Canada

Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense. Existing solutions often rely on explicit images for visual knowledge augmentation (requiring time-consuming retrieval or generation), and they also conduct the augmentation for the whole input text, without considering whether it is actually needed in specific inputs or tasks. To address these issues, we propose a novel **V**isually-**A**ugmented fine-tuning approach that can be generally applied to various PLMs or NLP tasks, **W**ithout using any retrieved or generated **I**mages, namely **VAWI**. Experimental results show that our approach can consistently improve the performance of BERT, RoBERTa, BART, and T5 at different scales, and outperform several competitive baselines on ten tasks. Our codes and data are publicly available at https://github.com/RUCAIBox/VAWI.

&lt;iframe src=&quot;https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/8185863b-2fc0-4a15-ad8a-5bd79b2b04d3&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Visually-augmented pretrained language models for NLP tasks without images

visually-augmented language model

multimodal

pre-trained language model

### 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.

Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense. Existing solutions often rely on explicit images for visual knowledge augmentation (requiring time-consuming retrieval or generation), and they also conduct the augmentation for the whole input text, without considering whether it is actually needed in specific inputs or tasks. To address these issues, we propose a novel **V**isually-**A**ugmented fine-tuning approach that can be generally applied to various PLMs or NLP tasks, **W**ithout using any retrieved or generated **I**mages, namely **VAWI**. Experimental results show that our approach can consistently improve the performance of BERT, RoBERTa, BART, and T5 at different scales, and outperform several competitive baselines on ten tasks. Our codes and data are publicly available at https://github.com/RUCAIBox/VAWI.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/8185863b-2fc0-4a15-ad8a-5bd79b2b04d3" width="300" height="400"></iframe>

technical paper

By scaling the model size, large pre-trained language models~(PLMs) have shown remarkable performance in various natural language processing tasks, mostly outperforming small PLMs by a large margin.However, due to the high computational cost, the huge number of parameters also restricts the applicability of large PLMs in real-world systems. In this paper, we focus on scaling up the parameters of PLMs \emph{only during} fine-tuning, to benefit from the over-parameterization, while without increasing \emph{the inference latency}. Given a relatively small PLM, we over-parameterize it by employing a matrix product operator, an efficient and almost lossless decomposition method to factorize its contained parameter matrices into a set of higher-dimensional tensors.Considering the efficiency, we further propose both static and dynamic strategies to select the most important parameter matrices for over-parameterization.Extensive experiments have demonstrated that our approach can significantly boost the fine-tuning performance of small PLMs and even help small PLMs outperform $3\times$ parameterized larger ones.Our code is publicly available at \url{https://github.com/zfgao66/OPF}.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/9782798c-2a37-4e66-88f2-5aef2da37244" width="300" height="400"></iframe>

Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization

We study grammar induction with mildly context-sensitive grammars for unsupervised discontinuous parsing. Using the probabilistic linear context-free rewriting system (LCFRS) formalism, our approach fixes the rule structure in advance and focuses on parameter learning with maximum likelihood. To reduce the computational complexity of both parsing and parameter estimation, we restrict the grammar formalism to LCFRS-2 (i.e., binary LCFRS with fan-out two) and further discard rules that require O(l^6) time to parse, reducing inference to O(l^5). We find that using a large number of nonterminals is beneficial and thus make use of tensor decomposition-based rank-space dynamic programming with an embedding-based parameterization of rule probabilities to scale up the number of nonterminals. Experiments on German and Dutch show that our approach is able to induce linguistically meaningful trees with continuous and discontinuous structures.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/0861f523-8b97-4533-86bc-46d0f49795cb" width="300" height="400"></iframe>

Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars

Automatic metrics play a crucial role in machine translation. Despite the widespread use of n-gram-based metrics, there has been a recent surge in the development of pre-trained model-based metrics that focus on measuring sentence semantics. However, these neural metrics, while achieving higher correlations with human evaluations, are often considered to be black boxes with potential biases that are difficult to detect. In this study, we systematically analyze and compare various mainstream and cutting-edge automatic metrics from the perspective of their guidance for training machine translation systems. Through Minimum Risk Training (MRT), we find that certain metrics exhibit robustness defects, such as the presence of universal adversarial translations in BLEURT and BARTScore. In-depth analysis suggests two main causes of these robustness deficits: distribution biases in the training datasets, and the tendency of the metric paradigm. By incorporating token-level constraints, we enhance the robustness of evaluation metrics, which in turn leads to an improvement in the performance of machine translation systems. Codes are available at \url{https://github.com/powerpuffpomelo/fairseq_mrt}.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/b39c8006-41d4-4da3-8538-6d05e701fb06" width="300" height="400"></iframe>

BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training

We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xsim++. In comparison to xsim, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which more closely mirror the scenarios we encounter during large-scale mining. We validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages, and subsequently train NMT systems on the mined data. In comparison to xsim, we show that xsim++ is better correlated with the downstream BLEU scores of translation systems trained on mined bitexts, providing a reliable proxy of bitext mining performance without needing to run expensive bitext mining pipelines. xsim++ also reports performance for different error types, offering more fine-grained feedbacks for model development.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/61672226-98d5-40e8-b320-ca021192fc91" width="300" height="400"></iframe>

xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages

Ternary and binary neural networks enable multiplication-free computation and promise multiple orders of magnitude efficiency gains over full-precision networks if implemented on specialized hardware. However, since both the parameter and the output space are highly discretized, such networks have proven very difficult to optimize. The difficulties are compounded for the class of transformer text generation models due to the sensitivity of the attention operation to quantization and the noise-compounding effects of autoregressive decoding in the high-cardinality output space. We approach the problem with a mix of statistics-based quantization for the weights and elastic quantization of the activations and demonstrate the first ternary and binary transformer models on the downstream tasks of summarization and machine translation. Our ternary BART base achieves an R1 score of 41 on the CNN/DailyMail benchmark, which is merely 3.9 points behind the full model while being 16x more efficient. Our binary model, while less accurate, achieves a highly non-trivial score of 35.6. For machine translation, we achieved BLEU scores of 21.7 and 17.6 on the WMT16 En-Ro benchmark, compared with a full precision mBART model score of 26.8. We also compare our approach in the 8-bit activation setting, where our ternary and even binary weight models can match or outperform the best existing 8-bit weight models in the literature. Our code and models will be released.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/32236b66-016c-4a2d-b8c9-292233bc7d41" width="300" height="400"></iframe>

Binary and Ternary Natural Language Generation

Zero-shot stance detection (ZSSD) aims to determine whether the author of a text is in favor of, against, or neutral toward a target that is unseen during training. Despite the growing attention on ZSSD, most recent advances in this task are limited to English and do not pay much attention to other languages such as Chinese. To support ZSSD research, in this paper, we present C-STANCE that, to our knowledge, is the first Chinese dataset for zero-shot stance detection. We introduce two challenging subtasks for ZSSD: target-based ZSSD and domain-based ZSSD. Our dataset includes both noun-phrase targets and claim targets, covering a wide range of domains. We provide a detailed description and analysis of our dataset. To establish results on C-STANCE, we report performance scores using state-of-the-art deep learning models. We publicly release our dataset and code to facilitate future research.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/cc0a3a09-17f4-42f6-b867-d64b41d19385" width="300" height="400"></iframe>

C-STANCE: A Large Dataset for Chinese Zero-Shot Stance Detection

The task of Stance Detection is concerned with identifying the attitudes expressed by an author towards a target of interest. This task spans a variety of domains ranging from social media opinion identification to detecting the stance for a legal claim. However, the framing of the task varies within these domains in terms of the data collection protocol, the label dictionary and the number of available annotations. Furthermore, these stance annotations are significantly imbalanced on a per-topic and inter-topic basis. These make multi-domain stance detection challenging, requiring standardization and domain adaptation. To overcome this challenge, we propose Topic Efficient StancE Detection (TESTED), consisting of a topic-guided diversity sampling technique used for creating a multi-domain data efficient training set and a contrastive objective that is used for fine-tuning a stance classifier using the produced set. We evaluate the method on an existing benchmark of 16 datasets with in-domain, i.e. all topics seen and out-of-domain, i.e. unseen topics, experiments. The results show that the method outperforms the state-of-the-art with an average of 3.5 F1 points increase in-domain and is more generalizable with an averaged 10.2 F1 on out-of-domain evaluation while using <10% of the training data. We show that our sampling technique mitigates both inter- and per-topic class imbalances. Finally, our analysis demonstrates that the contrastive learning objective allows the model for a more pronounced segmentation of samples with varying labels.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/5eb2c105-2aec-45c1-89b5-b9e2b2bacd17" width="300" height="400"></iframe>

Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection

In this paper, we tackle the problem of sign language translation (SLT) without gloss annotations. Although intermediate representation like gloss has been proven effective, gloss annotations are hard to acquire, especially in large quantities. This limits the domain coverage of translation datasets, thus handicapping real-world applications. To mitigate this problem, we design the Gloss-Free End-to-end sign language translation framework (GloFE). Our method improves the performance of SLT in the gloss-free setting by exploiting the shared underlying semantics of signs and the corresponding spoken translation. Common concepts are extracted from the text and used as a weak form of intermediate representation. The global embedding of these concepts is used as a query for cross-attention to find the corresponding information within the learned visual features. In a contrastive manner, we encourage the similarity of query results between samples containing such concepts and decrease those that do not. We obtained state-of-the-art results on large-scale datasets, including OpenASL and How2Sign.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/75dad8b8-cc99-407c-8359-c3cfd33358ef" width="300" height="400"></iframe>

Gloss-Free End-to-End Sign Language Translation

To overcome the overparameterized problem in Pre-trained Language Models (PLMs), pruning is widely used as a simple and straightforward compression method by directly removing unimportant weights. Previous first-order methods successfully compress PLMs to extremely high sparsity with little performance drop. These methods, such as movement pruning, use first-order information to prune PLMs while fine-tuning the remaining weights. In this work, we argue fine-tuning is redundant for first-order pruning, since first-order pruning is sufficient to converge PLMs to downstream tasks without fine-tuning. Under this motivation, we propose Static Model Pruning (SMP), which only uses first-order pruning to adapt PLMs to downstream tasks while achieving the target sparsity level. In addition, we also design a new masking function and training objective to further improve SMP. Extensive experiments at various sparsity levels show SMP has significant improvements over first-order and zero-order methods. Unlike previous first-order methods, SMP is also applicable to low sparsity and outperforms zero-order methods. Meanwhile, SMP is more parameter efficient than other methods due to it does not require fine-tuning.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/6214caab-cbbc-4a55-8854-3f1e140d3c91" width="300" height="400"></iframe>

Pruning Pre-trained Language Models Without Fine-Tuning

Large multilingual language models typically share their parameters across all languages, which enables cross-lingual task transfer, but learning can also be hindered when training updates from different languages are in conflict. In this article, we propose novel methods for using language-specific subnetworks, which control cross-lingual parameter sharing, to reduce conflicts and increase positive transfer during fine-tuning. We introduce dynamic subnetworks, which are jointly updated with the model, and we combine our methods with meta-learning, an established, but complementary, technique for improving cross-lingual transfer. Finally, we provide extensive analyses of how each of our methods affects the models.

Downloads

Next from ACL 2023

Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization

Similar lecture

Learning to Imagine: Visually-Augmented Natural Language Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES