Canada

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the pre-trained models grow bigger (e.g., 175B parameters for GPT-3), even the fine-tuning process can be time-consuming and computationally expensive; (b) the fine-tuned model has the same size as its starting point by default, which is neither sensible due to its more specialized functionality, nor practical since many fine-tuned models will be deployed in resource-constrained environments. To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning - by enforcing sparsity-aware low-rank updates on top of the pre-trained weights; and (ii) resource-efficient inference - by encouraging a sparse weight structure towards the final fine-tuned model. We leverage sparsity in these two directions by exploiting both unstructured and structured sparse patterns in pre-trained language models viaa unified approach. Extensive experiments and in-depth investigations, with diverse network backbones (i.e., BERT, RoBERTa, and GPT-2) on dozens of datasets, consistently demonstrate impressive parameter-/inference-efficiency, while maintaining competitive downstream performance. For instance, DSEE saves about 25% inference FLOPs while achieving comparable performance, with 0.5% trainable parameters on BERT. Codes are available at https://github.com/VITA-Group/DSEE.

&lt;iframe src=&quot;https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/c2402fcc-1768-4d70-a98c-f10d615400a1&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

matrix decomposition

low-rank

sparsity

### 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.

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the pre-trained models grow bigger (e.g., 175B parameters for GPT-3), even the fine-tuning process can be time-consuming and computationally expensive; (b) the fine-tuned model has the same size as its starting point by default, which is neither sensible due to its more specialized functionality, nor practical since many fine-tuned models will be deployed in resource-constrained environments. To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning - by enforcing sparsity-aware low-rank updates on top of the pre-trained weights; and (ii) resource-efficient inference - by encouraging a sparse weight structure towards the final fine-tuned model. We leverage sparsity in these two directions by exploiting both unstructured and structured sparse patterns in pre-trained language models viaa unified approach. Extensive experiments and in-depth investigations, with diverse network backbones (i.e., BERT, RoBERTa, and GPT-2) on dozens of datasets, consistently demonstrate impressive parameter-/inference-efficiency, while maintaining competitive downstream performance. For instance, DSEE saves about 25% inference FLOPs while achieving comparable performance, with 0.5% trainable parameters on BERT. Codes are available at https://github.com/VITA-Group/DSEE.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/c2402fcc-1768-4d70-a98c-f10d615400a1" width="300" height="400"></iframe>

poster

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack.Generally, adversarial purification aims to remove the adversarial perturbations therefore can make correct predictions based on the recovered clean samples.Despite the success of adversarial purification in the computer vision field that incorporates generative models such as energy-based models and diffusion models,using purification as a defense strategy against textual adversarial attacks is rarely explored.In this work, we introduce a novel adversarial purification method that focuses on defending against textual adversarial attacks.With the help of language models, we can inject noise by masking input texts and reconstructing the masked texts based on the masked language models.In this way, we construct an adversarial purification process for textual models against the most widely used word-substitution adversarial attacks.We test our proposed adversarial purification method on several strong adversarial attack methods including Textfooler and BERT-Attack and experimental results indicate that the purification algorithm can successfully defend against strong word-substitution attacks.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/70d54338-f1cf-4d26-bf49-5ad26b7c76da" width="300" height="400"></iframe>

Text Adversarial Purification as Defense against Adversarial Attacks

The ability to infer pre- and postconditions of an action is vital for comprehending complex instructions, and is essential for applications such as autonomous instruction-guided agents and assistive AI that supports humans to perform physical tasks.In this work, we propose a task dubbed action condition inference, which extracts mentions of preconditions and postconditions of actions in instructional manuals.We propose a weakly supervised approach utilizing automatically constructed large-scale training instances from online instructions, and curate a densely human-annotated and validated dataset to study how well the current NLP models do on the proposed task.We design two types of models differ by whether contextualized and global information is leveraged, as well as various combinations of heuristics to construct the weak supervisions.Our experiments show a > 20% F1-score improvement with considering the entire instruction contexts and a >~6% F1-score benefit with the proposed heuristics. However, the best performing model is still well-behind human performance.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/ae782320-7225-4ca5-bca1-6656d560cfda" width="300" height="400"></iframe>

Learning Action Conditions from Instructional Manuals for Instruction Understanding

With the rapid growth of Massive Open Online Courses (MOOCs), it is expensive and time-consuming to extract high-quality knowledgeable concepts taught in the course by human effort to help learners grasp the essence of the course. In this paper, we propose to automatically extract course concepts using distant supervision to eliminate the heavy work of human annotations, which generates labels by matching them with an easily accessed dictionary. However, this matching process suffers from severe noisy and incomplete annotations because of the limited dictionary and diverse MOOCs. To tackle these challenges, we present a novel three-stage framework DS-MOCE, which leverages the power of pre-trained language models explicitly and implicitly and employs discipline-embedding models with a self-train strategy based on label generation refinement across different domains. We also provide an expert-labeled dataset spanning 20 academic disciplines. Experimental results demonstrate the superiority of DS-MOCE over the state-of-the-art distantly supervised methods (with 7% absolute F1 score improvement). Code and data are now available at https://github.com/THU-KEG/MOOC-NER.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/98fb5752-7171-4967-b251-a04f5b371e02" width="300" height="400"></iframe>

Distantly Supervised Course Concept Extraction in MOOCs with Academic Discipline

Meta-learning has emerged as a trending technique to tackle few-shot text classication and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semantics of sampled classes are distinct while failing to differentiate classes with similar semantics. In this paper, we propose a novel Task-Adaptive Reference Transformation (TART) network, aiming to enhance the generalization by transforming the class prototypes to per-class fixed reference points in task-adaptive metric spaces. To further maximize divergence between transformed prototypes in task-adaptive metric spaces, TART introduces a discriminative reference regularization among transformed prototypes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, our model surpasses the state-of-the-art method by 7.4% and 5.4% in 1-shot and 5-shot classification on the 20 Newsgroups dataset, respectively.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/32c8bd65-247f-4098-ab39-2dbdc12d1a4d" width="300" height="400"></iframe>

TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation

Peer review constitutes a core component of scholarly publishing; yet it demands substantial expertise and training, and is susceptible to errors and biases. Various applications of NLP for peer reviewing assistance aim to support reviewers in this complex process, but the lack of clearly licensed datasets and multi-domain corpora prevent the systematic study of NLP for peer review. To remedy this, we introduce NLPeer-- the first ethically sourced multidomain corpus of more than 5k papers and 11k review reports from five different venues. In addition to the new datasets of paper drafts, camera-ready versions and peer reviews from the NLP community, we establish a unified data representation and augment previous peer review datasets to include parsed and structured paper representations, rich metadata and versioning information. We complement our resource with implementations and analysis of three reviewing assistance tasks, including a novel guided skimming task.Our work paves the path towards systematic, multi-faceted, evidence-based study of peer review in NLP and beyond. The data and code are publicly available.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/416be0c5-3a21-4bb9-a126-1f886599ff2f" width="300" height="400"></iframe>

NLPeer: A Unified Resource for the Computational Study of Peer Review

Humans often make creative use of words to expressnovel senses. A long-standing effort in natural language processing hasbeen focusing on word sense disambiguation (WSD), but little has been explored about how the sense inventory of a word may be extended toward novel meanings. We present a paradigm of word sense extension (WSE) thatenables words to spawn new senses toward novel context. We develop a framework that simulates novel word sense extension by first partitioning a polysemous word type into two pseudo-tokens that mark its different senses, and then inferring whether the meaning of a pseudo-token can be extended to convey the sense denoted by the token partitioned from the same word type. Our framework combines cognitivemodels of chaining with a learning scheme that transforms a language model embedding space to supportvarious types of word sense extension. We evaluate our frameworkagainst several competitive baselines and show that it is superior in predicting plausible novel senses for over 7,500 English words. Furthermore, we show that our WSE framework improves performance over a range of transformer-based WSD models in predicting rare word senses with few or zero mentions in the training data.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/08cd63c0-282a-42de-81a7-a1d606c0e438" width="300" height="400"></iframe>

Word sense extension

Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e.g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress.This paper presents a thorough empirical study, a unified view of ED models, and a better unified baseline. For fair evaluation, we compare 12 representative methods on three datasets, which are roughly grouped into prompt-based and prototype-based models for detailed analysis. Experiments consistently demonstrate that prompt-based methods, including ChatGPT, still significantly trail prototype-based methods in terms of overall performance. To investigate their superior performance, we break down their design elements along several dimensions and build a unified framework on prototype-based methods. Under such unified view, each prototype-method can be viewed a combination of different modules from these design elements. We further combine all advantageous modules and propose a simple yet effective baseline, which outperforms existing methods by a large margin (e.g., 2.7% F1 gains under low-resource setting).

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/b9f02f72-e092-4bae-859a-100ee29949b8" width="300" height="400"></iframe>

Few-shot Event Detection: An Empirical Study and a Unified View

Adversarial attacks on deep neural networks keep raising security concerns in natural language processing research. Existing defenses focus on improving the robustness of the victim model in the training stage. However, they often neglect to proactively mitigate adversarial attacks during inference. Towards this overlooked aspect, we propose a defense framework that aims to mitigate attacks by confusing attackers and correcting adversarial contexts that are caused by malicious perturbations. Our framework comprises three components: (1) a synonym-based transformation to randomly corrupt adversarial contexts in the word level, (2) a developed BERT defender to correct abnormal contexts in the representation level, and (3) a simple detection method to filter out adversarial examples, any of which can be flexibly combined. Additionally, our framework helps improve the robustness of the victim model during training. Extensive experiments demonstrate the effectiveness of our framework in defending against word-level adversarial attacks.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/f9257d9d-ebf5-4d55-bb4f-5bcc9c51b2f8" width="300" height="400"></iframe>

RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial Attacks

We present CrossSum, a large-scale cross-lingual summarization dataset comprising 1.68 million article-summary samples in 1,500+ language pairs. We create CrossSum by aligning parallel articles written in different languages via cross-lingual retrieval from a multilingual abstractive summarization dataset and perform a controlled human evaluation to validate its quality. We propose a multistage data sampling algorithm to effectively train a cross-lingual summarization model capable of summarizing an article in any target language. We also introduce LaSE, an embedding-based metric for automatically evaluating model-generated summaries. LaSE is strongly correlated with ROUGE and, unlike ROUGE, can be reliably measured even in the absence of references in the target language. Performance on ROUGE and LaSE indicate that our proposed model consistently outperforms baseline models. To the best of our knowledge, CrossSum is the largest cross-lingual summarization dataset and the first ever that is not centered around English. We are releasing the dataset, training and evaluation scripts, and models to spur future research on cross-lingual summarization. The resources can be found at https://github.com/csebuetnlp/CrossSum

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/30709ff4-66c2-4380-9c7a-6c5f78a8e551" width="300" height="400"></iframe>

CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs

Jointly fine-tuning a Pre-trained Language Model (PLM) on a pre-defined set of tasks with in-context instructions has been proven to improve its generalization performance, allowing us to build a universal language model that can be deployed across task boundaries. In this work, we explore for the first time whether this attractive property of in-context instruction learning can be extended to a scenario in which tasks are fed to the target PLM in a sequential manner. The primary objective of so-called lifelong in-context instruction learning is to improve the target PLM's instance- and task-level generalization performance as it observes more tasks. DynaInst, the proposed method to lifelong in-context instruction learning, achieves noticeable improvements in both types of generalization, nearly reaching the upper bound performance obtained through joint training.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/6a149207-63ab-40fb-a359-e9e63fcebf71" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Text Adversarial Purification as Defense against Adversarial Attacks

Similar lecture

Parameter-Efficient Fine-Tuning without Introducing New Latency