Canada

Large neural networks can now generate jokes, but do they really &quot;understand&quot; humor? We challenge AI models with three tasks derived from the New Yorker Cartoon Caption Contest: matching a joke to a cartoon, identifying a winning caption, and explaining why a winning caption is funny. These tasks encapsulate progressively more sophisticated aspects of &quot;understanding&quot; a cartoon; key elements are the complex, often surprising relationships between images and captions and the frequent inclusion of indirect and playful allusions to human experience and culture. We investigate both multimodal and language-only models: the former are challenged with the cartoon images directly, while the latter are given multifaceted descriptions of the visual scene to simulate human-level visual understanding. We find that both types of models struggle at all three tasks. For example, our best multimodal models fall 30 accuracy points behind human performance on the matching task, and, even when provided ground-truth visual scene descriptors, human-authored explanations are preferred head-to-head over the best machine-authored ones (few-shot GPT-4) in more than 2/3 of cases. We release models, code, leaderboard, and corpus, which includes newly-gathered annotations describing the image&#39;s locations/entities, what&#39;s unusual in the scene, and an explanation of the joke.

&lt;iframe src=&quot;https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/ab1ce0cc-64eb-4a96-8042-9d9d0da715fe&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Do Androids Laugh at Electric Sheep? Humor &quot;Understanding&quot; Benchmarks from The New Yorker Caption Contest

humor

vision and language

benchmark

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community."<br>

*Message from the General Chair, Dirk Hovy*





<br>

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Large neural networks can now generate jokes, but do they really "understand" humor? We challenge AI models with three tasks derived from the New Yorker Cartoon Caption Contest: matching a joke to a cartoon, identifying a winning caption, and explaining why a winning caption is funny. These tasks encapsulate progressively more sophisticated aspects of "understanding" a cartoon; key elements are the complex, often surprising relationships between images and captions and the frequent inclusion of indirect and playful allusions to human experience and culture. We investigate both multimodal and language-only models: the former are challenged with the cartoon images directly, while the latter are given multifaceted descriptions of the visual scene to simulate human-level visual understanding. We find that both types of models struggle at all three tasks. For example, our best multimodal models fall 30 accuracy points behind human performance on the matching task, and, even when provided ground-truth visual scene descriptors, human-authored explanations are preferred head-to-head over the best machine-authored ones (few-shot GPT-4) in more than 2/3 of cases. We release models, code, leaderboard, and corpus, which includes newly-gathered annotations describing the image's locations/entities, what's unusual in the scene, and an explanation of the joke.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/ab1ce0cc-64eb-4a96-8042-9d9d0da715fe" width="300" height="400"></iframe>

Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest

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.

Automatic postediting (APE) is an automated process to refine a given machine translation (MT).Recent findings present that existing APE systems are not good at handling high-quality MTs even for a language pair with abundant data resources, EnglishGerman: the better the given MT is, the harder it is to decide what parts to edit and how to fix these errors.One possible solution to this problem is to instill deeper knowledge about the target language into the model.Thus, we propose a linguistically motivated method of regularization that is expected to enhance APE models' understanding of the target language: a loss function that encourages symmetric self-attention on the given MT.Our analysis of experimental results demonstrates that the proposed method helps improving the state-of-the-art architecture's APE quality for high-quality MTs.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/457b6ae2-fc3d-4b1b-ada4-51956cfdfba5" width="300" height="400"></iframe>

Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations

Improving text representation has attracted much attention to achieve expressive text-to-speech (TTS). However, existing works only implicitly learn the prosody with masked token reconstruction tasks, which leads to low training efficiency and difficulty in prosody modeling. We propose CLAPSpeech, a cross-modal contrastive pre-training framework that learns from the prosody variance of the same text token under different contexts. Specifically, 1) with the design of a text encoder and a prosody encoder, we encourage the model to connect the text context with its corresponding prosody pattern in the joint multi-modal space; 2) we introduce a multi-scale pre-training pipeline to capture prosody patterns in multiple levels. 3) we show how to incorporate CLAPSpeech into existing TTS models for better prosody. Experiments on three datasets not only show that CLAPSpeech could improve the prosody prediction for existing TTS methods, but also demonstrate its generalization ability to adapt to multiple languages and multi-speaker text-to-speech. We also deeply analyze the principle behind the performance of CLAPSpeech. Ablation studies demonstrate the necessity of each component in CLAPSpeech. Source code and audio samples are available at https://clapspeech.github.io.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/64234b5a-84a7-4291-bdd7-d32b6815b20a" width="300" height="400"></iframe>

CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-Training

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the MT model, trading inference speed at the cost of the translation quality. In this paper, we propose to address the problem from the point of view of decoding algorithms, as a less explored but rather compelling direction. We propose to reframe the standard greedy autoregressive decoding of MT with a parallel formulation leveraging Jacobi and Gauss-Seidel fixed-point iteration methods for fast inference.This formulation allows to speed up existing models without training or modifications while retaining translation quality. We present three parallel decoding algorithms and test them on different languages and models showing how the parallelization introduces a speedup up to 38% w.r.t. the standard autoregressive decoding and nearly 2x when scaling the method on parallel resources. Finally, we introduce a decoding dependency graph visualizer (DDGviz) that let us see how the model has learned the conditional dependence between tokens and inspect the decoding procedure.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/ae9f496c-d2d8-46b4-b95e-96bc10d1c52b" width="300" height="400"></iframe>

Accelerating Transformer Inference for Translation via Parallel Decoding

Faithfully correcting factual errors is critical for maintaining the integrity of textual knowledge bases and preventing hallucinations in sequence-to-sequence models. Drawing on humans' ability to identify and correct factual errors, we present a zero-shot framework that formulates questions about input claims, looks for correct answers in the given evidence, and assesses the faithfulness of each correction based on its consistency with the evidence. Our zero-shot framework outperforms fully-supervised approaches, as demonstrated by experiments on the FEVER and SciFact datasets, where our outputs are shown to be more faithful. More importantly, the decomposability nature of our framework inherently provides interpretability. Additionally, to reveal the most suitable metrics for evaluating factual error corrections, we analyze the correlation between commonly used metrics with human judgments in terms of three different dimensions regarding intelligibility and faithfulness.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/7108567f-b29e-43f6-bfea-1944c0140de8" width="300" height="400"></iframe>

Zero-shot Faithful Factual Error Correction

Utilizing language models (LMs) without internal access is becoming an attractive paradigm in the field of NLP as many cutting-edge LMs are released through APIs and boast a massive scale.The de-facto method in this type of black-box scenario is known as prompting, which has shown progressive performance enhancements in situations where data labels are scarce or unavailable.Despite their efficacy, they still fall short in comparison to fully supervised counterparts and are generally brittle to slight modifications.In this paper, we propose Clustering-enhanced Linear Discriminative Analysis (CELDA), a novel approach that improves the text classification accuracy with a very weak-supervision signal (i.e., name of the labels).Our framework draws a precise decision boundary without accessing weights or gradients of the LM model or data labels.The core ideas of CELDA are twofold:(1) extracting a refined pseudo-labeled dataset from an unlabeled dataset, and (2) training a lightweight and robust model on the top of LM, which learns an accurate decision boundary from an extracted noisy dataset.Throughout in-depth investigations on various datasets, we demonstrated that CELDA reaches new state-of-the-art in weakly-supervised text classification and narrows the gap with a fully-supervised model.Additionally, our proposed methodology can be applied universally to any LM and has the potential to scale to larger models, making it a more viable option for utilizing large LMs.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/c95e4122-5916-4a78-9484-692c481ce0f1" width="300" height="400"></iframe>

CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels

As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of factual correctness. Generating unfactual texts not only leads to lower performances but also degrades the trust and validity of their applications. Chain-of-Thought (CoT) prompting improves trust and model performance on complex reasoning tasks by generating interpretable reasoning chains, but still suffers from factuality concerns in knowledge-intensive tasks. In this paper, we propose the Verify-and-Edit framework for CoT prompting, which seeks to increase prediction factuality by post-editing reasoning chains according to external knowledge. Building on top of GPT-3, our framework lead to accuracy improvements in multiple open-domain question-answering tasks.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/2d9fcefe-d16b-4d68-82a5-1b1c03dc0719" width="300" height="400"></iframe>

Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework

Document-level Event Causality Identification (DECI) aims to extract causal relations between events in a document. It challenges conventional sentence-level task (SECI) with difficult long-text understanding. In this paper, we propose a novel DECI model (SENDIR) for better document-level reasoning. Different from existing works that build an event graph via linguistic tools, SENDIR does not require any prior knowledge. The basic idea is to discriminate event pairs in the same sentence or span multiple sentences by assuming their different information density: 1) low density in the document suggests sparse attention to skip irrelevant information. Our module 1 designs various types of attention for event representation learning to capture long-distance dependence. 2) High density in a sentence makes SECI relatively easy. Module 2 uses different weights to highlight the roles and contributions of intra- and inter-sentential reasoning, which introduces supportive event pairs for joint modeling. Extensive experiments demonstrate great improvements in SENDIR and the effectiveness of various sparse attention for document-level representations. Codes will be released later.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/6eb8b0c7-1c26-4ca6-9478-21f37203d3b3" width="300" height="400"></iframe>

Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction

Predicting how a user responds to news events enables important applications such as allowing intelligent agents or content producers to estimate the effect on different communities and revise unreleased messages to prevent unexpected bad outcomes such as social conflict and moral injury. We present a new task, Response Forecasting on Personas for News Media, to estimate the response a persona (characterizing an individual or a group) might have upon seeing a news message. Compared to the previous efforts which only predict generic comments to news, the proposed task not only introduces personalization in the modeling but also predicts the sentiment polarity and intensity of each response. This enables more accurate and comprehensive inference on the mental state of the persona. Meanwhile, the generated sentiment dimensions make the evaluation and application more reliable. We create the first benchmark dataset, which consists of 13,357 responses to 3,847 news headlines from Twitter. We further evaluate the SOTA neural language models with our dataset. The empirical results suggest that the included persona attributes are helpful for the performance of all response dimensions. Our analysis shows that the best-performing models are capable of predicting responses that are consistent with the personas, and as a byproduct, the task formulation also enables many interesting applications in the analysis of social network groups and their opinions, such as the discovery of extreme opinion groups.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/2f11f8d9-30b4-4c7b-b4f9-360c3df07feb" width="300" height="400"></iframe>

Measuring the Effect of Influential Messages on Varying Personas

Recent advances in NLP have led to the creation of powerful language models for many languages including Ancient Greek and Latin. While prior work on Classical languages unanimously uses BERT, in this work we create four language models for Ancient Greek that vary along two dimensions to study their versatility for tasks of interest for Classical languages: we explore (i) encoder-only and encoder-decoder architectures using RoBERTa and T5 as strong model types, and create for each of them (ii) a monolingual Ancient Greek and a multilingual instance that includes Latin and English. We evaluate all models on morphological and syntactic tasks, including lemmatization, which demonstrates the added value of T5's decoding abilities. We further define two probing tasks to investigate the knowledge acquired by models pre-trained on Classical texts. Our experiments provide the first benchmarking analysis of existing models of Ancient Greek. Results show that our models provide significant improvements over the SoTA. The systematic analysis of model types can inform future research in designing language models for Classical languages, including the development of novel generative tasks. We make all our models available as community resources, along with a large curated pre-training corpus for Ancient Greek, to support the creation of a larger, comparable model zoo for Classical Philology.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/a5631409-142d-4904-8a18-e258e83c335b" width="300" height="400"></iframe>

Exploring Large Language Models for Classical Philology

Many state-of-the-art natural language understanding (NLU) models are based on pretrained neural language models. These models often make inferences using information from multiple sources. An important class of such inferences are those that require both background knowledge, presumably contained in a model's pretrained parameters, and instance-specific information that is supplied at inference time. However, the integration and reasoning abilities of NLU models in the presence of multiple knowledge sources have been largely understudied. In this work, we propose a test suite of coreference resolution subtasks that require reasoning over multiple facts. These subtasks differ in terms of which knowledge sources contain the relevant facts. We also introduce subtasks where knowledge is present only at inference time using fictional knowledge. We evaluate state-of-the-art coreference resolution models on our dataset. Our results indicate that several models struggle to reason on-the-fly over knowledge observed both at pretrain time and at inference time. However, with task-specific training, a subset of models demonstrates the ability to integrate certain knowledge types from multiple sources. Still, even the best performing models seem to have difficulties with reliably integrating knowledge presented only at inference time.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/72e5d22b-0305-45f7-bb9c-69257f39c751" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations

Similar lecture

Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs