Thailand

Majority voting and averaging are common approaches employed to resolve annotator disagreements and derive singular ground truth labels from multiple annotations. However, annotators may systematically disagree with one another, often reflecting their individual biases and values, especially in the case of subjective tasks such as detecting affect, aggression, and hate speech. Annotator disagreements may capture important nuances in such tasks that are often ignored while aggregating annotations to single ground truth. In order to address this, we investigate the efficacy of multi-annotator models. In particular, our multi-task based approach treats predicting each annotators&#39; judgements as separate subtasks, while sharing a common learned representation of the task. We show that this approach yields better performance than aggregating labels in the data prior to training. Our approach also provides a way to better estimate uncertainty in predictions, which we demonstrate better correlate with annotation disagreements than traditional methods. Being able to model uncertainty is especially useful in deployment scenarios where knowing when not to make a prediction is important.

ACL-IJCNLP 2021

Multi-Annotator Modeling to Encode Diverse Perspectives in Hate Speech Annotations

prediction uncertainty

annotator disagreements

annotator bias

# 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)

ACL 2022

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). 

Majority voting and averaging are common approaches employed to resolve annotator disagreements and derive singular ground truth labels from multiple annotations. However, annotators may systematically disagree with one another, often reflecting their individual biases and values, especially in the case of subjective tasks such as detecting affect, aggression, and hate speech. Annotator disagreements may capture important nuances in such tasks that are often ignored while aggregating annotations to single ground truth. In order to address this, we investigate the efficacy of multi-annotator models. In particular, our multi-task based approach treats predicting each annotators' judgements as separate subtasks, while sharing a common learned representation of the task. We show that this approach yields better performance than aggregating labels in the data prior to training. Our approach also provides a way to better estimate uncertainty in predictions, which we demonstrate better correlate with annotation disagreements than traditional methods. Being able to model uncertainty is especially useful in deployment scenarios where knowing when not to make a prediction is important.

workshop paper

**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).

Syntactic structure is an important component of natural language text. Recent top-performing models in Answer Sentence Selection (AS2) use self-attention and transfer learning, but not syntactic structure. Tree structures have shown strong performance in tasks with sentence pair input like semantic relatedness. We investigate whether tree structures can boost performance in AS2. We introduce the Tree Aggregation Transformer: a novel recursive, tree-structured self-attention model for AS2. The recursive nature of our model is able to represent all levels of syntactic parse trees with only one additional self-attention layer. Without transfer learning, we establish a new state of the art on the popular TrecQA and WikiQA benchmark datasets. Additionally, we evaluate our method on four Community Question Answering datasets, and find that tree-structured representations have limitations with noisy user-generated text. We conduct probing experiments to evaluate how our models leverage tree structures across datasets. Our findings show that the ability of tree-structured models to successfully absorb syntactic information is strongly correlated with a higher performance in AS2.

Recursive Tree-Structured Self-Attention for Answer Sentence Selection

Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowledge to improve the efficiency of RL agents for TBGs. In this paper, we posit that to act efficiently in TBGs, an agent must be able to track the state of the game while retrieving and using relevant commonsense knowledge. Thus, we propose an agent for TBGs that induces a graph representation of the game state and jointly grounds it with a graph of commonsense knowledge from ConceptNet. This combination is achieved through bidirectional knowledge graph attention between the two symbolic representations. We show that agents that incorporate commonsense into the game state graph outperform baseline agents.

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations

We introduce mTVR, a large-scale multilingual video moment retrieval dataset, containing 218K English and Chinese queries from 21.8K TV show video clips. The dataset is collected by extending the popular TVR dataset (in English) with paired Chinese queries and subtitles. Compared to existing moment retrieval datasets, mTVR is multilingual, larger, and comes with diverse annotations. We further propose mXML, a multilingual moment retrieval model that learns and operates on data from both languages, via encoder parameter sharing and language neighborhood constraints. We demonstrate the effectiveness of mXML on the newly collected mTVR dataset, where mXML outperforms strong monolingual baselines while using fewer parameters. In addition, we also provide detailed dataset analyses and model ablations. Data and code are publicly available at https://github.com/jayleicn/mTVRetrieval

mTVR: Multilingual Moment Retrieval in Videos

Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop FastSeq framework to accelerate sequence generation without accuracy loss. The proposed optimization techniques include an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O. These optimizations are general enough to be applicable to Transformer-based models (e.g., T5, GPT2, and UniLM). Our benchmark results on a set of widely used and diverse models demonstrate 4-9x inference speed gain. Additionally, FastSeq is easy to use with a simple one-line code change. The source code is available at https://github.com/microsoft/fastseq.

FastSeq: Make Sequence Generation Faster

In recent years, conversational recommender system (CRS) has drawn a wide attention in the research community, which focuses on providing high-quality recommendations to users via natural language conversations. To facilitate the implementation of CRS, we release an open-source toolkit CRSLab, which provides a unified and extensible framework with highly-decoupled modules to develop CRSs.
Based on this framework, we collect 6 commonly used human-annotated CRS datasets and implement 19 models. Besides, our toolkit provides a series of automatic evaluation protocols and a human-machine interaction interface to evaluate and compare different CRS methods. The project and documents are released at https://github.com/RUCAIBox/CRSLab.

CRSLab: An Open-Source Toolkit for Building Conversational Recommender System

Hate speech-related lexicons have been proved to be useful for many tasks such as data collection and classification. However, existing Portuguese lexicons do not distinguish between European and Brazilian Portuguese, and do not include neutral terms that are potentially useful to detect a broader spectrum of content referring to minorities. In this work, we present MIN\_PT, a new European Portuguese Lexicon for Minorities-Related Terms specifically designed to tackle the limitations of existing resources. We describe the data collection and annotation process, discuss the limitation and ethical concerns, and prove the utility of the resource by applying it to a use case for the Portuguese 2021 presidential elections.

MIN_PT: An European Portuguese Lexicon for Minorities Related Terms

Social media texts such as blog posts, comments, and tweets often contain offensive languages including racial hate speech comments, personal attacks, and sexual harassment. Detecting inappropriate use of language is, therefore, of utmost importance for the safety of the users as well as for suppressing hateful conduct and aggression. Existing approaches to this problem are mostly available for resource-rich languages such as English and German. In this paper, we characterize the offensive language in Nepali, a low-resource language, highlighting the challenges that need to be addressed for processing Nepali social media text. We also present experiments for detecting offensive language using supervised machine learning. Besides contributing the first baseline approaches of detecting offensive language in Nepali, we also release human annotated data sets to encourage future research on this crucial topic.

Offensive Language Detection in Nepali Social Media

Hateful memes pose a unique challenge for current machine learning systems because their message is derived from both text- and visual-modalities. To this effect, Facebook re-leased the Hateful Memes Challenge, a dataset of memes with pre-extracted text captions, but it is unclear whether these synthetic examples generalize to ‘memes in the wild’. In this paper, we collect hateful and non-hateful memes from Pinterest to evaluate out-of-sample performance on models pre-trained on the Facebook dataset. We find that memes in the wild differ in two key aspects: 1) Captions must be extracted via OCR, injecting noise and diminishing performance of multimodal models, and 2) Memes are more diverse than ‘traditional memes’, including screenshots of conversations or text on a plain background. This paper thus serves as a reality check for the current benchmark of hateful meme detection and its applicability for detecting real world hate.

Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset

User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on current datasets will also disregard context, making the detection of context-sensitive toxicity a lot harder when it occurs. We constructed and publicly release a dataset of 10k posts with two kinds of toxicity labels per post, obtained from annotators who considered (i) both the current post and the previous one as context, or (ii) only the current post. We introduce a new task, context sensitivity estimation, which aims to identify posts whose perceived toxicity changes if the context (previous post) is also considered. Using the new dataset, we show that systems can be developed for this task. Such systems could be used to enhance toxicity detection datasets with more context-dependent posts, or to suggest when moderators should consider the parent posts, which may not always be necessary and may introduce an additional cost.

Multi-Annotator Modeling to Encode Diverse Perspectives in Hate Speech Annotations

Downloads

Next from ACL-IJCNLP 2021

Recursive Tree-Structured Self-Attention for Answer Sentence Selection

Similar lecture

Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations

Multi-Annotator Modeling to Encode Diverse Perspectives in Hate Speech Annotations

.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

Recursive Tree-Structured Self-Attention for Answer Sentence Selection

Similar lecture

Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations

Downloads