Canada

We train neural networks to optimize a Minimum Description Length score, i.e., to balance between the complexity of the network and its accuracy at a task. We show that networks optimizing this objective function master tasks involving memory challenges and go beyond context-free languages. These learners master languages such as $a^nb^n$, $a^nb^nc^n$, $a^nb^{2n}$, $a^nb^mc^{n+m}$, and they perform addition. Moreover, they often do so with 100% accuracy. The networks are small, and their inner workings are transparent. We thus provide formal proofs that their perfect accuracy holds not only on a given test set, but for any input sequence. To our knowledge, no other connectionist model has been shown to capture the underlying grammars for these languages in full generality.

ACL 2023

Minimum Description Length Recurrent Neural Networks

pushdown automaton

minimum description length

language induction

kolmogorov complexity

evolutionary algorithm

recurrent neural network

overfitting

regularization

formal languages

generalization

### 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. <br>Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.<br><br><br>

You are required to register for this event. <br>**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.

poster

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
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.<br>
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)**
<br><br><br><br>

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.

Design biases in NLP systems, such as performance differences for different populations, often stem from their creator's positionality, i.e., views and lived experiences shaped by identity and background. Despite the prevalence and risks of design biases, they are hard to quantify because researcher, system, and dataset positionality is often unobserved. We introduce NLPositionality, a framework for characterizing design biases and quantifying the positionality of NLP datasets and models. Our framework continuously collects annotations from a diverse pool of volunteer participants on LabintheWild, and statistically quantifies alignment with dataset labels and model predictions. We apply NLPositionality to existing datasets and models for two tasks---social acceptability and hate speech detection. To date, we have collected 16,299 annotations in over a year for 600 instances from 1,096 annotators across 87 countries.We find that datasets and models align predominantly with Western, White, college-educated, and younger populations. Additionally, certain groups, such as non-binary people and non-native English speakers, are further marginalized by datasets and models as they rank least in alignment across all tasks. Finally, we draw from prior literature to discuss how researchers can examine their own positionality and that of their datasets and models, opening the door for more inclusive NLP systems.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/aeb6cfac-79c9-4b07-8a39-d41736b2f04a" width="300" height="400"></iframe>

NLPositionality: Characterizing Design Biases of Datasets and Models

In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities in language understanding, reasoning, and reading comprehension. These PLMs have achieved impressive results on these benchmarks, even surpassing human performance in some cases. This has led to claims of superhuman capabilities and the provocative idea that certain tasks have been solved. In this position paper, we take a critical look at these claims and ask whether PLMs truly have superhuman abilities and what the current benchmarks are really evaluating. We show that these benchmarks have serious limitations affecting the comparison between humans and PLMs and provide recommendations for fairer and more transparent benchmarks.

<iframe src="https://app.sli.do/event/eX4PwSmcCc1EvCqjxcYdKB/embed/polls/9b5d2c71-bc6f-48f3-94d9-fce98604a7bb" width="300" height="400"></iframe>

What's the Meaning of Superhuman Performance in Today's NLU?

Leveraging knowledge from electronic health records (EHRs) to predict a patient's condition is essential to the effective delivery of appropriate care. Clinical notes of patient EHRs contain valuable information from healthcare professionals, but have been underused due to their difficult contents and complex hierarchies. Recently, hypergraph-based methods have been proposed for document classifications. Directly adopting existing hypergraph methods on clinical notes cannot sufficiently utilize the hierarchy information of the patient, which can degrade clinical semantic information by (1) frequent neutral words and (2) hierarchies with imbalanced distribution. Thus, we propose a taxonomy-aware multi-level hypergraph neural network (TM-HGNN), where multi-level hypergraphs assemble useful neutral words with rare keywords via note and taxonomy level hyperedges to retain the clinical semantic information. The constructed patient hypergraphs are fed into hierarchical message passing layers for learning more balanced multi-level knowledge at the note and taxonomy levels. We validate the effectiveness of TM-HGNN by conducting extensive experiments with MIMIC-III dataset on benchmark in-hospital-mortality prediction.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/a6ff4694-7c33-4bfa-b9f1-e5152cda9e97" width="300" height="400"></iframe>

Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learning

Social stereotypes negatively impact individuals' judgements about different groups and may have a critical role in understanding language directed toward marginalized groups. Here, we assess the role of social stereotypes in the automated detection of hate speech in the English language by examining the impact of social stereotypes on annotation behaviors, annotated datasets, and hate speech classifiers.  Specifically, we first investigate the impact of novice annotators' stereotypes on their hate-speech-annotation behavior. Then, we examine the effect of normative stereotypes in language on the aggregated annotators' judgements in a large annotated corpus. Finally, we demonstrate how normative stereotypes embedded in language resources are associated with systematic prediction errors in a hate-speech classifier. The results demonstrate that hate-speech classifiers reflect social stereotypes against marginalized groups which can perpetuate social inequalities when propagated at scale. This framework, combining social-psychological and computational-linguistic methods, provides insights into sources of bias in hate-speech moderation, informing ongoing debates regarding machine learning fairness.

Hate Speech Classifiers Learn Normative Social Stereotypes

Non-AutoRegressive (NAR) text generation models have drawn much attention because of their significantly faster decoding speed and good generation quality in machine translation. However, in a wider range of text generation tasks, existing NAR models lack proper pre-training, making them still far behind the pre-trained autoregressive models. In this paper, we propose Pre-trained Directed Acyclic Transformer (PreDAT) and a novel pre-training task to promote sentence-level prediction consistency in NAR generation. Experiments on five text generation tasks show that our PreDAT remarkably outperforms existing pre-trained NAR models (+4.2 scores on average) and even achieves better results than pre-trained autoregressive baselines in automatic evaluation, along with 17 times speedup in throughput. Further analysis shows that PreDAT benefits from the unbiased prediction order that alleviates the error accumulation problem in the autoregressive generation, which provides new insights into the advantages of NAR generation.

Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation

Large-scale language models, like ChatGPT, have garnered significant media attention and stunned the public with their remarkable capacity for generating coherent text from short natural language prompts. In this paper, we aim to conduct a systematic inspection of ChatGPT's performance in two controllable generation tasks, with respect to ChatGPT's ability to adapt its output to different target audiences (expert vs. layman) and writing styles (formal vs. informal). Additionally, we evaluate the faithfulness of the generated text, and compare the model's performance with human-authored texts. Our findings indicate that the stylistic variations produced by humans are considerably larger than those demonstrated by ChatGPT, and the generated texts diverge from human samples in several characteristics, such as the distribution of word types. Moreover, we observe that ChatGPT sometimes incorporates factual errors or hallucinations when adapting the text to suit a specific style.

ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer

In recent years, pre-trained language models have garnered significant attention due to their effectiveness, which stems from the rich knowledge acquired during pre-training. To mitigate the inconsistency issues between pre-training tasks and downstream tasks and to facilitate the resolution of language-related issues, prompt-based approaches have been introduced, which are particularly useful in low-resource scenarios. However, existing approaches mostly rely on verbalizers to translate the predicted vocabulary to task-specific labels. The major limitations of this approach are the ignorance of potentially relevant domain-specific words and being biased by the pre-training data. To address these limitations, we propose a framework that incorporates conceptual knowledge for text classification in the extreme zero-shot setting. The framework includes prompt-based keyword extraction, weight assignment to each prompt keyword, and final representation estimation in the knowledge graph embedding space. We evaluated the method on four widely-used datasets for sentiment analysis and topic detection, demonstrating that it consistently outperforms recently-developed prompt-based approaches in the same experimental settings.

Prompt-based Zero-shot Text Classification with Conceptual Knowledge

The goal of portfolio management is to maximize investment returns while reducing investment risk. Reinforcement learning-based portfolio management continuously seeks characteristics in past data to maximize returns. Existing financial text information processing methods are not optimized for investment decision events, making it difficult to accurately reflect the actual impact of financial text information on investment. Additionally, differences in the quality of financial text information result in noisy data. In view of these limitations, this research proposal has two main goals. The first goal is to find effective ways to extract signals present in the financial news and the second goal is to eventually use the signals from the news articles to improve portfolio management. More specifically, in our proposal we focus on analysing sentiment signals from the financial news articles and we observe the effect of the sentiment scores on reinforcement learning based portfolio management approaches. We did an initial investigation to observe the effect of sentiment scores in portfolio management. In our experiments, we randomly selected eight stocks from Dow Jones Industrial Average index for experiments and verified that our model can significantly improve cumulative returns 117.3% while reduce max drawdown 15.2%. It greatly improves the performance of reinforcement learning-based investment management methods.

Improving Portfolio Management with Signals from Financial News

This study addresses the automatic generation of distractors for English fill-in-the-blank exercises in the entrance examinations for Japanese universities. While previous studies applied the same method to all questions, actual entrance examinations have multiple question types that reflect the purpose of the questions. Therefore, we define three types of questions (grammar, function word, and context) and propose a method to generate distractors according to the characteristics of each question type. Experimental results on 500 actual questions show the effectiveness of the proposed method for both automatic and manual evaluation.

Distractor Generation for Fill-in-the-Blank Exercises by Question Type

"When Words Fail, Emojis Prevail": A Novel Architecture for Generating Sarcastic Sentences With Emoji Using Valence Reversal and Semantic Incongruity

<iframe src="https://app.sli.do/event/uyG7EHDP5trs2LHubv2Gj8/embed/polls/79f2fe57-f5d5-4b9b-9256-28c6bcc8fbdb" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

NLPositionality: Characterizing Design Biases of Datasets and Models

Similar lecture

Bridging the Empirical-Theoretical Gap in Neural Network Formal Language Learning Using Minimum Description Length

.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

NLPositionality: Characterizing Design Biases of Datasets and Models

Similar lecture

Bridging the Empirical-Theoretical Gap in Neural Network Formal Language Learning Using Minimum Description Length

Downloads