United States

In this presentation, we are going to talk about the work we&#39;ve done in task3, PreTENS, which is aimed at evaluating the acceptability of simple sentences containing constructions whose two arguments are presupposed to be or not to be in an ordered taxonomic relation.

NAACL 2022

Recognize Appropriate Taxonomic Relations Between Two Nominal Arguments with ERNIE-M Model

presupposition prediction

ernie-m

pre-trained model

data augmentation

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
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, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 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 and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

In this presentation, we are going to talk about the work we've done in task3, PreTENS, which is aimed at evaluating the acceptability of simple sentences containing constructions whose two arguments are presupposed to be or not to be in an ordered taxonomic relation.

workshop paper

In the SubTaskA, we use InfoXLM as text encoder and exponential moving average (EMA) method and the adversarial attack strategy.

In the SubTaskB, we add an cross-attention module, contrastive objective and employ a momentum contrast.

Additionally, we use the alignment and uniformity properties to measure the quality of sentence embeddings.

ZhichunRoad at SemEval-2022 Task 2: Adversarial Training and Contrastive Learning for Multiword Representations

Kyle (1985) proposes two types of rumors: in- formed rumors that are based on some private information and uninformed rumors that are not based on any information (i.e. bluffing). Also, prior studies find that when people have credible source of information, they are likely to use a more confident textual tone in their spreading of rumors. Motivated by these theoretical findings, we propose a double-channel structure to determine the ex-ante veracity of rumors on social media. Our ultimate goal is to classify each rumor into true, false, or unverifiable category. We first assign each text into either certain (informed rumor) or uncertain (uninformed rumor) category. Then, we apply lie detection algorithm to informed rumors and thread-reply agreement detection algorithm to uninformed rumors. Using the dataset of SemEval 2019 Task 7, which requires ex-ante threefold classification (true, false, or unverifiable) of social media rumors, our model yields a macro-F1 score of 0.4027, outperforming all the baseline models and the second-place winner (Gorrell et al., 2019). Furthermore, we empirically validate that the double-channel structure outperforms single-channel structures which use either lie detection or agreement de- tection algorithm to all posts.

Detecting Rumor Veracity with Only Textual Information by Double-Channel Structure

The last few years have witnessed an exponential rise in the propagation of offensive text on social media. Identification of this text with high precision is crucial for the well-being of society. Most of the existing approaches tend to give high toxicity scores to innocuous statements (e.g., “I am a gay man”). These false positives result from over-generalization on the training data where specific terms in the statement may have been used in a pejorative sense (e.g., “gay”). Emphasis on such words alone can lead to discrimination against the classes these systems are designed to protect. In this paper, we address the problem of offensive language detection on Twitter, while also detecting the type and the target of the offence. We propose a novel approach called SyLSTM, which integrates syntactic features in the form of the dependency parse tree of a sentence and semantic features in the form of word embeddings into a deep learning architecture using a Graph Convolutional Network. Results show that the proposed approach significantly outperforms the state-of-the-art BERT model with orders of magnitude fewer number of parameters.

Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks

The present work constitutes an attempt to investigate the relational structures learnt by mBERT, a multilingual transformer-based network, with respect to different cross-linguistic regularities proposed in the fields of theoretical and quantitative linguistics. We pursued this objective by relying on a zero-shot transfer experiment, evaluating the model's ability to generalize its native task to artificial languages that could either respect or violate some proposed language universal, and comparing its performance to the output of BERT, a monolingual model with an identical configuration. We created four artificial corpora through a Probabilistic Context-Free Grammar by manipulating the distribution of tokens and the structure of their dependency relations. We showed that while both models were favoured by a Zipfian distribution of the tokens and by the presence of head-dependency type structures, the multilingual transformer network exhibited a stronger reliance on hierarchical cues compared to its monolingual counterpart.

Multilingualism Encourages Recursion: a Transfer Study with mBERT

This study describes the structure and the results of the SIGTYP 2022 shared task on the prediction of cognate reflexes from multilingual wordlists. We asked participants to submit systems that would predict words in individual languages with the help of cognate words from related languages. Training and surprise data were based on standardized multilingual wordlists from several language families. Four teams submitted a total of eight systems, including both neural and non-neural systems, as well as systems adjusted to the task and systems using more general settings. While all systems showed a rather promising performance, reflecting the overwhelming regularity of sound change, the best performance throughout was achieved by a system based on convolutional networks originally designed for image restoration.

The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes

This talk introduces a database for cross-linguistic modal semantics. the purpose of this database is to (1) enable ongoing consolidation of modal semantic typological knowledge into a repository according to uniform data standards and to (2) provide data for investigations in crosslinguistic modal semantic theory and experiments explaining such theories. We describe the kind of semantic variation that the database aims to record, the format of the data, and a current snapshot of the database, emphasizing access and contribution to the database in light of the goals above. Additionally, we dicuss some research potentials of this database.

A Database for Modal Semantic Typology

In Jäger (2019) a computational framework was defined to start from parallel word lists of related languages and infer the corresponding vocabulary of the shared proto-language. The SIGTYP 2022 Shared Task is closely related. The main difference is that what is to be reconstructed is not the proto-form but an unknown word from an extant language. The system described here is a re-implementation of the tools used in the mentioned paper, adapted to the current task.

Bayesian phylogenetic cognate prediction

This work describes an implementation of the “extended alignment” model for cognate reflex prediction submitted to the “SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes”. Similarly to List et al. (2022a), the technique involves an automatic extension of sequence alignments with multilayered vectors that encode informational tiers on both site-specific traits, such as sound classes and distinctive features, as well as contextual and suprasegmental ones, conveyed by cross-site referrals and replication. The method allows to generalize the problem of cognate reflex prediction as a classification problem, with models trained using a parallel corpus of cognate sets. A model using random forests is trained and evaluated on the shared task for reflex prediction, and the experimental results are presented and discussed along with some differences to other implementations.

Reflex Prediction Through Extended Alignments

Digital harms can manifest across any interface. Key problems in addressing these harms include the high individuality of harms and the fast-changing nature of digital systems. As a result, we still lack a systematic approach to study harms and produce interventions for end-users. We put forward GreaseVision, a new framework that enables end-users to collaboratively develop interventions against harms in software using a no-code approach and recent advances in few-shot machine learning. The contribution of the framework and tool allow individual end-users to study their usage history and create personalized interventions. Our contribution also enables researchers to study the distribution of harms and interventions at scale.

Rewriting the Rules of the Interface

This work describes the process of creating a corpus of Twitter conversations annotated for the presence of \textit{counterspeech} in response to toxic speech related to axes of discrimination linked to sexism, racism and homophobia. 
The main novelty is an annotated dataset comprising relevant tweets in their context of occurrence. 
The corpus is made up of tweets and responses captured by different profiles replying to discriminatory content or objectionably couched news. 
An annotation scheme was created to illustrate the relevant dimensions of toxic speech and counterspeech.
An analysis of the collected and annotated data and of the Inter-Annotator Agreement (IAA) that emerged during the annotation process is included. Moreover, we report about preliminary experiments on automatic \textit{counterspeech} detection, based on supervised automatic learning models trained on the new dataset. 
The results highlight the fundamental role played by the context in this detection task, confirming our intuitions about the importance to collect tweets in their context of occurrence.

Downloads

Next from NAACL 2022

ZhichunRoad at SemEval-2022 Task 2: Adversarial Training and Contrastive Learning for Multiword Representations

Similar lecture

PreTENS — EvaluatingNeural Networks on Presuppositional Semantic Knowledge