Canada

The naïve approach for fine-tuning pretrained deep learning models on downstream tasks involves feeding them mini-batches of randomly sampled data. In this paper, we propose a more elaborate method for fine-tuning Pretrained Multilingual Transformers (PMTs) on multilin-gual data. Inspired by the success of curriculum learning approaches, we investigate the significance of fine-tuning PMTs on multilingual data in a sequential fashion language by language. Unlike the curriculum learning paradigm where the model is presented with increasingly complex examples, we do not adopt a notion of “easy” and “hard” samples. Instead, our experiments draw insight from psychological findings on how the human brain processes new information and the persistence of newly learned concepts. We perform our experiments on a challenging news-framing dataset that contains texts in six languages. Our proposed method outperforms the naïve approach by achieving improvements of 2.57% in terms of F1 score. Even when we supplement the naïve approach with recency fine-tuning, we still achieve an improvement of 1.34% with a 3.63% convergence speed-up. Moreover, we are the first to observe an interesting pattern in which deep learning models exhibit a human-like primacy-recency effect.

ACL 2023

BERTastic at SemEval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?

sequential fine-tuning

multilingual transformers

sustainibility

serial-position-effect

primacy-recency-effect

cognitive modeling

efficient training

curriculum learning

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

AAAI 2026

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

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.

This paper describes our approach to Subtask 1 "News Genre Categorization" of SemEval-2023 Task 3 "Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multi-lingual Setup", which aims to determine whether a given news article is an opinion piece, an objective report, or satirical. We fine-tuned the domain-specific language model POLITICS, which was pre-trained on a large-scale dataset of more than 3.6M English political news articles following ideology-driven pre-training objectives. In order to use it in the multilingual setup of the task, we added as a pre-processing step the translation of all documents into English. Our system ranked among the top systems overall in most language, and ranked 1st on the English dataset.

MELODI at SemEval-2023 Task 3: In-domain Pre-training for Low-resource Classification of News Articles

This paper describes our submission to the SemEval 2023 multilingual tweet intimacy analysis shared task. The goal of the task was to assess the level of intimacy of Twitter posts in ten languages. The proposed approach consists of several steps. First, we perform in-domain pre-training to create a language model adapted to Twitter data. In the next step, we train an ensemble of regression models to expand the training set with pseudo-labeled examples. The extended dataset is used to train the final solution. Our method was ranked first in five out of ten language subtasks, obtaining the highest average score across all languages.

OPI at SemEval 2023 Task 9: A Simple but Effective Approach to Multilingual Tweet Intimacy Analysis

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.

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

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.

Downloads

Next from ACL 2023

MELODI at SemEval-2023 Task 3: In-domain Pre-training for Low-resource Classification of News Articles

Similar lecture

Difficulty Is Not Enough: Curriculum Learning for LLMs Fine-tuning Must Consider Utility