Canada

Zero-shot and few-shot stance detection identify the polarity of text with regard to a certain target when we have only limited or no training resources for the target. Previous work generally formulates the problem into a classification setting, ignoring the potential use of label text. In this paper, we instead utilize a conditional generation framework and formulate the problem as denoising from partially-filled templates, which can better utilize the semantics among input, label, and target texts. We further propose to jointly train an auxiliary task, target prediction, and to incorporate manually constructed incorrect samples with unlikelihood training to improve the representations for both target and label texts. We also verify the effectiveness of target-related Wikipedia knowledge with the generation framework. Experiments show that our proposed method significantly outperforms several strong baselines on VAST, and achieves new state-of-the-art performance.

&lt;iframe src=&quot;https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/88da33d6-ef1f-42ed-8ed3-68a77d849726&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Zero-Shot and Few-Shot Stance Detection on Varied Topics via Conditional Generation

few-shot

stance detection

zero-shot

generation

Zero-shot and few-shot stance detection identify the polarity of text with regard to a certain target when we have only limited or no training resources for the target. Previous work generally formulates the problem into a classification setting, ignoring the potential use of label text. In this paper, we instead utilize a conditional generation framework and formulate the problem as denoising from partially-filled templates, which can better utilize the semantics among input, label, and target texts. We further propose to jointly train an auxiliary task, target prediction, and to incorporate manually constructed incorrect samples with unlikelihood training to improve the representations for both target and label texts. We also verify the effectiveness of target-related Wikipedia knowledge with the generation framework. Experiments show that our proposed method significantly outperforms several strong baselines on VAST, and achieves new state-of-the-art performance.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/88da33d6-ef1f-42ed-8ed3-68a77d849726" 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.

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual Data Augmentation (CDA) to balance the training corpus. However, CDA slightly modifies the original corpus, limiting the representation distance between different demographic groups to a narrow range. As a result, the debiasing model easily fits the differences between counterfactual pairs, which affects its debiasing performance with limited text resources. In this paper, we propose an adversarial training-inspired two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation (named CCPA) to mitigate social biases in PLMs' encoding. In the first stage, we propose a data augmentation method based on continuous prompt tuning to push farther the representation distance between sample pairs along different demographic groups. In the second stage, we utilize contrastive learning to pull closer the representation distance between the augmented sample pairs and then fine-tune PLMs' parameters to get debiased encoding. Our approach guides the model to achieve stronger debiasing performance by adding difficulty to the training process. Extensive experiments show that CCPA outperforms baselines in terms of debiasing performance. Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/a5deaac1-f074-4998-b16d-578e707ed616" width="300" height="400"></iframe>

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model while under-fit the language model, resulting in poor generalization to out-of-distribution error patterns. Given that BERT is the backbone of most CSC models, this phenomenon has a significant negative impact. To address this issue, we are releasing a multi-domain benchmark LEMON, with higher quality and diversity than existing benchmarks, to allow a comprehensive assessment of the open domain generalization of CSC models. Then, we demonstrate that a very simple strategy randomly masking 20\% non-error tokens from the input sequence during fine-tuning is sufficient for learning a much better language model without sacrificing the error model. This technique can be applied to any model architecture and achieves new state-of-the-art results on SIGHAN, ECSpell, and LEMON.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/940c667c-ebe7-4470-be82-f8bdb46c8c2c" width="300" height="400"></iframe>

Rethinking Masked Language Modeling for Chinese Spelling Correction

Automated Essay Scoring (AES) aims to evaluate the quality score for input essays. In this work, we propose a novel unsupervised AES approach ULRA, which does not require groundtruth scores of essays for training. The core idea of our ULRA is to use multiple heuristic quality signals as the pseudo-groundtruth, and then train a neural AES model by learning from the aggregation of these quality signals. To aggregate these inconsistent quality signals into a unified supervision, we view the AES task as a ranking problem, and design a special Deep Pairwise Rank Aggregation (DPRA) loss for training. In the DPRA loss, we set a learnable confidence weight for each signal to address the conflicts among signals, and train the neural AES model in a pairwise way to disentangle the cascade effect among partial-order pairs. Experiments on eight prompts of ASPA dataset show that ULRA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both transductive and inductive settings. Further, our approach achieves comparable performance with many existing domain-adapted supervised models, showing the effectiveness of ULRA. The code is available at https://github.com/tenvence/ulra.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/b7ddb166-fe2d-4180-bd6b-070c8f0642f5" width="300" height="400"></iframe>

Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring

Text revision is a necessary process to improve text quality. During this process, writers constantly edit texts out of different edit intentions.Identifying edit intention for a raw text is always an ambiguous work, and most previous work on revision systems mainly focuses on editing texts according to one specific edit intention.In this work, we aim to build a multi-intent text revision system that could revise texts without explicit intent annotation.Our system is based on prefix-tuning, which first gets prefixes for every edit intent, and then trains a prefix transfer module, enabling the system to selectively leverage the knowledge from various prefixes according to the input text.We conduct experiments on the IteraTeR dataset, and the results show that our system outperforms baselines. The system can significantly improve the SARI score with more than 3% improvements, which thrives on the learned editing intention prefixes.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/1bd0714f-c929-46db-ba64-e38b8b90b586" width="300" height="400"></iframe>

Leveraging Prefix Transfer for Multi-Intent Text Revision

When applied to processing long text, Large Language Models (LLMs) are limited by their context window. Existing efforts to address this limitation involve training specialized architectures, and cannot be easily applied to off- the-shelf LLMs. We present Parallel Context Windows (PCW), a method that alleviates the context window restriction for any off-the-shelf LLM without further training. The key to the approach is to carve a long context into chunks ("windows), restrict the attention mechanism to apply only within each window, and re-use the positional embeddings across the windows. Our main results test the PCW approach on in-context learning with models that range in size between 750 million and 178 billion parameters, and show substantial improvements for tasks with diverse input and output spaces. We show additional benefits in other settings where long context windows may be beneficial: multi-hop questions and retrieval-augmented question answering with multiple retrieved documents. Our results highlight Parallel Context Windows as a promising method for applying off-the-shelf LLMs in a range of settings that require long text sequences. We make our code publicly available at https://github.com/ ai21labs/parallel-context-windows.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/e6f2a8e4-a3dc-4dfa-b385-60f698d60967" width="300" height="400"></iframe>

Parallel Context Windows for Large Language Models

The ability of commonsense reasoning (CR) decides whether a neural machine translation (NMT) model can move beyond pattern recognition. Despite the rapid advancement of NMT and the use of pretraining to enhance NMT models, research on CR in NMT is still in its infancy, leaving much to be explored in terms of effectively training NMT models with high CR abilities and devising accurate automatic evaluation metrics. This paper presents a comprehensive study aimed at expanding the understanding of CR in NMT.For the training, we confirm the effectiveness of incorporating pretrained knowledge into NMT models and subsequently utilizing these models as robust testbeds for investigating CR in NMT. For the evaluation, we propose a novel entity-aware evaluation method that takes into account both the NMT candidate and important entities in the candidate, which is more aligned with human judgement. Based on the strong testbed and evaluation methods, we identify challenges in training NMT models with high CR abilities and suggest directions for further unlabeled data utilization and model design. We hope that our methods and findings will contribute to advancing the research of CR in NMT. Source data, code and scripts are freely available at https://github.com/YutongWang1216/CR-NMT.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/d1558b6b-581b-49f3-b9d1-3af6bf947906" width="300" height="400"></iframe>

Revisiting Commonsense Reasoning in Machine Translation: Training, Evaluation and Challenge

Dynamic networks, e.g., Dynamic Convolution (DY-Conv) and the Mixture of Experts (MoE), have been extensively explored as they can considerably improve the model's representation power with acceptable computational cost. The common practice in implementing dynamic networks is to convert the given static layers into fully dynamic ones where all parameters are dynamic (at least within a single layer) and vary with the input. However, such a fully dynamic setting may cause redundant parameters and high deployment costs, limiting the applicability of dynamic networks to a broader range of tasks and models. The main contributions of our work are challenging the basic commonsense in dynamic networks and proposing a partially dynamic network, namely PAD-Net, to transform the redundant dynamic parameters into static ones. Also, we further design Iterative Mode Partition to partition dynamic and static parameters efficiently. Our method is comprehensively supported by large-scale experiments with two typical advanced dynamic architectures, i.e., DY-Conv and MoE, on both image classification and GLUE benchmarks. Encouragingly, we surpass the fully dynamic networks by $+0.7\%$ top-1 acc with only $30\%$ dynamic parameters for ResNet-50 and $+1.9\%$ average score in language understanding with only $50\%$ dynamic parameters for BERT. Code will be released at: \url{https://github.com/Shwai-He/PAD-Net}.

<iframe src="https://app.sli.do/event/9yzqPifSAmy9Efyrt2gEbX/embed/polls/3c82bcf7-4d0d-47ed-9c3c-2f16098bce90" width="300" height="400"></iframe>

PAD-Net: An Efficient Framework for Dynamic Networks

Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter gradients, which entails a high cost of extra memory overheads. To solve this problem, several memory-efficient optimizers (e.g., Adafactor) have been proposed to obtain a drastic reduction in auxiliary memory usage, but with a performance penalty. In this paper, we first study a confidence-guided strategy to reduce the instability of existing memory efficient optimizers. Based on this strategy, we propose CAME to simultaneously achieve two goals: fast convergence as in traditional adaptive methods, and low memory usage as in memory-efficient methods. Extensive experiments demonstrate the training stability and superior performance of CAME across various NLP tasks such as BERT and GPT-2 training. Notably, for BERT pre-training on the large batch size of 32,768, our proposed optimizer attains faster convergence and higher accuracy compared with the Adam optimizer. The implementation of CAME is publicly available.

<iframe src="https://app.sli.do/event/eX4PwSmcCc1EvCqjxcYdKB/embed/polls/37fcc85e-fef2-4aa2-8966-9e822d83c3fe" width="300" height="400"></iframe>

CAME: Confidence-guided Adaptive Memory Efficient Optimization

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting the scope of attacks. Moreover, the majority of attacks for pre-trained models are designed for understanding tasks. In this paper, we propose task-agnostic backdoor attacks for code pre-trained models. Our backdoored model is pre-trained with two learning strategies (i.e., Poisoned Seq2Seq learning and token representation learning) to support the multi-target attack of downstream code understanding and generation tasks. During the deployment phase, the implanted backdoors in the victim models can be activated by the designed triggers to achieve the targeted attack. We evaluate our approach on two code understanding tasks and three code generation tasks over seven datasets. Extensive experimental results demonstrate that our approach effectively and stealthily attacks code-related downstream tasks.

<iframe src="https://app.sli.do/event/eX4PwSmcCc1EvCqjxcYdKB/embed/polls/030aa0f2-e3d3-4d74-9913-2521c4fad7a0" width="300" height="400"></iframe>

Multi-target Backdoor Attacks for Code Pre-trained Models

Answering multi-hop questions over hybrid factual knowledge from the given text and table (TextTableQA) is a challenging task. Existing models mainly adopt a retriever-reader framework, which have several deficiencies, such as noisy labeling in training retriever, insufficient utilization of heterogeneous information over text and table, and deficient ability for different reasoning operations. In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner. We use a retriever with refinement training to solve the noisy labeling problem. Then, a hybrid selector considers the linked relationships between heterogeneous data to select the most relevant factual knowledge. For the final stage, instead of adapting a reading comprehension module like in previous methods, we employ a generation-based reasoner to obtain answers. This includes two approaches: a row-wise generator and an LLM prompting generator~(first time used in this task). The experimental results demonstrate that our method achieves competitive results in the few-shot setting. When trained on the full dataset, our approach outperforms all baseline methods, ranking first on the HybridQA leaderboard.

<iframe src="https://app.sli.do/event/eX4PwSmcCc1EvCqjxcYdKB/embed/polls/a4ad8707-5906-4818-b54e-81b9a81aa184" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES