasis Selection for Written Text in Visual Media

In this paper, we present SemEval-2020 Task 4, CommonsenseValidation, and explanation(ComVE), which includes three subtasks, aiming to evaluate whether a system can distinguish a natural language statement that makes sense to humans from one that does not, and provide the reasons. Specifically, in our first subtask, the participating systems are required to choose from two natural language statements of similar wording the one that makes sense and the one does not. The second subtask additionally asks a system to select the key reason from three options why a given statement does not make sense. In the third subtask, a participating system needs to generate reason. We finally attracted 39 teams participating in at least one of the three subtasks. For SubtaskA and Subtask B, the performances of top-ranked systems are close to that of humans. However, for Subtask C, there is still a relatively large gap between systems and human performance. The dataset used in our task can be found at https://github.com/wangcunxiang/SemEval2020-Task4-Commonsense-Validation-and-Explanation;The leaderboard can be found athttps://competitions.codalab.org/competiti

Commonsense Validation and Explanation

Lexical entailment (LE) is a fundamental asymmetric lexico-semantic relation, supporting the hierarchies in lexical resources (e.g., WordNet, ConceptNet) and applications like natural language inference and taxonomy induction. Multilingual and cross-lingual NLP applications warrant models for LE detection that go beyond language boundaries. As part of SemEval 2020, we carried out a shared task (Task 2) on multilingual and cross-lingual LE. The shared task spans three dimensions: (1) monolingual LE in multiple languages versus cross-lingual LE, (2) binary versus graded LE, and (3) a set of 6 diverse languages (and 15 corresponding language pairs). We offered two different evaluation tracks: (a) distributional (Dist): for unsupervised, fully distributional models that capture LE solely on the basis of unannotated corpora, and (b) Any: for externally informed models, allowed to leverage any resources, including lexico-semantic networks (e.g., WordNet or BabelNet). In the Any track, we received system runs that push state-of-the-art across all languages and language pairs, for both binary LE detection and graded LE prediction.

Predicting Multilingual and Cross-Lingual
(Graded) Lexical Entailment

Information on social media comprises of various modalities such as textual, visual and audio.NLP and Computer Vision communities often leverage only one prominent modality in isolation to study social media. However, the computational processing of Internet memes needs a hybrid approach. The growing ubiquity of Internet memes on social media platforms such as Facebook, Instagram, and Twitter further suggests that we can not ignore such multimodal content any-more. To the best of our knowledge, there is not much attention towards meme emotion analysis. The objective of this proposal is to bring the attention of the research community towards the automatic processing of Internet memes. The task Memotion analysis released approx 10K an-notated memes- with human-annotated labels namely sentiment(positive, negative, neutral), type of emotion(sarcastic, funny,offensive, motivation) and their corresponding intensity. The challenge consisted of three subtasks: sentiment (positive, negative, and neutral) analysis of memes, overall emotion (humour, sarcasm, offensive, and motivational) classification of memes, and classifying intensity of meme emotion. The best performances achieved were F1(macro average)scores of 0.35, 0.51 and 0.32, respectively for each of the three subtasks.

The Visuo-Lingual Metaphor!

We present the results of the SemEval-2020 Task 9 on Sentiment Analysis of CodeMixed Tweets (SentiMix 2020). We also release and describe our Hinglish (Hindi-English) and Spanglish (Spanish-English) corpora annotated with word-level language identification and sentence-level sentiment labels. These corpora are comprised of 20K and 19K examples, respectively. The sentiment labels are - Positive, Negative, and Neutral. SentiMix attracted 89 submissions in total including 61 teams that participated in the Hinglish contest and 28 submitted systems to the Spanglish competition. The best performance achieved was 75.0% F1 score
for Hinglish and 80.6% F1 for Spanglish. We observe that BERT-like models and ensemble methods are the most common and successful approaches among the participants.

Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models

Downloads

Next from COLING 2020

Fine-tuning BERT for Domain-Specific Definition Classification

Similar lecture

Joint Learning of the Graph and the Data Representation for Graph-Based Semi-Supervised Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models

.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 BERT for Domain-Specific Definition Classification

Similar lecture

Joint Learning of the Graph and the Data Representation for Graph-Based Semi-Supervised Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads