Thailand

Current abusive language detection systems have demonstrated unintended bias towards sensitive features such as nationality or gender. This is a crucial issue, which may harm minorities and underrepresented groups if such systems were integrated in real-world applications. In this paper, we create ad hoc tests through the CheckList tool (Ribeito et al., 2020) to detect biases within abusive language classifiers for English. We compare the behaviour of two BERT-based models, one trained on a generic abusive language dataset and the other on a dataset for misogyny detection. Our evaluation shows that, although BERT-based classifiers achieve high accuracy levels on a variety of natural language processing tasks, they perform very poorly as regards fairness and bias, in particular on samples involving implicit stereotypes, expressions of hate towards minorities and protected attributes such as race or sexual orientation. We release both the notebooks implemented to extend the Fairness tests and the synthetic datasets usable to evaluate systems bias independently of CheckList.

ACL-IJCNLP 2021

Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList

unintended bias

fairness

bias

evaluation

abusive language detection

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

workshop paper

Recently, the sequence-to-sequence models have made remarkable progress on the task of keyphrase generation (KG) by concatenating multiple keyphrases in a predefined order as a target sequence during training. However, the keyphrases are inherently an unordered set rather than an ordered sequence. Imposing a predefined order will introduce wrong bias during training, which can highly penalize shifts in the order between keyphrases. In this work, we propose a new training paradigm One2Set without predefining an order to concatenate the keyphrases. To fit this paradigm, we propose a novel model that utilizes a fixed set of learned control codes as conditions to generate a set of keyphrases in parallel. To solve the problem that there is no correspondence between each prediction and target during training, we propose a K-step label assignment mechanism via bipartite matching, which greatly increases the diversity and reduces the repetition rate of generated keyphrases. The experimental results on multiple benchmarks demonstrate that our approach significantly outperforms the state-of-the-art methods.

One2Set: Generating Diverse Keyphrases as a Set

This paper presents a simple recipe to trainstate-of-the-art multilingual Grammatical Error Correction (GEC) models. We achieve this by first proposing a language-agnostic method to generate a large number of synthetic examples. The second ingredient is to use large-scale multilingual language models (up to 11B parameters). Once fine-tuned on language-specific supervised sets we surpass the previous state-of-the-art results on GEC benchmarks in four languages: English, Czech, German and Russian. Having established a new set of baselines for GEC, we make our results easily reproducible and accessible by releasing a CLANG-8 dataset. It is produced by using our best model, which we call gT5, to clean the targets of a widely used yet noisy Lang-8 dataset. cLang-8 greatly simplifies typical GEC training pipelines composed of multiple fine-tuning stages – we demonstrate that performing a single fine-tuning stepon cLang-8 with the off-the-shelf language models yields further accuracy improvements over an already top-performing gT5 model for English.

A Simple Recipe for Multilingual Grammatical Error Correction

Recent years have witnessed various types of generative models for natural language generation (NLG), especially RNNs or transformer based sequence-to-sequence models, as well as variational autoencoder (VAE) and generative adversarial network (GAN) based models. However, flow-based generative models, which achieve strong performance in image generation due to their invertibility and exact density estimation properties, have been less explored for NLG. In this paper, we propose a flow-based language generation model by adapting previous flow generative models to language generation via continuous input embeddings, adapted affine coupling structures, and a novel architecture for autoregressive text generation. We also apply our framework to Sequence-to-Sequence generation, including text- and video-based Question Generation (QG) and Neural Machine Translation (NMT), and data augmentation for Question Answering (QA). We use our language flow model to provide extra input features for QG and NMT, which achieves improvements over the strong QG baselines on SQuAD and TVQA and NMT baseline on WMT16. We also augment QA data with new context by injecting noise to the latent features of the language flow and show this augmentation leads to a large performance improvement from strong baselines on SQuAD and TVQA.

Continuous Language Generative Flow

Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given. In this paper, we present a neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) to solve complex Text-to-SQL tasks for cross-domain databases. Statement Position Code (SPC) is defined to transform a nested SQL query into a set of non-nested SELECT statements; a sketch-based slot filling approach is proposed to synthesize each SELECT statement for its corresponding SPC. Additionally, two input manipulation methods are presented to improve generation performance further. RYANSQL achieved competitive result of 58.2% accuracy on the challenging Spider bench- mark. At the time of paper submission (April 2020), RYANSQL v2, a variant of original RYANSQL, is positioned at 3rd place among all systems and 1st place among the systems not using database content with 60.6% exact matching accuracy. The source code is available at https://github.com/kakaoenterprise/RYANSQL.

RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases

We introduce ChrEnTranslate, an online ma­chine translation demonstration system for translation between English and an endangered language Cherokee. It supports both statistical and neural translation models as well as pro­vides quality estimation to inform users of re­liability, two user feedback interfaces for ex­perts and common users respectively, exam­ple inputs to collect human translations for monolingual data, word alignment visualiza­tion, and relevant terms from the Cherokee­-English dictionary. The quantitative evalu­ation demonstrates that our backbone trans­lation models achieve state­of­the­art transla­tion performance and our quality estimation well correlates with both BLEU and human judgment. By analyzing 216 pieces of expert feedback, we find that NMT is preferable be­cause it copies less than SMT, and, in gen­eral, current models can translate fragments of the source sentence but make major mistakes. When we add these 216 expert­-corrected paral­lel texts into the training set and retrain mod­els, equal or slightly better performance is observed, which demonstrates indicates the po­tential of human-­in­-the­-loop learning.

ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback

Our understanding of why Transformer-based NLP models have been achieving their recent success lags behind our ability to continue scaling these models. To increase the transparency of Transformer-based language models, we present Ecco -- an open-source library for the explainability of Transformer-based NLP models. 

Ecco provides a set of tools to capture, analyze, visualize, and interactively explore inner mechanics of these models. This includes 
1) Gradient-based feature attribution for natural language generation 
2) Hidden states and their evolution between model layers 
3) Convenient access and examination tools for neuron activations in the under-explored Feed-Forward Neural Network sublayer of Transformer layers. 
4) Convenient examination of activation vectors via canonical correlation analysis (CCA), non-negative matrix factorization (NMF), and probing classifiers. 

We find that syntactic information can be retrieved from BERT's FFNN representations in levels comparable to those in hidden state representations. More curiously, we find that the model builds up syntactic information in its hidden states even when intermediate FFNNs indicate diminished levels of syntactic information. Ecco is available at https://www.eccox.io/.

Ecco: An Open Source Library for the Explainability of Transformer Language Models

Adobe’s Portable Document Format (PDF) is a popular way of distributing view-only documents with a rich visual markup. This presents a challenge to NLP practitioners who wish to use the information contained within PDF documents for training models or data analysis, because annotating these documents is difficult. In this paper, we present PDF Annotation with Labels and Structure (PAWLS), a new annotation tool designed specifically for the PDF document format. PAWLS is particularly suited for mixed-mode annotation and scenarios in which annotators require extended context to annotate accurately. PAWLS supports span-based textual annotation, N-ary relations and freeform, non-textual bounding boxes, all of which can be exported in convenient formats for training multi-modal machine learning models. A read-only PAWLS server is available at https://pawls.apps.allenai.org/ (please see Appendix for instructions on accessing the demo), and the source code is available at https://github.com/allenai/pawls.

PAWLS: PDF Annotation With Labels and Structure

The usage of individual words can change over time, for example, when words experience a semantic shift. As text datasets generally comprise documents that were collected over a longer period of time, examining word usage changes in a corpus can often reveal interesting patterns. In this paper, we introduce a simple and intuitive way to track word usage changes via continuously evolving embeddings, computed as a weighted running average of transformer-based contextualized embeddings. We demonstrate our approach on a corpus of recent New York Times article snippets and provide code for an easy to use web app to conveniently explore semantic shifts with interactive plots.

Exploring Word Usage Change with Continuously Evolving Embeddings

Hate speech and profanity detection sufferfrom data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane subspaces in wordand sentence representations and explore their generalization capability on a variety of similar and distant target tasks in a zero-shot setting. This is done monolingually (German) and cross-lingually to closely-related (English), distantly-related (French) and non-related (Arabic) tasks. We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10.9 and F1 +42.9 over the baselines across all tested monolingual and cross-lingual scenarios.

Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces

Mainstream research on hate speech focused so far predominantly on the task of classifying, e.g., social media posts, with respect to predefined typologies of rather coarse-grained hate speech categories. This may be sufficient if the goal is to detect and delete abusive language posts. However, removal is not always possible due to the legislation of a country. Also, there is evidence that hate speech cannot be successfully combated by merely removing hate speech posts; they should be countered by education and counter-narratives. For this purpose, we need to identify (i) who is the target in a given hate speech post, and (ii) what aspects (or characteristics) of the target are attributed to the target in the post. As the first approximation, we propose to adapt a generic state-of-the-art concept extraction model to the hate speech domain. The outcome of the experiments is promising and can serve as inspiration for further work on the task.

Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList

Downloads

Next from ACL-IJCNLP 2021

One2Set: Generating Diverse Keyphrases as a Set

Similar lecture

Mitigating Biases in Toxic Language Detection through Invariant Rationalization

Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL-IJCNLP 2021

One2Set: Generating Diverse Keyphrases as a Set

Similar lecture

Mitigating Biases in Toxic Language Detection through Invariant Rationalization

Downloads