Canada

We present the first unified study of the efficiency of self-attention-based Transformer variants spanning text, speech and vision. We identify input length thresholds (tipping points) at which efficient Transformer variants become more efficient than vanilla models, using a variety of efficiency metrics (latency, throughput, and memory). To conduct this analysis for speech, we introduce L-HuBERT, a novel local-attention variant of a self-supervised speech model. We observe that these thresholds are (a) much higher than typical dataset sequence lengths and (b) dependent on the metric and modality, showing that choosing the right model depends on modality, task type (long-form vs. typical context) and resource constraints (time vs. memory). By visualising the breakdown of the computational costs for transformer components, we also show that non-self-attention components exhibit significant computational costs. We release our profiling toolkit at https://github.com/ajd12342/profiling-transformers .

&lt;iframe src=&quot;https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/505e7c4e-27e9-4caa-ba59-3da55497a73b&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants

efficiency

multimodal

transformers

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. <br><br>
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks.  Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. <br><br>

<br><br>
We wish you a wonderful conference! <br><br>
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
<br><br>
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing)<br>
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing)<br>
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)


ACL 2022

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 (NLP). 

We present the first unified study of the efficiency of self-attention-based Transformer variants spanning text, speech and vision. We identify input length thresholds (tipping points) at which efficient Transformer variants become more efficient than vanilla models, using a variety of efficiency metrics (latency, throughput, and memory). To conduct this analysis for speech, we introduce L-HuBERT, a novel local-attention variant of a self-supervised speech model. We observe that these thresholds are (a) much higher than typical dataset sequence lengths and (b) dependent on the metric and modality, showing that choosing the right model depends on modality, task type (long-form vs. typical context) and resource constraints (time vs. memory). By visualising the breakdown of the computational costs for transformer components, we also show that non-self-attention components exhibit significant computational costs. We release our profiling toolkit at https://github.com/ajd12342/profiling-transformers .

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/505e7c4e-27e9-4caa-ba59-3da55497a73b" width="300" height="400"></iframe>

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.

Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative that a priori seems impossible: can smaller language models (e.g., GPT-2) win over models that are orders of magnitude larger and better (e.g., GPT-3), if powered with novel commonsense distillation algorithms?The key intellectual challenge is to design a learning algorithm that achieve a competitive level of commonsense acquisition, without relying on the benefits of scale. In particular, we study generative models of commonsense knowledge, focusing on the task of generating generics, statements of commonsense facts about everyday concepts, e.g., birds can fly.We introduce I2D2, a novel commonsense distillation framework that loosely follows the Symbolic Knowledge Distillation of West et al. but breaks the dependence on the extreme-scale teacher model with two innovations: (1) the novel adaptation of NeuroLogic Decoding to enhance the generation quality of the weak, off-the-shelf language models, and (2) self-imitation learning to iteratively learn from the model's own enhanced commonsense acquisition capabilities. Empirical results suggest that scale is not the only way, as novel algorithms can be a promising alternative. Moreover, our study leads to a new corpus of generics, Gen-A-tomic, that is the largest and highest quality available to date.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/16e3972e-9c52-48dd-a6ce-5b4159a4e779" width="300" height="400"></iframe>

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation

NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not considered specific dimensions of linguistic drift that affect model performance, and they have not been validated in their ability to predict model performance at the individual example level, where such metrics are often used in practice. In this paper, we propose three dimensions of linguistic dataset drift: vocabulary, structural, and semantic drift. These dimensions correspond to content word frequency divergences, syntactic divergences, and meaning changes not captured by word frequencies (e.g. lexical semantic change). We propose interpretable metrics for all three drift dimensions, and we modify past performance prediction methods to predict model performance at both the example and dataset level for English sentiment classification and natural language inference. We find that our drift metrics are more effective than previous metrics at predicting out-of-domain model accuracies (mean 16.8% root mean square error decrease), particularly when compared to popular fine-tuned embedding distances (mean 47.7% error decrease). Fine-tuned embedding distances are much more effective at ranking individual examples by expected performance, but decomposing into vocabulary, structural, and semantic drift produces the best example rankings of all considered model-agnostic drift metrics (mean 6.7% ROC AUC increase).

