Canada

The goal of visual word sense disambiguation is to find the image that best matches the provided description of the word&#39;s meaning. It is a challenging problem, requiring approaches that combine language and image understanding. In this paper, we present our submission to SemEval 2023 visual word sense disambiguation shared task. The proposed system integrates multimodal embeddings, learning to rank methods, and knowledge-based approaches. We build a classifier based on the CLIP model, whose results are enriched with additional information retrieved from Wikipedia and lexical databases. Our solution was ranked third in the multilingual task and won in the Persian track, one of the three language subtasks.

ACL 2023

OPI at SemEval 2023 Task 1: Image-Text Embeddings and Multimodal Information Retrieval for Visual Word Sense Disambiguation

image-text embedding

visual word sense disambiguation

wordnet

wikipedia

The goal of visual word sense disambiguation is to find the image that best matches the provided description of the word's meaning. It is a challenging problem, requiring approaches that combine language and image understanding. In this paper, we present our submission to SemEval 2023 visual word sense disambiguation shared task. The proposed system integrates multimodal embeddings, learning to rank methods, and knowledge-based approaches. We build a classifier based on the CLIP model, whose results are enriched with additional information retrieved from Wikipedia and lexical databases. Our solution was ranked third in the multilingual task and won in the Persian track, one of the three language subtasks.

workshop paper

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

To improve the ability of language models to handle Natural Language Processing
(NLP) tasks and intermediate step of pre-training has recently been
introduced. In this setup, one takes a pre-trained language model, trains it on
a (set of) NLP dataset(s), and then finetunes it for a target task. It is
known that the selection of relevant transfer tasks is important, but recently
some work has shown substantial performance gains by doing intermediate
training on a very large set of datasets. Most previous work uses generative
language models or only focuses on one or a couple of tasks and uses a
carefully curated setup. We compare intermediate training with one or many
tasks in a setup where the choice of datasets is more arbitrary; we use all
SemEval 2023 text-based tasks. We reach performance improvements for most tasks
when using intermediate training. Gains are higher when doing intermediate
training on single tasks than all tasks if the right transfer task
is identified. Dataset smoothing and heterogeneous batching did not lead to
robust gains in our setup.


MaChAmp at SemEval-2023 Tasks 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.

We describe our contribution to the SemEVAl 2023 AfriSenti-SemEval shared task, where we tackle the task of sentiment analysis in 14 different African languages. We develop both monolingual and multilingual models under a full supervised setting (subtasks A and B). We also develop models for the zero-shot setting (subtask C). Our approach involves experimenting with transfer learning using six language models, including further pretraining of some of these models as well as a final finetuning stage. Our best performing models achieve an f1-score of 70.36 on development data and a f1-score of 66.13 on test data. Unsurprisingly, our results demonstrate the effectiveness of transfer learning and finetuning techniques for sentiment analysis across multiple languages. Our approach can be applied to other sentiment analysis tasks in different languages and domains.

UBC-DLNLP at SemEval-2023 Task 12: Impact of Transfer Learning on African Sentiment Analysis

The following is a description of the RIGA team’s submissions for the English track of the SemEval-2023 Task 2: Multilingual Complex Named Entity Recognition (MultiCoNER) II. Our approach achieves 17% boost in results by utilizing pre-existing Large-scale Language Models (LLMs), such as GPT-3, to gather additional contexts. We then fine-tune a pre-trained neural network utilizing these contexts. The final step of our approach involves meticulous model and compute resource scaling, which results in improved performance. Our results placed us 12th out of 34 teams in terms of overall ranking and 7th in terms of the noisy subset ranking. The code for our method is available on GitHub1.

RIGA at SemEval-2023 Task 2: NER Enhanced with GPT-3

This article presents our solution for SemEval-2023 Task 1: Visual Word Sense Disambiguation. The aim of the task was to select the most suitable from a list of ten images for a given word, extended by a small textual context. Our solution comprises two parts. The first focuses on an attempt to further extend the textual context, based on word definitions contained in WordNet and in Open English WordNet. The second focuses on selecting the most suitable image using the CLIP model with previously developed word context and additional information obtained from the BEiT image classification model. Our solution allowed us to achieve a result of 70.84% on the official test dataset for the English language.

OPI PIB at SemEval-2023 Task 1: A CLIP-based Solution Paired with an Additional Word Context Extension

This presentation describes the participation of the research laboratory MIND, at the University of Milano-Bicocca, in the SemEval 2023 task related to Learning With Disagreements (Le-Wi-Di). The main goal is to identify the level of agreement/disagreement from a collection of textual datasets with different characteristics in terms of style, language, and task. The proposed approach is grounded on the hypothesis that the disagreement between annotators
could be grasped by the uncertainty that a model, based on several linguistic characteristics, could have on the prediction of a given gold label.

MIND at SemEval-2023 Task 11: From Uncertain Predictions to Subjective Disagreement

We describe the methods we used for legal text understanding, specifically Task 6 Legal-Eval at SemEval 2023. The outcomes could assist law practitioners and help automate the working process of judicial systems. The shared task defined three main sub-tasks: sub-task A, Rhetorical Roles Prediction (RR); sub-task B, Legal Named Entities Extraction (L-NER); and sub-task C, Court Judgement Prediction with Explanation (CJPE). Our team addressed all three sub-tasks by exploring various Deep Learning (DL) based models. Overall, our team's approaches achieved promising results on all three sub-tasks, demonstrating the potential of deep learning-based models in the judicial domain.

uOttawa at SemEval-2023 Task 6: Deep Learning for Legal Text Understanding

We describe our participation in the Clickbait challenge at SemEval 2023. In this work, we address the Clickbait classification task using transformers models in an ensemble configuration. We tackle the Spoiler Generation task using a two-level ensemble strategy of models trained for extractive QA, and selecting the best K candidates for multi-part spoilers. In the test partitions, our approaches obtained a classification accuracy of 0.716 for classification and a BLEU-4 score of 0.439 for spoiler generation.

Walter Burns at SemEval-2023 Task 5: NLP-CIMAT - Leveraging Model Ensembles for Clickbait Spoiling

This poster describes the participation of SINAI research team in the Explainable Detection of Online Sexism (EDOS) Shared Task at SemEval 2023. Specifically, we participate in subtask A (binary sexism detection), subtask B (category of sexism), and subtask C (fine-grained vector of sexism). For the three subtasks, we propose a system that integrates information related to emotions, sentiments, and irony in order to check whether these features help detect sexism content. Our team ranked 46th in subtask A, 37th in subtask B, and 29th in subtask C, achieving 0.8245, 0.6043, and 0.4376 of macro f1-score, respectively, among the participants.


SINAI at SemEval-2023 Task 10: Leveraging Emotions, Sentiments, and Irony Knowledge for Explainable Detection of Online Sexism

This presentation describes the submission of UZH\_CLyp for the SemEval 2023 Task 9 ``Multilingual Tweet Intimacy Analysis''. We achieved second-best results in all 10 languages according to the official Pearson's correlation regression evaluation measure. Our cross-lingual transfer learning approach explores the benefits of using a Head-First Fine-Tuning method (HeFiT) that first updates only the regression head parameters and then also updates the pre-trained transformer encoder parameters at a reduced learning rate. Additionally, we study the impact of using a small set of automatically generated examples (in our case, from ChatGPT) for low-resource settings where no human-labeled data is available. Our study shows that HeFiT stabilizes training and consistently improves results for pre-trained models that lack domain adaptation to tweets. Our study also shows a noticeable performance increase in cross-lingual learning when synthetic data is used, confirming the usefulness of current text generation systems to improve zero-shot baseline results. Finally, we examine how possible inconsistencies in the annotated data contribute to cross-lingual interference issues.

UZH_CLyp at SemEval-2023 Task 9: Head-First Fine-Tuning and ChatGPT Data Generation for Cross-Lingual Learning in Tweet Intimacy Prediction

Human Value Detection in Arguments is a complex task requiring a high-level understanding of language due to the hidden nature of opinions and beliefs in arguments. In this presentation, the Augustine of Hippo team shows its solution to SemEval2023 Task 4: the proposed methodology leverages an unsurpervised explainable knowledge extraction system capable of identifying concepts to associate with human values.

Premium content

OPI at SemEval 2023 Task 1: Image-Text Embeddings and Multimodal Information Retrieval for Visual Word Sense Disambiguation

Downloads

Next from ACL 2023

MaChAmp at SemEval-2023 Tasks 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES