Thailand

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.

IJCNLP-AACL 2021

Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces

subspace

hate speech

zero-shot

multilingual

**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

We study the problem of building entity tagging systems by using a few rules as weak supervision. Previous methods mostly focus on disambiguating entity types based on contexts and expert-provided rules, while assuming entity spans are given. In this work, we propose a novel method TALLOR that bootstraps high-quality logical rules to train a neural tagger in a fully automated manner. Specifically, we introduce compound rules that are composed from simple rules to increase the precision of boundary detection and generate more diverse pseudo labels. We further design a dynamic label selection strategy to ensure pseudo label quality and therefore avoid overfitting the neural tagger. Experiments on three datasets demonstrate that our method outperforms other weakly supervised methods and even rivals a state-of-the-art distantly supervised tagger with a lexicon of over 2,000 terms when starting from only 20 simple rules. Our method can serve as a tool for rapidly building taggers in emerging domains and tasks. Case studies show that learned rules can potentially explain the predicted entities.

Weakly Supervised Named Entity Tagging with Learnable Logical Rules

Fine-tuning is the de facto way of leveraging large pretrained language models for downstream tasks. However, fine-tuning modifies all the language model parameters and therefore necessitates storing a full copy for each task. In this paper, we propose prefix-tuning, a lightweight alternative to fine-tuning for natural language generation tasks, which keeps language model parameters frozen and instead optimizes a sequence of continuous task-specific vectors, which we call the prefix. Prefix-tuning draws inspiration from prompting for language models, allowing subsequent tokens to attend to this prefix as if it were “virtual tokens”. We apply prefix-tuning to GPT-2 for table-to-text generation and to BART for summarization. We show that by learning only 0.1% of the parameters, prefix-tuning obtains comparable performance in the full data setting, outperforms fine-tuning in low-data settings, and extrapolates better to examples with topics that are unseen during training.

Prefix-Tuning: Optimizing Continuous Prompts for Generation

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

Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called ``extractive search'', in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and its benefits and potential.
Our prototype is available at \url{https://spike.neural-sim.apps.allenai.org/} and a video demonstration is available at \url{https://vimeo.com/559586687}.

Neural Extractive Search

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

CLTR is an end-to-end system for table question answering (QA). It can retrieve tables from a large table corpus for given natural language questions and locate table cells to answer the questions.

The system integrates the Row-Column Intersection (RCI) model with traditional information retrieval methods. CLTR is the current state-of-the-art system for table retrieval. It can accurately answer user-given natural language questions using table cells and create heatmap over tables.

With the CLTR system, we introduce two new benchmarks to the community for end-to-end table QA evaluation. 


CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering

Probing (or diagnostic classification) has become a popular strategy for investigating
whether a given set of intermediate features is present in the representations of neural models. Probing studies may have misleading results, but various recent works have suggested more reliable methodologies that compensate for the possible pitfalls of probing. However, these best practices are numerous and fast-evolving. To simplify the process of running a set of probing experiments in line with suggested methodologies, we introduce Probe-Ably: an extendable probing framework which supports and automates the application of probing methods
to the user's inputs.

Does My Representation Capture X? Probe-Ably

Abusive language is a growing phenomenon on social media platforms. Its effects can reach beyond the online context, contributing to mental or emotional stress on users. Automatic tools for detecting abuse can alleviate the issue. In practice, developing automated methods to detect abusive language relies on good quality data. However, there is currently a lack of standards for creating datasets in the field. These standards include definitions of what is considered abusive language, annotation guidelines and reporting on the process. This paper introduces an anno- tation framework inspired by legal concepts to define abusive language in the context of online harassment. The framework uses a 7- point Likert scale for labelling instead of class labels. We also present ALYT – a dataset of Abusive Language on YouTube. ALYT includes YouTube comments in English extracted from videos on different controversial topics and labelled by Law students. The comments were sampled from the actual collected data, without artificial methods for increasing the abusive content. The paper describes the annotation process thoroughly, including all its guidelines and training steps.

Abusive Language on Social Media Through the Legal Looking Glass

Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most training datasets for toxicity detection. The biases make the learned models unfair and can even exacerbate the marginalization of people. Considering that current debiasing methods for general natural language understanding tasks cannot effectively mitigate the biases in the toxicity detectors, we propose to use invariant rationalization (InvRat), a game-theoretic framework consisting of a rationale generator and a predictor, to rule out the spurious correlation of certain syntactic patterns (e.g., identity mentions, dialect) to toxicity labels. We empirically show that our method yields lower false positive rate in both lexical and dialectal attributes than previous debiasing methods.

Mitigating Biases in Toxic Language Detection through Invariant Rationalization

As socially unacceptable language become pervasive in social media platforms, the need for automatic content moderation become more pressing. This contribution introduces the Dutch Abusive Language Corpus (DALC v1.0), a new dataset with tweets manually an- notated for abusive language. The resource address a gap in language resources for Dutch and adopts a multi-layer annotation scheme modeling the explicitness and the target of the abusive messages. Baselines experiments on all annotation layers have been conducted, achieving a macro F1 score of 0.748 for binary classification of the explicitness layer and .489 for target classification.

Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces

Downloads

Next from IJCNLP-AACL 2021

Weakly Supervised Named Entity Tagging with Learnable Logical Rules

Similar lecture

How to Adapt Your Pretrained Multilingual Model to 1600 Languages

Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces

.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 IJCNLP-AACL 2021

Weakly Supervised Named Entity Tagging with Learnable Logical Rules

Similar lecture

How to Adapt Your Pretrained Multilingual Model to 1600 Languages

Downloads