Ireland

Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale. However, despite their real-world deployment, we do not yet comprehensively understand the extent to which offensive language classifiers are robust against adversarial attacks. Prior work in this space is limited to studying robustness of offensive language classifiers against primitive attacks such as misspellings and extraneous spaces. To address this gap, we systematically analyze the robustness of state-of-the-art offensive language classifiers against more crafty adversarial attacks that leverage greedy- and attention-based word selection and context-aware embeddings for word replacement. Our results on multiple datasets show that these crafty adversarial attacks can degrade the accuracy of offensive language classifiers by more than 50% while also being able to preserve the readability and meaning of the modified text.

ACL 2022

On the Robustness of Offensive Language Classifiers

obfuscation

offense

robustness

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

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 (NLP). 

findings / work in progress

Knowledge probing is crucial for understanding the knowledge transfer mechanism behind the pre-trained language models (PLMs). Despite the growing progress of probing knowledge for PLMs in the general domain, specialised areas such as biomedical domain are vastly under-explored. To catalyse the research in this direction, we release a well-curated biomedical knowledge probing benchmark, MedLAMA, which is constructed based on the Unified Medical Language System (UMLS) Metathesaurus. We test a wide spectrum of state-of-the-art PLMs and probing approaches on our benchmark, reaching at most 3% of acc@10. While highlighting various sources of domain-specific challenges that amount to this underwhelming performance, we illustrate that the underlying PLMs have a higher potential for probing tasks. To achieve this, we propose Contrastive-Probe, a novel self-supervised contrastive probing approach, that adjusts the underlying PLMs without using any probing data. While Contrastive-Probe pushes the acc@10 to 28%, the performance gap still remains notable. Our human expert evaluation suggests that the probing performance of our Contrastive-Probe is still under-estimated as UMLS still does not include the full spectrum of factual knowledge. We hope MedLAMA and Contrastive-Probe facilitate further developments of more suited probing techniques for this domain.

Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models

Understanding tables is an important aspect of natural language understanding. Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. Such spurious biases make the model vulnerable to row and column order perturbations. Additionally, prior work has not thoroughly modeled the table structures or table-text alignments, hindering the table-text understanding ability. In this work, we propose a robust and structurally aware table-text encoding architecture TableFormer, where tabular structural biases are incorporated completely through learnable attention biases. TableFormer is (1) strictly invariant to row and column orders, and, (2) could understand tables better due to its tabular inductive biases. Our evaluations showed that TableFormer outperforms strong baselines in all settings on SQA, WTQ and TabFact table reasoning datasets, and achieves state-of-the-art performance on SQA, especially when facing answer-invariant row and column order perturbations (6% improvement over the best baseline), because previous SOTA models' performance drops by 4% - 6% when facing such perturbations while TableFormer is not affected.

TableFormer: Robust Transformer Modeling for Table-Text Encoding

The learning trajectories of linguistic phenomena in humans provide insight into linguistic representation, beyond what can be gleaned from inspecting the behavior of an adult speaker. To apply a similar approach to analyze neural language models (NLM), it is first necessary to establish that different models are similar enough in the generalizations they make. 
In this paper, we show that NLMs with different initialization, architecture, and training data acquire linguistic phenomena in a similar order, despite their different end performance. These findings suggest that there is some mutual inductive bias that underlies these models' learning of linguistic phenomena. Taking inspiration from psycholinguistics, we argue that studying this inductive bias is an opportunity to study the linguistic representation implicit in NLMs.

The Grammar-Learning Trajectories of Neural Language Models

Interpretability of semantic textual similarity (STS) is important for understanding how the similarity is made. In this presentation, we briefly introduce three useful outcomes described in the paper: an analytic method for STS, an approach of computing STS, and the training framework for STS. We show the effectiveness of these outcomes with various experimental settings.

Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning

We present a complete pipeline to extract characters in a novel and link them to their direct-speech utterances. Our model is divided into three independent components: extracting direct-speech, compiling a list of characters, and attributing those characters to their utterances. Although we find that existing systems can perform the first two tasks accurately, attributing characters to direct speech is a challenging problem due to the narrator's lack of explicit character mentions, and the frequent use of nominal and pronominal coreference when such explicit mentions are made. We adapt the progress made on Dialogue State Tracking to tackle a new problem: attributing speakers to dialogues. This is the first application of deep learning to speaker attribution, and it shows that is possible to overcome the need for the hand-crafted features and rules used in the past. Our full pipeline improves the performance of state-of-the-art models by a relative 50% in F1-score.

What does the sea say to the shore? A BERT based DST style approach for speaker to dialogue attribution in novels

Handing in a paper or exercise and merely receiving "bad" or "incorrect" as feedback is not very helpful when the goal is to improve. Unfortunately, this is currently the kind of feedback given by many Automatic Short Answer Grading (ASAG) systems. One of the reasons for this is a lack of content-focused elaborated feedback datasets. To encourage research on explainable and understandable feedback systems, we present the Short Answer Feedback dataset (SAF). Similar to other ASAG datasets, SAF contains learner responses and reference answers to German and English questions. However, instead of only assigning a label or score to the learners' answers, SAF also contains elaborated feedback explaining the given score. Thus, SAF enables supervised training of models that grade answers and explain where and why mistakes were made. This paper discusses the need for enhanced feedback models in real-world pedagogical scenarios, describes the dataset annotation process, gives a comprehensive analysis of SAF, and provides T5-based baselines for future comparison.

Introducing a Bilingual Short Answer Feedback Dataset

The COVID-19 pandemic has received extensive media coverage, with a vast variety of claims made about different aspects of the virus. In order to track these claims, we present COVID-19 Claim Radar, a system that automatically extracts claims relating to COVID-19 in news articles. We provide a comprehensive structured view of such claims, with rich attributes (such as claimers and their affiliations) and associated knowledge elements (such as events, relations and entities). 
Further, we use this knowledge to identify inter-claim connections such as equivalent, supporting, or refuting relations, with shared structural evidence like claimers, similar centroid events and arguments. In order to consolidate claim structures at the corpus-level, we leverage Wikidata as the hub to merge coreferential knowledge elements, and apply machine translation to aggregate claims from news articles in multiple languages. The system provides users with a comprehensive exposure to COVID-19 related claims, their associated knowledge elements, and related connections to other claims. The system is publicly available on GitHub and DockerHub, with complete documentation.

COVID-19 Claim Radar: A Structured Claim Extraction and Tracking System

Despite data's crucial role in machine learning, most existing tools and research tend to focus on systems on top of existing data rather than how to interpret and manipulate data. In this paper, we propose DataLab, a unified data-oriented platform that not only allows users to interactively analyze the characteristics of data, but also provides a standardized interface for different data processing operations

DataLab: A Platform for Data Analysis and Intervention

We present PromptSource, a system for creating, using and sharing natural language prompts. Prompting language models is an emerging area in NLP, and Promptsource allows seamless application of prompts, with a flexible templating language and a web-based GUI. Promptsource is straightforward to install in standard environments and interfaces with HF datasets library.

PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts

Lyrics generation has been a very popular application of natural language generation. Previous works mainly focused on generating lyrics based on a couple of attributes or keywords, rendering very limited control over the content of the lyrics. In this paper, we demonstrate the QiuNiu, a Chinese lyrics generation system which is conditioned on passage-level text rather than a few attributes or keywords. By using the passage-level text as input, the content of generated lyrics is expected to reflect the nuances of users’ needs. The QiuNiu system supports various forms of passage-level input, such as short stories, essays, poetry. The training of it is conducted under the framework of unsupervised machine translation, due to the lack of aligned passage-level text-to-lyrics corpus. We initialize the parameters of QiuNiu with a custom pretrained Chinese GPT-2 model and adopt a two-step process to finetune the model for better alignment between passage-level text and lyrics. Additionally, a postprocess module is used to filter and rerank the generated lyrics to select the ones of highest quality. The demo video of the system is available at https://youtu.be/OCQNzahqWgM.

On the Robustness of Offensive Language Classifiers

Downloads

Next from ACL 2022

Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models

Similar lecture

Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings