Canada

We demonstrate a simple yet effective approach to augmenting training data for multilingual named entity recognition using machine trans- lation. The named entity spans from the origi- nal sentences are transferred to the translations via word alignment and then filtered with the baseline recognizer to retain high quality an- notations. The proposed data augmentation approach improves the baseline performance of XLM-Roberta on the multilingual dataset.

ACL 2023

Sakura at SemEval-2023 Task 2: Data Augmentation via Translation

name entity recognition

machine translation

information extraction

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

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.


We conduct a comparison of pre-trained encoder-only and decoder-only language mod- els with and without continued pre-training, to detect online sexism. Our fine-tuning-based classifier system achieved the 16th rank in the SemEval 2023 Shared Task 10 Subtask A that asks to distinguish sexist and non-sexist texts. Additionally, we conduct experiments aimed at enhancing the interpretability of systems de- signed to detect online sexism. Our findings provide insights into the features and decision- making processes underlying our classifier sys- tem, thereby contributing to a broader effort to develop explainable AI models to detect online sexism.

DCU at SemEval-2023 Task 10: A Comparative Analysis of Encoder-only and Decoder-only Language Models with Insights into Interpretability

In this work, we present a Named Entity Recognition (NER) system that was trained using a Frustratingly Easy Domain Adaptation (FEDA) over multiple legal corpora. The goal was to create a NER capable of detecting 14 types of legal named entities in Indian judgments. Besides the FEDA architecture, we explored a method based on overlapping context and averaging tensors to process long input texts, which can be beneficial when processing legal documents. The proposed NER reached an F1-score of 0.9007 in the sub-task B of Semeval-2023 Task 6, Understanding Legal Texts.

Jus Mundi at SemEval-2023 Task 6: Using a Frustratingly Easy Domain Adaption for a Legal Named Entity Recognition System

The rise of social media has exponentially witnessed the use of clickbait posts that grab users' attention. This paper presents our approach, which use different encoding techniques. We propose hierarchical encoding with count and document length feature-based model for spoiler type classification, which uses Recurrence over Pretrained Encoding. We also propose combining multiple ranking with reciprocal rank fusion for passage spoiler retrieval and question-answering approach for phrase spoiler retrieval. For multipart spoiler retrieval, we combine the above two spoiler retrieval methods. Based on the benchmark, the experimental results indicate that our proposed spoiler retrieval methods are highly effective in retrieving spoilers that are semantically very close to the ground truth spoilers.

Jack-flood at SemEval-2023 Task 5:Hierarchical Encoding and Reciprocal Rank Fusion-Based System for Spoiler Classification and Generation

Many nations and organizations have begun collecting and storing clinical trial records for storage and analytical purposes so that medical and clinical practitioners can refer to them on a centralized database over the internet and stay updated with the current clinical information. Clinical trial records have increased significantly, making it difficult for many medical and clinical practitioners to stay updated with the latest information. To help and support medical and clinical practitioners, there is a need to build intelligent systems that can update them with the latest information in a byte-sized condensed format and, at the same time, leverage their understanding capabilities to help them make decisions. This paper describes our contribution to SemEval 2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data (NLI4CT). Our results show that there is still a need to build domainspecific models as smaller transformer-based models can be finetuned on that data and outperform foundational large language models like GPT-3.5. We also demonstrate how the performance of GPT-3.5 can be increased using few-shot prompting by leveraging the semantic similarity of the text samples and the few-shot train snippets. We will also release our code and models on open-source hosting platforms, GitHub and HuggingFace

BpHigh at SemEval-2023 Task 7: Can Fine-tuned Cross-encoders Outperform GPT-3.5 in NLI Tasks on Clinical Trial Data?

The computational identification of human values is a novel and challenging research that holds the potential to offer valuable insights into the nature of human behavior and cognition. This paper presents the methodology adopted by the Arthur-Caplan research team for the SemEval-2023 Task 4, which entailed the detection of human values behind arguments. The proposed system integrates BERT, ERNIE2.0, RoBERTA and XLNet models with fine tuning. Experimental results show that the macro F1 score of our system achieved 0.512, which overperformed baseline methods by 9.2% on the test set.

Arthur Caplan at SemEval-2023 Task 4: Enhancing Human Value Detection through Fine-tuned Pre-trained Models

Introduction to our submission to SemEval-2023 Task 10: Explainable Detection of Online Sexism by Fine-tuning Language Model Ensembles.


UIRISC at SemEval-2023 Task 10: Explainable Detection of Online Sexism by Ensembling Fine-tuning Language Models

The class imbalance problem can cause machine learning models to produce an undesirable performance on the minority class as well as the whole dataset. Using data augmentation techniques to increase the number of samples is one way to tackle this problem. We introduce a novel counterfactual data augmentation by verb replacement for the identification of medical claims. In addition, we investigate the impact of this method and compare it with 3 other data augmentation techniques, showing that the proposed method can result in a significant (relative) improvement in the minority class.

CAISA at SemEval-2023 Task 8: Counterfactual Data Augmentation for Mitigating Class Imbalance in Causal Claim Identification

Our study describes a multilingual persuasion detection system "ReDASPersuasion" that incorporates persuasion technique attributes for a multi-label classification task. The proposed method combines language agnostic feature embeddings with sequence classification using pre-trained multilingual transformers. It supports a total of 100 languages, guaranteed by the multilingual transformer module and the Google translator interface. Our persuasion system outperforms the SemEval Task 3 Substak3 baseline in all languages, except zero shot prediction languages, which was not the main focus of our research. With the highest F1-Micro score of 0.45 for Italian, it achieved the eighth position on the official leaderboard before the end of the test phase. The reopening of the leaderboard allowed us to improve the "ReDASPersuasion" system's classification which got us currently ranked second in both Italian and French.

Team ReDASPersuasion at SemEval-2023 Task 3: Persuasion Detection Using Multilingual Transformers and Language Agnostic Features

Literature permeates almost every facet of our lives, whether through books, magazines, or in- ternet articles. Moreover, every piece of written work contains ideas and opinions that we tend to relate to, accept or disregard, the debate over, or enlighten ourselves. However, the existence of subtle themes that are difficult to discern inspired us to utilize four machine learning al- gorithms: Decision Trees, Random Forest, Lo- gistic Regression, and Support Vector Classifier (SVC) to aid in their detection. Trained on the ValueEval data set as a multi-label classifica- tion problem, the supervised machine learning models did not perform as well as expected, with F1 metrics hovering from 0.0 to 0.04 for each value. Noting this, our paper discusses our approach’s limitations and weaknesses.

Friedrich Nietzsche at SemEval-2023 Task 4: Detection of Human Values from Text Using Machine Learning

In this presentation, we introduce our approach to Visual Word Sense Disambiguation (Visual-WSD) which leverages prompt engineering, text-to-image systems, and CLIP for evaluation. We compare the performance of GLIDE and DALL-E 2 as text-to-image systems, utilizing Simple and Generated prompts, with the evaluation carried out through the CLIP model. Our research highlights the effectiveness of image modality over cross-modality for Visual-WSD tasks and shows DALL-E 2's superior performance in image generation. The presentation provides insights into the potential of our approach and opens up new avenues for further development in multimodal word sense disambiguation.

Downloads

Next from ACL 2023

DCU at SemEval-2023 Task 10: A Comparative Analysis of Encoder-only and Decoder-only Language Models with Insights into Interpretability

Similar lecture

Addressing Entity Translation Problem via Translation Difficulty and Context Diversity

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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 ACL 2023

DCU at SemEval-2023 Task 10: A Comparative Analysis of Encoder-only and Decoder-only Language Models with Insights into Interpretability

Similar lecture

Addressing Entity Translation Problem via Translation Difficulty and Context Diversity

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads