Thailand

Tackling online hatred using informed textual responses -- called counter narratives -- has been brought under the spotlight recently. Accordingly, a research line has emerged to automatically generate counter narratives in order to facilitate the direct intervention in the hate discussion and to prevent hate content from further spreading. Still, current neural approaches tend to produce generic/repetitive responses and lack grounded and up-to-date evidence such as facts, statistics, or examples. Moreover, these models can create plausible but not necessarily true arguments. In this paper we present the first complete knowledge-bound counter narrative generation pipeline, grounded in an external knowledge repository that can provide more informative content to fight online hatred. Together with our approach, we present a series of experiments that show its feasibility to produce suitable and informative counter narratives in in-domain and cross-domain settings.

ACL-IJCNLP 2021

Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

knowledge-grounded generation

counter narrative generation

hate speech countering

**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

Understanding privacy policies is crucial for users as it empowers them to learn about the information that matters to them. Sentences written in a privacy policy document explain privacy practices, and the constituent text spans convey further specific information about that practice. We refer to predicting the privacy practice explained in a sentence as intent classification and identifying the text spans sharing specific information as slot filling. In this work, we propose PolicyIE, an English corpus consisting of 5,250 intent and 11,788 slot annotations spanning 31 privacy policies of websites and mobile applications. PolicyIE corpus is a challenging real-world benchmark with limited labeled examples reflecting the cost of collecting large-scale annotations from domain experts. We present two alternative neural approaches as baselines, (1) intent classification and slot filling as a joint sequence tagging and (2) modeling them as a sequence-to-sequence (Seq2Seq) learning task. The experiment results show that both approaches perform comparably in intent classification, while the Seq2Seq method outperforms the sequence tagging approach in slot filling by a large margin. We perform a detailed error analysis to reveal the challenges of the proposed corpus.

Intent Classification and Slot Filling for Privacy Policies

For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities, or domains. In pursuit of these goals, we introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. By including tasks with limited training data, RADDLE is designed to favor and encourage models with a strong generalization ability. RADDLE also includes a diagnostic checklist that facilitates detailed robustness analysis in aspects such as language variations, speech errors, unseen entities, and out-of-domain utterances. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain. Adversarial training is also proposed to improve model robustness against noisy inputs. Overall, existing models are less than satisfactory in robustness evaluation, which suggests opportunities for future improvement.

RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adaptive pretraining objectives on downstream tasks. In particular, three objectives, including a novel objective focusing on modeling predicate-argument relations, are evaluated on two challenging dialogue understanding tasks. Experimental results demonstrate that domain-adaptive pretraining with proper objectives can significantly improve the performance of a strong baseline on these tasks, achieving the new state-of-the-art performances.

Domain-Adaptive Pretraining Methods for Dialogue Understanding

This talk introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Compared to most previous publicly available text understanding systems and tools, TexSmart holds some unique features.
First, the NER function of TexSmart supports over 1,000 entity types, while most other public tools typically support several to (at most) dozens of entity types.
Second, TexSmart introduces new semantic analysis functions like semantic expansion and deep semantic representation, that are absent in most previous systems. Third, a spectrum of algorithms (from very fast algorithms to those that are relatively slow but more accurate) are implemented for one function in TexSmart, to fulfill the requirements of different academic and industrial applications.
The adoption of unsupervised or weakly-supervised algorithms is especially emphasized, with the goal of easily updating our models to include fresh data with less human annotation efforts.~\footnote{TexSmart is available at \url{https://texsmart.qq.com/en}, and the long version of this paper can be found in the technical report~\cite{zhang2020texsmart}.}

TexSmart: A System for Enhanced Natural Language Understanding

In this paper, we release an open-source library, called TextBox, to provide a unified, modularized, and extensible text generation framework. TextBox aims to support a broad set of text generation tasks and models. In our library, we implement 21 text generation models on 9 benchmark datasets, covering the categories of VAE, GAN, and pretrained language models. Meanwhile, our library maintains sufficient modularity and extensibility by properly decomposing the model architecture, inference, and learning process into highly reusable modules, which allows users to easily incorporate new models into our framework. The above features make TextBox specially suitable for researchers and practitioners to quickly reproduce baseline models and develop new models. TextBox is implemented based on PyTorch, and released under Apache License 2.0 at the link https: //github.com/RUCAIBox/TextBox.

TextBox: A Unified, Modularized, and Extensible Framework for Text Generation

ASCENT is a fully automated methodology for extracting and consolidating commonsense assertions from web contents (Nguyen et al., WWW 2021). It advances traditional triple-based commonsense knowledge representation by capturing semantic facets like locations and purposes, and composite concepts, i.e., subgroups and related aspects of subjects. In this demo, we present a web portal that allows users to understand its construction process, explore its content, and observe its impact in the use case of question answering. The demo website (https://ascent.mpi-inf.mpg.de/) and an introductory video (https://youtu.be/qMkJXqu_Yd4) are both available online.

Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering

Ethical aspects of research in language technologies have received much attention recently. It is a standard practice to get a study involving human subjects reviewed and approved by a professional ethics committee/board of the institution. How commonly do we see mention of ethical approvals in NLP research? What types of research or aspects of studies are usually subject to such reviews? With the rising concerns and discourse around the ethics of NLP, do we also observe a rise in formal ethical reviews of NLP studies? And, if so, would this imply that there is a heightened awareness of ethical issues that was previously lacking? We aim to address these questions by conducting a detailed quantitative and qualitative analysis of the ACL Anthology, as well as comparing the trends in our field to those of other related disciplines, such as cognitive science, machine learning, data mining, and systems.

Use of Formal Ethical Reviews in NLP Literature: Historical Trends and Current Practices

Social media has changed the way we engage in social activities. On Twitter, users can participate in social movements using hashtags such as #MeToo; this is known as hashtag activism. However, while these hashtags can help reshape social norms, they can also be used maliciously by spammers or troll communities for other purposes, such as signal boosting unrelated content, making a dent in a movement, or sharing hate speech. We present a Tweet-level hashtag hijacking detection framework focusing on hashtag activism. Our weakly-supervised framework uses bootstrapping to update itself as new Tweets are posted. Our experiments show that the system adapts to new topics in a social movement, as well as new hijacking strategies, maintaining strong performance over time.

Detecting Hashtag Hijacking for Hashtag Activism

Technologies for enhancing well-being, healthcare vigilance and monitoring are on the rise.
However, despite patient interest, such technologies suffer from low adoption. One hypothesis for this limited adoption is loss of human interaction that is central to doctor-patient encounters. In this paper we seek to address this limitation via a conversational agent that adopts one aspect of in-person doctor-patient interactions: A human avatar to facilitate medical grounded question answering. This is akin to the in-person scenario where the doctor may point to the human body or the patient may point to their own body to express their conditions. Additionally, our agent has multiple interaction modes, that may give more options for the patient to use the agent, not just for medical question answering, but also to engage in conversations about general topics and current events. Both the avatar, and the multiple interaction modes could help improve adherence.

We present a high level overview of the design of our agent, Marie Bot Wellbeing. We also report implementation details of our early prototype , and present preliminary results

A Grounded Well-being Conversational Agentwith Multiple Interaction Modes: Preliminary Results

Augmentative and Alternative Communication (AAC) devices and applications are intended to make it easier for individuals with complex communication needs to participate in conversations. However, these devices have low adoption and retention rates. We review prior work with text recommendation systems that have not been successful in mitigating these problems. To address these gaps, we propose applying Dialogue Act classification to AAC conversations. We evaluated the performance of a state of the art model on a limited AAC dataset that was trained on both AAC and non-AAC datasets. The one trained on AAC (accuracy = 38.6%) achieved better performance than that trained on a non-AAC corpus (accuracy = 34.1%). These results reflect the need to incorporate representative datasets in later experiments. We discuss the need to collect more labeled AAC datasets and propose areas of future work.


Next from ACL-IJCNLP 2021

Intent Classification and Slot Filling for Privacy Policies

Similar lecture

Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech