United States

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

NAACL 2021

Ad hominem attacks are those that target some feature of a person's character instead of the position the person is maintaining. These attacks are harmful because they propagate implicit biases and diminish a person's credibility. Since dialogue systems respond directly to user input, it is important to study ad hominems in dialogue responses. To this end, we propose categories of ad hominems, compose an annotated dataset, and build a classifier to analyze human and dialogue system responses to English Twitter posts. We specifically compare responses to Twitter topics about marginalized communities (#BlackLivesMatter, #MeToo) versus other topics (#Vegan, #WFH), because the abusive language of ad hominems could further amplify the skew of power away from marginalized populations. Furthermore, we propose a constrained decoding technique that uses salient n-gram similarity as a soft constraint for top-k sampling to reduce the amount of ad hominems generated. Our results indicate that 1) responses from both humans and DialoGPT contain more ad hominems for discussions around marginalized communities, 2) different quantities of ad hominems in the training data can influence the likelihood of generating ad hominems, and 3) we can use constrained decoding techniques to reduce ad hominems in generated dialogue responses.

"Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses

technical paper

Implicitly Abusive Language -- What does it actually look like and why are we not getting there?

On learning and representing social meaning in NLP: a sociolinguistic perspective

The Importance of Modeling Social Factors of Language: Theory and Practice

Preregistering NLP research

Noisy Self-Knowledge Distillation for Text Summarization

Extending Multi-Document Summarization Evaluation to the Interactive Setting

Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation

Enhancing Factual Consistency of Abstractive Summarization

Extractive Opinion Summarization in Quantized Transformer Spaces

Few-shot Intent Classification and Slot Filling with Retrieved Examples

https://d3smihljt9218e.cloudfront.net/transcript/13570/subtitle/815c409bed56d763fa62fcbd73738dc9.vtt

English (automatic)

"Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses

Downloads

Next from NAACL 2021

Implicitly Abusive Language -- What does it actually look like and why are we not getting there?

Similar lecture

FUDGE: Controlled Text Generation With Future Discriminators