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/1ceea37c-a7c9-4349-a85e-379dcdb99a38" width="300" height="400"></iframe>

Characterizing and Measuring Linguistic Dataset Drift

Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaining decent performance on downstream tasks. However, current WVLP methods use only local descriptions of images, i.e., object tags, as cross-modal anchors to construct weakly-aligned image-text pairs for pre-training. This affects the data quality and thus the effectiveness of pre-training. In this paper, we propose to directly take a small number of aligned image-text pairs as anchors, and represent each unaligned image and text by its similarities to these anchors, i.e., relative representations. We build a WVLP framework based on the relative representations, namely RELIT, which collects high-quality weakly-aligned image-text pairs from large-scale image-only and text-only data for pre-training through relative representation-based retrieval and generation. Experiments on four downstream tasks show that RELIT achieves new state-of-the-art results under the weakly supervised setting.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/3e9dce8d-58a9-40a8-bd11-1a5a076e849d" width="300" height="400"></iframe>

Weakly Supervised Vision-and-Language Pre-training with Relative Representations

Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly. In this work we introduce a novel neural language model that enforces, via inductive biases, explicit relational structures which allow for compositionality onto the output representations of pretrained language models. Specifically, the model encodes sentences into sequences of symbols (composed representations), which correspond to the nodes visited by biased random walkers on a global latent graph, and infers the posterior distribution of the latter. We first demonstrate that the model is able to uncover ground-truth graphs from artificially generated datasets of random token sequences. Next, we leverage pretrained BERT and GPT-2 language models as encoder and decoder, respectively, to infer networks of symbols (schemata) from natural language datasets. Our experiments show that (i) the inferred symbols can be interpreted as encoding different aspects of language, as e.g. topics or sentiments, and that (ii) GPT-2-like models can effectively be conditioned on symbolic representations. Finally, we explore training autoregressive, random walk "reasoning" models on schema networks inferred from commonsense knowledge databases, and using the sampled paths to enhance the performance of pretrained language models on commonsense If-Then reasoning tasks.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/c3e84480-8291-4d6d-ba48-bf734c1d7cba" width="300" height="400"></iframe>

Hidden Schema Networks

Document-level multi-event extraction aims to extract the structural information from a given document automatically. Most recent approaches usually involve two steps: (1) modeling entity interactions; (2) decoding entity interactions into events. However, such approaches ignore a global view of inter-dependency of multiple events. Moreover, an event is decoded by iteratively merging its related entities as arguments, which might suffer from error propagation and is computationally inefficient. In this paper, we propose an alternative approach for document-level multi-event extraction with event proxy nodes and Hausdorff distance minimization. The event proxy nodes, representing pseudo-events, are able to build connections with other event proxy nodes, essentially capturing global information. The Hausdorff distance makes it possible to compare the similarity between the set of predicted events and the set of ground-truth events. By directly minimizing Hausdorff distance, the model is trained towards the global optimum directly, which improves performance and reduces training time. Experimental results show that our model outperforms previous state-of-the-art method in F1-score on two datasets with only a fraction of training time.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/65454448-f53a-490a-b9b1-f634753317d2" width="300" height="400"></iframe>

Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization

In this study, we create a CConS (Counter-commonsense Contextual Size comparison) dataset to investigate how physical commonsense affects the contextualized size comparison task; the proposed dataset consists of both contexts that fit physical commonsense and those that do not.This dataset tests the ability of language models to predict the size relationship between objects under various contexts generated from our curated noun list and templates.We measure the ability of several masked language models and encoder-decoder models.The results show that while large language models can use prepositions such as "in" and "into" in the provided context to infer size relationships, they fail to use verbs and thus make incorrect judgments led by their prior physical commonsense.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/09a79136-8dbf-4430-8786-2cc35832e0aa" width="300" height="400"></iframe>

Probing Physical Reasoning with Counter-Commonsense Context

The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption.While the pre-trained models can perform many tasks, such models are often fine-tuned to improve their performance on various downstream applications.However, this leads to issues over violation of model licenses, model theft, and copyright infringement.Moreover, recent advances show that generative technology is capable of producing harmful content which exacerbates the problems of accountability within model supply chains.Thus, we need a method to investigate how a model was trained or a piece of text was generated and what their pre-trained base model was.In this paper we take the first step to address this open problem by tracing back the origin of a given fine-tuned LLM to its corresponding pre-trained base model. We consider different knowledge levels and attribution strategies, and find that we can correctly trace back 8 out of the 10 fine tuned models with our best method.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/7a4767e7-a7b8-4739-8d12-ac6bc9ad58f0" width="300" height="400"></iframe>

Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models

Humans are storytellers, even in communication scenarios which are assumed to be more rationality-oriented, such as argumentation. Indeed, supporting arguments with narratives or personal experiences (henceforth, stories) is a very natural thing to do -- and yet, this phenomenon is largely unexplored in computational argumentation. Which role do stories play in an argument? Do they make the argument more effective? What are their narrative properties? To address these questions, we collected and annotated StoryARG, a dataset sampled from well-established corpora in computational argumentation (ChangeMyView and RegulationRoom), and the Social Sciences (Europolis), as well as comments to New York Times articles. StoryARG contains 2451 textual spans annotated at two levels. At the argumentative level, we annotate the function of the story (e.g., clarification, disclosure of harm, search for a solution, establishing speaker's authority), as well as its impact on the effectiveness of the argument and its emotional load. At the level of narrative properties, we annotate whether the story has a plot-like development, is factual or hypothetical, and who the protagonist is.What makes a story effective in an argument? Our analysis of the annotations in StoryARG uncover a positive impact on effectiveness for stories which illustrate a solution to a problem, and in general, annotator-specific preferences that we investigate with regression analysis.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/3ce47d23-c9a9-4cd2-94e3-8d262259e403" width="300" height="400"></iframe>

StoryARG: a corpus of narratives and personal experiences in argumentative texts

Morphological inflection is a popular task in sub-word NLP with both practical and cognitive applications. For years now, state-of-the-art systems have reported high, but also highly variable, performance across data sets and languages. We investigate the causes of this high performance and high variability; we find several aspects of data set creation and evaluation which systematically inflate performance and obfuscate differences between languages. To improve generalizability and reliability of results, we propose new data sampling and evaluation strategies that better reflect likely use-cases. Using these new strategies, we make new observations on the generalization abilities of current inflection systems.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/cc20faa1-92ab-4900-8a4b-a177b4a577eb" width="300" height="400"></iframe>

Morphological Inflection: A Reality Check

In this paper, we examine the current state-of-the-art in AMR parsing, which relies on ensemble strategies by merging multiple graph predictions. Our analysis reveals that the present models often violate AMR structural constraints. To address this issue, we develop a validation method, and show how ensemble models can exploit SMATCH metric weaknesses to obtain higher scores, but sometimes result in corrupted graphs. Additionally, we highlight the demanding need to compute the SMATCH score among all possible predictions. To overcome these challenges, we propose two novel ensemble strategies based on Transformer models, improving robustness to structural constraints, while also reducing the computational time. Our methods provide new insights for enhancing AMR parsers and metrics. Our code is available at [https://www.github.com/babelscape/AMRs-Assemble](https://www.github.com/babelscape/AMRs-Assemble).

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/0065a6bd-a5e7-46e7-8e40-f42476c1cbd8" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation

Similar lecture

On the Locality of Attention in Direct Speech Translation