Canada

Training an effective video-and-language model intuitively requires multiple frames as model inputs. However, it is unclear whether using multiple frames is beneficial to downstream tasks, and if yes, whether the performance gain is worth the drastically-increased computation and memory costs resulting from using more frames. In this work, we explore single-frame models for video-and-language learning. On a diverse set of video-and-language tasks (including text-to-video retrieval and video question answering), we show the surprising result that, with large-scale pre-training and a proper frame ensemble strategy at inference time, a single-frame trained model that does not consider temporal information can achieve better performance than existing methods that use multiple frames for training. This result reveals the existence of a strong ``static appearance bias&#39;&#39; in popular video-and-language datasets. Therefore, to allow for a more comprehensive evaluation of video-and-language models, we propose two new retrieval tasks based on existing fine-grained action recognition datasets that encourage temporal modeling. Our code is available at https://github.com/jayleicn/singularity.

&lt;iframe src=&quot;https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/30e41bd6-7b6b-40e6-8b10-bc14f72fb70f&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Revealing Single Frame Bias for Video-and-Language Learning

efficient large-scale training

video-and-language

multimodal learning

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 
<br>
<br>

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
<br>
<br>https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

IJCNLP-AACL 2022

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

Training an effective video-and-language model intuitively requires multiple frames as model inputs. However, it is unclear whether using multiple frames is beneficial to downstream tasks, and if yes, whether the performance gain is worth the drastically-increased computation and memory costs resulting from using more frames. In this work, we explore single-frame models for video-and-language learning. On a diverse set of video-and-language tasks (including text-to-video retrieval and video question answering), we show the surprising result that, with large-scale pre-training and a proper frame ensemble strategy at inference time, a single-frame trained model that does not consider temporal information can achieve better performance than existing methods that use multiple frames for training. This result reveals the existence of a strong ``static appearance bias'' in popular video-and-language datasets. Therefore, to allow for a more comprehensive evaluation of video-and-language models, we propose two new retrieval tasks based on existing fine-grained action recognition datasets that encourage temporal modeling. Our code is available at https://github.com/jayleicn/singularity.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/30e41bd6-7b6b-40e6-8b10-bc14f72fb70f" 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.

Classic approaches to content moderation typically apply a rule-based heuristic approach to flag content. While rules are easily customizable and intuitive for humans to interpret, they are inherently fragile and lack the flexibility or robustness needed to moderate the vast amount of undesirable content found online today. Recent advances in deep learning have demonstrated the promise of using highly effective deep neural models to overcome these challenges. However, despite the improved performance, these data-driven models lack transparency and explainability, often leading to mistrust from everyday users and a lack of adoption by many platforms. In this paper, we present Rule By Example (RBE): a novel exemplar-based contrastive learning approach for learning from logical rules for the task of textual content moderation. RBE is capable of providing rule-grounded predictions, allowing for more explainable and customizable predictions compared to typical deep learning-based approaches. We demonstrate that our approach is capable of learning rich rule embedding representations using only a few data examples. Experimental results on 3 popular hate speech classification datasets show that RBE is able to outperform state-of-the-art deep learning classifiers as well as the use of rules in both supervised and unsupervised settings while providing explainable model predictions via rule-grounding.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/e0548975-73a0-45df-9e1f-30cdfd0d3502" width="300" height="400"></iframe>

Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection

State-of-the-art techniques common to low resource Machine Translation (MT) are applied to improve MT of spoken language text to Sign Language (SL) glosses. In our experiments, we improve the performance of the transformer-based models via (1) data augmentation, (2) semi-supervised Neural Machine Translation (NMT), (3) transfer learning and (4) multilingual NMT. The proposed methods are implemented progressively on two German SL corpora containing gloss annotations. Multilingual NMT combined with data augmentation appear to be the most successful setting, yielding statistically significant improvements as measured by three automatic metrics (up to over 6 points BLEU), and confirmed via human evaluation. Our best setting outperforms all previous work that report on the same test-set and is also confirmed on a corpus of the American Sign Language (ASL).

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/93b81b18-9689-4cbb-b22d-8086ac30a2c6" width="300" height="400"></iframe>

Neural Machine Translation Methods for Translating Text to Sign Language Glosses

The bias-variance tradeoff is the idea that learning methods need to balance model complexity with data size to minimize both under-fitting and over-fitting. Recent empirical work and theoretical analysis with over-parameterized neural networks challenges the classic bias-variance trade-off notion suggesting that no such trade-off holds: as the width of the network grows, bias monotonically decreases while variance initially increases followed by a decrease. In this work, we first provide a variance decomposition-based justification criteria to examine whether large pretrained neural models in a fine-tuning setting are generalizable enough to have low bias and variance. We then perform theoretical and empirical analysis using ensemble methods explicitly designed to decrease variance due to optimization. This results in essentially a two-stage fine-tuning algorithm that first ratchets down bias and variance iteratively, and then uses a selected fixed-bias model to further reduce variance due to optimization by ensembling. We also analyze the nature of variance change with the ensemble size in low- and high-resource classes. Empirical results show that this two-stage method obtains strong results on SuperGLUE tasks and clinical information extraction tasks. Code and settings are available: https://github.com/christa60/bias-var-fine-tuning-plms.git

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/549fa3a8-7ef7-44ac-aab4-4028a2644c7d" width="300" height="400"></iframe>

Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models

Context is everything, even in commonsense moral reasoning. Changing contexts can flip the moral judgment of an action; Lying to a friend is wrong in general, but may be morally acceptable if it is intended to protect their life.We present ClarifyDelphi, an interactive system that learns to ask clarification questions (e.g., why did you lie to your friend?) in order to elicit additional salient contexts of a social or moral situation. We posit that questions whose potential answers lead to \textit{diverging} moral judgments are the most informative. Thus, we propose a reinforcement learning framework with a defeasibility reward that aims to maximize the divergence between moral judgments of hypothetical answers to a question. Human evaluation demonstrates that our system generates more relevant, informative and defeasible questions compared to competitive baselines. Our work is ultimately inspired by studies in cognitive science that have investigated the flexibility in moral cognition (i.e., the diverse contexts in which moral rules can be bent), and we hope that research in this direction can assist both cognitive and computational investigations of moral judgments.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/12a4b811-dadf-4a52-92e5-6744fc8c695a" width="300" height="400"></iframe>

ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations

Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning. In this paper, we present Program-Guided Fact-Checking (ProgramFC), a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions. We first leverage the in-context learning ability of large language models to generate reasoning programs to guide the verification process. Afterward, we execute the program by delegating each sub-task to the corresponding sub-task handler. This process makes our model both explanatory and data-efficient, providing clear explanations of its reasoning process and requiring minimal training data. We evaluate ProgramFC on two challenging fact-checking datasets and show that it outperforms seven fact-checking baselines across different settings of evidence availability, with explicit output programs that benefit human debugging. Our codes and data are publicly available at https://github.com/mbzuai-nlp/ProgramFC.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/055ed354-4b2f-4d84-9420-7eee73a4b249" width="300" height="400"></iframe>

Fact-Checking Complex Claims with Program-Guided Reasoning

Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since large-scale retraining of these models from scratch is both time and compute-expensive, a variety of approaches have been previously proposed that de-bias a pre-trained model. While the majority of current state-of-the-art debiasing methods focus on changes to the training regime, in this paper, we propose data intervention strategies as a powerful yet simple technique to reduce gender bias in pre-trained models. Specifically, we empirically show that by fine-tuning a pre-trained model on only 10 debiased (intervened) training examples, the tendency to favor any gender is significantly reduced. Since our proposed method only needs a few training examples, we argue that our few-shot de-biasing approach is highly feasible and practical. Through extensive experimentation, we show that our de-biasing technique performs better than competitive state-of-the-art baselines with minimal loss in language modeling ability.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/54ee5640-f2cf-46c7-a133-c7b9393e1e6f" width="300" height="400"></iframe>

Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions

Multi-label intent detection aims to assign multiple labels to utterances and attracts increasing attention as a practical task in task-oriented dialogue systems. As dialogue domains change rapidly and new intents emerge fast, the lack of annotated data motivates multi-label few-shot intent detection. However, previous studies are confused by the identical representation of the utterance with multiple labels and overlook the intrinsic intra-class and inter-class interactions. To address these two limitations, we propose a novel dual class knowledge propagation network in this paper. In order to learn well-separated representations for utterances with multiple intents, we first introduce a label-semantic augmentation module incorporating class name information. For better consideration of the inherent intra-class and inter-class relations, an instance-level and a class-level graph neural network are constructed, which not only propagate label information but also propagate feature structure. And we use a simple yet effective method to predict the intent count of each utterance. Extensive experimental results on two multi-label intent datasets have demonstrated that our proposed method outperforms strong baselines by a large margin.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/d78c8860-04ce-4c12-9fd8-cbabe0278e6d" width="300" height="400"></iframe>

Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection

Recent studies have shown the effectiveness of retrieval augmentation in many generative NLP tasks. These retrieval-augmented methods allow models to explicitly acquire prior external knowledge in a non-parametric manner and regard the retrieved reference instances as cues to augment text generation. These methods use similarity-based retrieval, which is based on a simple hypothesis: the more the retrieved demonstration resembles the original input, the more likely the demonstration label resembles the input label. However, due to the complexity of event labels and sparsity of event arguments, this hypothesis does not always hold in document-level EAE. This raises an interesting question: How do we design the retrieval strategy for document-level EAE? We investigate various retrieval settings from the input and label distribution views in this paper. We further augment document-level EAE with pseudo demonstrations sampled from event semantic regions that can cover adequate alternatives in the same context and event schema. Through extensive experiments on RAMS and WikiEvents, we demonstrate the validity of our newly introduced retrieval-augmented methods and analyze why they work.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/f180e9be-eada-4f93-9f86-512b7b35fb2c" width="300" height="400"></iframe>

Retrieve-and-Sample: Document-level Event Argument Extraction via Hybrid Retrieval Augmentation

Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task. Specifically, these methods utilize few-shot learning settings to fine-tune the sentiment classification model using manual or automatically generated prompts. However, the performance of these methods is sensitive to the perturbations of the utilized prompts. Furthermore, these methods depend on a few labeled instances for automatic prompt generation and prompt ranking. This study aims to find high-quality prompts for the given task in a zero-shot setting. Given a base prompt, our proposed approach automatically generates multiple prompts similar to the base prompt employing positional, reasoning, and paraphrasing techniques and then ranks the prompts using a novel metric. We empirically demonstrate that the top-ranked prompts are high-quality and significantly outperform the base prompt and the prompts generated using few-shot learning for the binary sentence-level sentiment classification task.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/a800a639-016e-47d0-bdc2-cb5ab69c5f0a" width="300" height="400"></iframe>

Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts

Given a text query, the task of Natural Language Video Localization (NLVL) is to localize a temporal moment in an untrimmed video that semantically matches the query. In this paper, we adopt a proposal-based solution that generates proposals (i.e. candidate moments) and then select the best matching proposal. On top of modeling the cross-modal interaction between candidate moments and the query, our proposed Moment Sampling DETR (MS-DETR) enables efficient moment-moment relation modeling. The core idea is to sample a subset of moments guided by the learnable templates with an adopted DETR framework. To achieve this, we design a multi-scale visual-linguistic encoder, and an anchor-guided moment decoder paired with a set of learnable templates. Experimental results on three public datasets demonstrate the superior performance of MS-DETR.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/56eb269d-614b-4488-bbae-f05c52951acc" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection

Similar lecture

Contrastive Video-Language Learning with Fine-grained Frame Sampling