Indonesia

Text detoxification is the task of transferring the style of text from toxic to neutral. While there are approaches yielding promising results in monolingual setup, e.g., (Dale et al.,2021; Hallinan et al., 2022), cross-lingual transfer for this task remains a challenging open problem (Moskovskiy et al., 2022). In this work, we present a large-scale study of strategies for cross-lingual text detoxification -- given a parallel detoxification corpus for one language; the goal is to transfer detoxification ability to another language for which we do not have such a corpus.
Moreover, we are the first to explore a new task where text translation and detoxification are performed simultaneously, providing several strong baselines for this task. Finally, we introduce new automatic detoxification evaluation metrics with higher correlations with human judgments than previous benchmarks. We assess the most promising approaches also with manual markup, determining the answer for the best strategy to transfer the knowledge of text detoxification between languages.

IJCNLP-AACL 2023

Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification

## Welcome to 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics!
This year, the conference is in Mexico City. NAACL was actually already planned for Mexico City in 2021, but due to the pandemic the entire conference was moved online. This year, finally, we get to go! So it is my sincere pleasure to welcome you to Mexico City, whether in person or virtually. Having the conference in Mexico City is a good opportunity to emphasize that NAACL is our flagship conference for ACL members not only in North America but also in Central and South America, even though NAACL has been bearing “North” in its name. At this year’s conference, we have a theme to match, with a theme track on the Languages of Latin America to showcase the linguistic diversity of the region.
 
The opportunity to present at NAACL should not depend on a researcher’s travel budget, or their family status. This is why it is so important to make virtual participation at NAACL as good an experience as possible – but we want to also provide a good experience for in-person participants. As a community, we are still working out the best way to do that. This year at NAACL, we are trying out a big virtual poster session ahead of the conference, with the hope that this will make make for a lively and interactive experience. At the same time, we are reducing virtual oral presentations, which seem to be particularly tricky to make to work well. A big thanks to the NAACL program chairs and to Luciana Benotti for all their ideas and work to improve the virtual experience. And participants, virtual as well as in-person: Please let us know what worked for you and what didn’t, so we can continue to improve hybrid conferences. 
 
I have been lucky to work with many amazing people. Without their insight, dedication and patience, and without the many hours of work they put in, NAACL would not have been possible. A huge thank you to the program chairs Helena Gomez, Kevin Duh, and Steve Bethard – you are the best! 
 
Finally, I would like to thank all authors, invited speakers and panelists, area chairs and reviewers, the volunteers organizing and chairing sessions, and all attendees, in-person and virtual. Thank you for helping us make NAACL 2024 come to life. 
 
Welcome and hope you all enjoy the conference! 
Katrin Erk 
The University of Texas at Austin 
NAACL-2024 General Chair 
*You can read the full Welcome message in the [Conference Handbook (downloadable)](https://drive.google.com/file/d/1H1NvW0VASQjkSCYgw3mr-3l4yYDSxz6B/view?usp=sharing)*

To access the event page you need to register [**here.**](http://acl.swoogo.com/naacl2024) 
Your access to the event page is limited based on your registration type. If you registered for workshops only, you will gain access to full workshops content on the day of the workshops program.

Please register!

NAACL 2024

2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

poster

### Welcome to IJCNLP-AACL 2023!
I am honored and happy to welcome you to IJCNLP-AACL 2023! The conference hosts both the 13th
International Joint Conference on Natural Language Processing (IJCNLP) and the 3rd Conference of
the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL). 
The joint conferences of IJCNLP and AACL have been organized by alternating leadership in the
Asia-Pacific region, in odd years by Asian Federation of Natural Language Processing (AFNLP) and
in even years by AACL. The conference is organized by AFNLP this year. 

Considering the current situation that we are not yet fully over the coronavirus pandemic, the
conference is offered in a hybrid mode, off-line in Nusa Dua, Bali, Indonesia, and on-line with the help
of Underline, during November 1-4, 2023. For those attending off-line, I hope that you will find time to
explore the exciting local area, which remains quite warm and pleasant at this time of the year. For
those attending on-line, I hope that the attendance is not much hampered, sometimes even enhanced
and comfortable, though the on-line arrangements have been made without ample time. 

Message from Jong C. Park, Korea Advanced Institute of Science and Technology (KAIST) 
IJCNLP-AACL 2023 General Chair 
###### [Conference Handbook](https://drive.google.com/file/d/1S2JSXa105xJxIkNBfhYmGH20Om6wARBx/view?usp=sharing)

In order to acces this event page, you need to register [here](http://www.ijcnlp-aacl2023.org/)

The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics

Despite the success of pretrained masked language models (MLM), why MLM pretraining is useful is still a question not fully answered. In this work we theoretically and empirically that MLM pretraining makes models robust to lexicon-level spurious features, partly answering the question. Our explanation is that MLM pretraining may alleviate problems brought by simplicity bias (Shah et al., 2020), which refers to the phenomenon that a deep model tends to rely excessively on simple features. In NLP tasks, those simple features could be token-level features whose spurious association with the label can be learned easily. We show that MLM pretraining makes learning from the context easier. Thus, pretrained models are less likely to rely excessively on a single token. We also explore the theoretical explanations of MLM's efficacy in causal settings. Compared with Wei et al. (2021), we achieve similar results with milder assumption. Finally, we close the gap between our theories and real-world practices by conducting experiments on real-world tasks.

On a Benefit of Masked Language Model Pretraining: Robustness to Simplicity Bias

Influencer marketing involves a wide range of strategies in which brands collaborate with popular content creators (i.e., influencers) to leverage their reach, trust, and impact on their audience to promote and endorse products or services. Because followers of influencers are more likely to buy a product after receiving an authentic product endorsement rather than an explicit direct product promotion, the line between personal opinions and commercial content promotion is frequently blurred. This makes automatic detection of regulatory compliance breaches related to influencer advertising (e.g., misleading advertising or hidden sponsorships) particularly difficult. In this work, we (1) introduce a new Twitter (now X) dataset consisting of 15,998 influencer posts mapped into commercial and non-commercial categories for assisting in the automatic detection of commercial influencer content; (2) experiment with an extensive set of predictive models that combine text and visual information showing that our proposed cross-attention approach outperforms state-of-the-art multimodal models; and (3) conduct a thorough analysis of strengths and limitations of our models. We show that multimodal modeling is useful for identifying commercial posts, reducing the amount of false positives, and capturing relevant context that aids in the discovery of undisclosed commercial posts.

A Multimodal Analysis of Influencer Content on Twitter

While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We propose Faithful CoT, a reasoning framework involving two stages: Translation (Natural Language query → symbolic reasoning chain) and Problem Solving (reasoning chain → answer), using an LM and a deterministic solver respectively. This guarantees that the reasoning chain provides a faithful explanation of the final answer. Aside from interpretability, Faithful CoT also improves empirical performance: it outperforms standard CoT on 9 of 10 benchmarks from 4 diverse domains, with a relative accuracy gain of 6.3% on Math Word Problems (MWP), 3.4% on Planning, 5.5% on Multi-hop Question Answering (QA), and 21.4% on Relational Inference. Furthermore, with GPT-4 and Codex, it sets the new state-of-the-art few-shot performance on 7 datasets (with 95.0+ accuracy on 6 of them), showing a strong synergy between faithfulness and accuracy.

Faithful Chain-of-Thought Reasoning

We propose a contrastive hashing method to compress and interpret the contextual representation of pre-trained language models into binary codes. Unlike previous work that generates token-level tags, our method narrows the representation bottleneck to codes with only 24 bits, retaining task-relevant information in a more interpretable and fine-grained format without sacrificing performance (in most cases). We provide experiments and discussions on various structured prediction tasks, such as part-of-speech tagging, named entity recognition, and constituency parsing, to demonstrate the effectiveness and interpretability of our method.

24-bit Languages

State-of-the-art question answering (QA) models exhibit a variety of social biases (e.g., with respect to sex or race), generally explained by similar issues in their training data. However, what has been overlooked so far is that in the critical domain of biomedicine, any unjustified change in model output due to patient demographics is problematic: it results in the unfair treatment of patients. Selecting only questions on biomedical topics whose answers do not depend on ethnicity, sex, or sexual orientation, we ask the following research questions: (RQ1) Do the answers of QA models change when being provided with irrelevant demographic information? (RQ2) Does the answer of RQ1 differ between knowledge graph (KG)-grounded and text-based QA systems? We find that irrelevant demographic information change up to 15% of the answers of a KG-grounded system and up to 23% of the answers of a text-based system, including changes that affect accuracy. We conclude that unjustified answer changes caused by patient demographics are a frequent phenomenon, which raises fairness concerns and should be paid more attention to.

Emerging Challenges in Personalized Medicine: Assessing Demographic Effects on Biomedical Question Answering Systems

Large language models (LLMs) are increasingly being used for generating text in a variety of use cases, including journalistic news articles. Given the potential malicious nature in which these LLMs can be used to generate disinformation at scale, it is important to build effective detectors for such AI-generated text. Given the surge in development of new LLMs, acquiring labeled training data for supervised detectors is a bottleneck. However, there might be plenty of unlabeled text data available, without information on which generator it came from. In this work we tackle this data problem, in detecting AI-generated news text, and frame the problem as an unsupervised domain adaptation task. Here the domains are the different text generators, i.e. LLMs, and we assume we have access to only the labeled source data and unlabeled target data. We develop a Contrastive Domain Adaptation framework, called ConDA, that blends standard domain adaptation techniques with the representation power of contrastive learning to learn domain invariant representations that are effective for the final unsupervised detection task. Our experiments demonstrate the effectiveness of our framework, resulting in average performance gains of 31.7% from the best performing baselines, and within 0.8% margin of a fully supervised detector.

ConDA: Contrastive Domain Adaptation for AI-generated Text Detection

We present PACT (Pretraining with Adversarial Contrastive Learning for Text Classification), a novel self-supervised framework for text classification. Instead of contrasting against in-batch negatives, a popular approach in the literature, PACT mines negatives closer to the anchor representation. PACT operates by endowing the standard pretraining mechanisms of BERT with adversarial contrastive learning objectives, allowing for effective joint optimization of token- and sentence-level pretraining of the BERT model. Our experiments on 13 diverse datasets including token-level, single-sentence, and sentence-pair text classification tasks show that PACT achieves consistent improvements over SOTA baselines. We further show that PACT regularizes both token-level and sentence-level embedding spaces into more uniform representations, thereby alleviating the undesirable anisotropic phenomenon of language models.

PACT: Pretraining with Adversarial Contrastive Learning for Text Classification

Investigating the behaviour of Machine Reading Comprehension (MRC) models under various types of test-time perturbations can shed light on the enhancement of their robustness and generalisation capability, despite the superhuman performance they have achieved on existing benchmark datasets. In this paper, we study the robustness of contemporary MRC systems to context paraphrasing, i.e., whether these models are still able to correctly answer the questions once the reading passages have been paraphrased. To this end, we systematically design a pipeline to semi-automatically generate perturbed MRC instances which ultimately lead to the creation of a paraphrased test set. We conduct experiments on this dataset with six state-of-the-art neural MRC models and we find that even the minimum performance drop of all these models exceeds 41%, whereas human performance remains high. Retraining models with augmented perturbed examples results in improved robustness, though the performance remains lower than on the original dataset. These results demonstrate that the existing high-performing MRC systems are still far away from real language understanding.

Are Machine Reading Comprehension Systems Robust to Context Paraphrasing?

To what extent do personal attributes affect the way we are spoken to? Answering this question requires the precise reproduction of a conversational context except for one personal attribute of interest, amounting to a classical, yet infeasible, causal inference problem. We present a method based on counterfactual analysis by manipulating speaker attributes in observational data. We present a case study of Advocate responses to Justices in debates in the Supreme Court of the United States. Specifically, we measure changes in politeness and coordination of Advocates when responding to (a) real Justices and (b) counterfactually-manipulated Justices, with responses generated with GPT2. We first validate our method, showing that GPT2-generated outputs capture coordination and politeness. Our results confirm a known impact of the attribute gender, and suggest a weaker effect of seniority on coordination.

It's not only What You Say, It's also Who It's Said to: Counterfactual Analysis of Interactive Behavior in the Courtroom

Bangla (or Bengali) is the ﬁfth most spoken language globally; yet, the state-of-the-art NLP in Bangla is lagging for even simple tasks such as lemmatization, POS tagging, etc. This is partly due to lack of a varied quality corpus. To alleviate this need, we build VACASPATI, a diverse corpus of Bangla literature. The literary works are collected from various websites; only those works that are publicly available without copyright violations or restrictions are collected. We believe that published literature captures the features of a language much better than newspapers, blogs or social media posts which tend to follow only a certain literary pattern and, therefore, miss out on language variety and vocabulary. Our corpus VACASPATI is varied from multiple aspects, including type of composition, topic, author, time, space, etc. It contains more than 11 million sentences
and 115 million words. We have also built a word embedding model, VAC-FT, using FastText from VACASPATI as well as trained an Electra model, VAC-BERT, using the corpus. VAC-BERT has far fewer parameters and requires only a fraction of resources compared to other state-of-the-art transformer models and yet performs either better or similar on various downstream tasks. Similarly, VAC-FT outperforms other FastText-based models on multiple downstream tasks. We also demonstrate the efﬁcacy of VACASPATI as a corpus by showing that similar models built from other corpora are not as effective. The models are available at https://bangla.iitk.ac.in/projects/vacaspati.html.

Downloads

Next from IJCNLP-AACL 2023

On a Benefit of Masked Language Model Pretraining: Robustness to Simplicity Bias

Similar lecture

MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages