Canada

Distilling knowledge from a high-resource task, e.g., machine translation, is an effective way to alleviate the data scarcity problem of end-to-end speech translation.However, previous works simply use the classical knowledge distillation that does not allow for adequate transfer of knowledge from machine translation.In this paper, we propose a comprehensive knowledge distillation framework for speech translation, CKDST, which is capable of comprehensively and effectively distilling knowledge from machine translation to speech translation from two perspectives: cross-modal contrastive representation distillation and simultaneous decoupled knowledge distillation. In the former, we leverage a contrastive learning objective to optmize the mutual information between speech and text representations for representation distillation in the encoder. In the later, we decouple the non-target class knowledge from target class knowledge for logits distillation in the decoder.Experiments on the MuST-C benchmark dataset demonstrate that our CKDST substantially improves the baseline by 1.2 BLEU on average in all translation directions, and outperforms previous state-of-the-art end-to-end and cascaded speech translation models.

ACL 2023

CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation

speech translation

end-to-end

knowledge distillation

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

NAACL 2021

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.

Disfluencies in user utterances can trigger a chain of errors impacting all the modules of a dialogue system: natural language understanding, dialogue state tracking, and response generation. In this work, we first analyze existing dialogue datasets commonly used in research and show that they only contain a marginal number of disfluent utterances. Due to this relative absence of disfluencies in their training data, dialogue systems may then critically fail when exposed to disfluent utterances. Following this observation, we propose to augment existing datasets with disfluent user utterances by paraphrasing fluent utterances into disfluent ones. Relying on a pre-trained language model, our few-shot disfluent paraphraser guided by a disfluency classifier can generate useful disfluent utterances for training better dialogue systems. We report on improvements for both dialogue state tracking and response generation when the dialogue systems are trained on datasets augmented with our disfluent utterances.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/016f3115-0014-45ad-97ff-4d53ea7c1770" width="300" height="400"></iframe>

Disfluency Generation for More Robust Dialogue Systems

Machine Reading Comprehension (MRC) models easily learn spurious correlations from complex contexts such as tabular data. Counterfactual training---using the factual and counterfactual data by augmentation---has become a promising solution. However, it is costly to construct faithful counterfactual examples because it is tricky to maintain the consistency and dependency of the tabular data. In this paper, we take a more efficient fashion to ask \textbf{hypothetical questions} like \textit{``in which year would the net profit be larger if the revenue in 2019 were \$38,298?''}, whose effects on the answers are equivalent to those expensive counterfactual tables. We propose a hypothetical training framework that uses paired examples with different hypothetical questions to supervise the direction of model gradient towards the counterfactual answer change. The superior generalization results on tabular MRC datasets, including a newly constructed stress test and MultiHiertt, validate our effectiveness.

Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context

Sequence-to-sequence (seq2seq) models based on the Transformer architecture have become a ubiquitous tool applicable not only to classical text generation tasks such as machine translation and summarization but also to any other task where an answer can be represented in a form of a finite text fragment (e.g., question answering, or even entity linking).However, when deploying a model in practical applications, we need not only high performance but also an ability to determine cases where the model is not applicable. Uncertainty estimation (UE) techniques provide a tool for determining out-of-distribution (OOD) data.State-of-the-art UE methods for seq2seq models rely on computationally heavyweight and impractical deep ensembles. In this work, we perform a computational study of various novel UE methods for large pre-trained seq2seq models T5 and BART on three tasks: machine translation, text summarization, and question answering. We adapt computationally lightweight density-based UE methods to seq2seq models and show that they often outperform heavyweight deep ensembles on the task of OOD detection.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/f5e28322-3d8f-40ab-b4dc-73f1b0f13135" width="300" height="400"></iframe>

Efficient Out-of-Domain Detection for Sequence to Sequence Models

Metaphors are highly creative constructs of human language that grow old and eventually die. Popular datasets used for metaphor processing tasks were constructed from dated source texts. In this paper, we propose MetaNews, a large high-quality contemporary dataset of news headlines hand-annotated with metaphorical verbs. The dataset comprises headlines from a variety of sources including political, satirical, reliable and fake. Our dataset serves the purpose of evaluation for the tasks of metaphor interpretation and generation.The experiments reveal several insights and limitations of using LLMs to automate metaphor processing tasks as frequently seen in the recent literature. The dataset is publicly available for research purposes\footnote{\url{https://github.com/AxleBlaze3/Metanews}}.

NewsMet : A 'do it all' Dataset of Contemporary Metaphors in News Headlines

Multilingual language models have recently gained attention as a promising solution for representing multiple languages in a single model. In this paper, we propose new criteria to evaluate the quality of lexical representation and vocabulary overlap observed in sub-word tokenizers.Our findings show that the overlap of vocabulary across languages can be actually detrimental to certain downstream tasks (POS, dependency tree labeling). In contrast, NER and sentence-level tasks (cross-lingual retrieval, NLI) benefit from sharing vocabulary. We also observe that the coverage of the language-specific tokens in the multilingual vocabulary significantly impacts the word-level tasks. Our study offers a deeper understanding of the role of tokenizers in multilingual language models and guidelines for future model developers to choose the most suitable tokenizer for their specific application before undertaking costly model pre-training.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/ef304169-8a10-41d4-ac79-a1964d51b5a7" width="300" height="400"></iframe>

Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce additional optimization criteria, and update the model to reach a new debiased state. However, in practice, end-users and practitioners might prefer to switch back to the original model, or apply debiasing only on a specific subset of protected attributes. To enable this, we propose a novel modular bias mitigation approach, consisting of stand-alone highly sparse debiasing subnetworks, where each debiasing module can be integrated into the core model on-demand at inference time. Our approach draws from the concept of diff pruning, and proposes a novel training regime adaptable to various representation disentanglement optimizations. We conduct experiments on three classification tasks with gender, race, and age as protected attributes. The results show that our modular approach, while maintaining task performance, improves (or at least remains on-par with) the effectiveness of bias mitigation in comparison with baseline finetuning. Particularly on a two-attribute dataset, our approach with separately learned debiasing subnetworks shows effective utilization of either or both the subnetworks for selective bias mitigation.

Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks

The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametric Decoding (Np Decoding) which can be applied to existing generative retrieval models. Np Decoding uses nonparametric contextualized vocab embeddings (external memory) rather than vanilla vocab embeddings as decoder vocab embeddings. By leveraging the contextualized vocab embeddings, the generative retrieval model is able to utilize both the parametric and nonparametric space. Evaluation over 9 datasets (8 single-hop and 1 multi-hop) in the document retrieval task shows that applying Np Decoding to generative retrieval models significantly improves the performance. We also show that Np Decoding is data- and parameter-efficient, and shows high performance in the zero-shot setting.

Nonparametric Decoding for Generative Retrieval

Work on hate speech has made considering rude and harmful examples in scientific publications inevitable. This situation raises various problems, such as whether or not to obscure profanities. While science must accurately disclose what it does, the unwarranted spread of hate speech can harm readers and increases its internet frequency. While maintaining publications' professional appearance, obfuscating profanities makes it challenging to evaluate the content, especially for non-native speakers.Surveying 150 ACL papers, we discovered that obfuscation is usually used for English but not other languages, and even then, quite unevenly.We discuss the problems with obfuscation and suggest a multilingual community resource called PrOf with a Python module to standardize profanity obfuscation processes. We believe PrOf can help scientific publication policies to make hate speech work accessible and comparable, irrespective of language.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/3db251ed-612e-43b7-a663-a6ea2de353cc" width="300" height="400"></iframe>

The State of Profanity Obfuscation in Natural Language Processing Scientific Publications

Event extraction (EE) is a crucial task aiming at extracting events from texts, which includes two subtasks: event detection (ED) and event argument extraction (EAE). In this paper, we check the reliability of EE evaluations and identify three major pitfalls: (1) The data preprocessing discrepancy makes the evaluation results on the same dataset not directly comparable, but the data preprocessing details are not widely noted and specified in papers. (2) The output space discrepancy of different model paradigms makes different-paradigm EE models lack grounds for comparison and also leads to unclear mapping issues between predictions and annotations. (3) The absence of pipeline evaluation of many EAE-only works makes them hard to be directly compared with EE works and may not well reflect the model performance in real-world pipeline scenarios. We demonstrate the significant influence of these pitfalls through comprehensive meta-analyses of recent papers and empirical experiments. To avoid these pitfalls, we suggest a series of remedies, including specifying data preprocessing, standardizing outputs, and providing pipeline evaluation results. To help implement these remedies, we develop a consistent evaluation framework OmniEvent, which can be obtained from https://github.com/THU-KEG/OmniEvent.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/85181956-fe4b-4ccd-913f-59c17687d298" width="300" height="400"></iframe>

The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation

In this paper, we propose a novel language model guided captioning approach, LAMOC, for knowledge-based visual question answering (VQA). Our approach employs the generated captions by a captioning model as the context of an answer prediction model, which is a Pre-Trained Language model (PLM). As the major contribution, we leverage the guidance and feedback of the prediction model to improve the capability of the captioning model. In this way, the captioning model can become aware of the task goal and information need from the PLM. To develop our approach, we design two specific training stages, where the first stage adapts the captioning model to the prediction model (selecting more suitable caption propositions for training) and the second stage tunes the captioning model according to the task goal (learning from feedback of the PLM). Extensive experiments demonstrate the effectiveness of the proposed approach on the knowledge-based VQA task. Specifically, on the challenging A-OKVQA dataset, LAMOC outperforms several competitive zero-shot methods and even achieves comparable results to a fine-tuned VLP model. Our code is publicly available at https://github.com/RUCAIBox/LAMOC.

Next from ACL 2023

Disfluency Generation for More Robust Dialogue Systems

Similar lecture

Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation