Korea, Republic of

The paper describes neural models developed for the DAGPap22 shared task hosted at the Third Workshop on Scholarly Document Processing. This shared task targets the automatic detection of generated scientific papers. Our work focuses on comparing different transformer-based models as well as using additional datasets and techniques to deal with imbalanced classes. As a final submission, we utilized an ensemble of SciBERT, RoBERTa, and DeBERTa fine-tuned using random oversampling technique. Our model achieved 99.24% in terms of F1-score. The official evaluation results have put our system at the third place.

COLING 2022

Detecting generated scientific papers using an ensemble of transformer models

generated texts

scientific texts

imbalanced data

text classification

transformer

The International Conference on Computational Processing of Portuguese (PROPOR) is the main event in the area of human language processing that is focused on theoretical and technological issues of written and spoken Portuguese and Galician. The meeting has been a very rich forum for the exchange of ideas and partnerships for the research and industry communities dedicated to the automated processing of Portuguese, promoting the development of methodologies, resources and projects that can be shared among researchers and practitioners in the field.

Find more information and pay the registration fee on [event organizer’s website](https://sites.universidadedefortaleza.com/propor2022/?page_id=401)

PROPOR 2022

The International Conference on Computational Processing of Portuguese (PROPOR) is the main event in the area of human language processing that is focused on theoretical and technological issues of written and spoken Portuguese and Galician.

workshop paper

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes but also in industrial research departments including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!<br><br><br>

To gain access to this event page you are required to register.<br> Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

We present a new gold-standard dataset and a benchmark for the \textit{Research Theme Identification} task, a sub-task of the Scholarly Knowledge Graph Generation shared task, at the 3rd Workshop on Scholarly Document Processing. The objective of the shared task was to label given research papers with research themes from a total of 36 themes. The benchmark was compiled using data drawn from the
largest overall assessment of university research
output ever undertaken globally (the Research Excellence Framework - 2014).

We provide a performance comparison of a transformer-based ensemble, which obtains multiple predictions for a research paper, given its multiple textual fields (e.g. title, abstract, reference), with traditional machine learning models. The ensemble involves enriching the initial data with additional information from open-access digital libraries and Argumentative Zoning techniques. It uses a weighted sum aggregation for the multiple predictions to obtain a final single prediction for the given research paper.

Both data and the ensemble are publicly available on https://www.kaggle.com/competitions/sdp2022-scholarly-knowledge-graph-generation/data?select=task1_test_no_label.csv and https://github.com/ProjectDoSSIER/sdp2022, respectively.

Benchmark for Research Theme Classification of Scholarly Documents

This paper is a description of our participation in the Multi-document Summarization for Literature Review (MSLR) Shared Task, in which we explore summarization models to create an automatic review of scientific results. Rather than maximizing the metrics using expensive computational models, we placed ourselves in a situation of scarce computational resources and investigate the limits of a base sequence to sequence models (thus with a limited input length) to the task. Although we explore methods to feed the abstractive model with salient sentences only (using a first extractive step), we find that the results still need some improvements.

Exploring the limits of a base BART for multi-document summarization in the medical domain

Text summarization has been a trending domain of research in NLP in the past few decades. The medical domain is no exception to the same. Medical documents often contain a lot of jargon pertaining to certain domains, and performing an abstractive summarization on the same remains a challenge. This paper presents a summary of the findings that we obtained based on the shared task of Multidocument Summarization for Literature Review (MSLR). We stood fourth in the leaderboards for evaluation on the MS^2 and Cochrane datasets. We finetuned pre-trained models such as BART-large, DistilBART and T5-base on both these datasets. These models’ accuracy was later tested with a part of the same dataset using ROUGE scores as the evaluation metrics.

Abstractive Approaches To Multidocument Summarization Of Medical Literature Reviews

The MuP-2022 shared task focuses on multi-perspective scientific document summarization. Given a scientific document, with multiple reference summaries, our goal was to develop a model that can produce a generic summary covering as many aspects of the document as covered by all of its reference summaries. This paper describes our best official model, a fine-tuned BART large, along with a discussion on
the challenges of this task and some of our unofficial models including SOTA generation models. Our submitted model out performed the given, MuP 2022 shared task baselines on ROUGE-2, ROUGE-L and average ROUGE F1-scores. Code of our submission can be accessed here.

Multi-Perspective Scientific Document Summarization Using Pre-trained Generation Models

Overview of the SV-Ident 2022 Shared Task on Survey Variable Identification in Social Science Publications

We are presenting an approach to the SV-Ident Shared Task which requires the detection and disambiguation of survey variables in sentences taken from social science publications. It deals with both subtasks as problems of semantic textual similarity (STS) and relies on the use of sentence transformers. Sentences and
variables are examined for semantic similarity for both detecting sentences containing variables and disambiguating the respective variables. The focus is placed on analyzing the effects of including different parts of the variables and observing the differences between English and German instances.

Variable Detection and Disambiguation Based on Semantic Similarity

Political competitions are complex settings where candidates use campaigns to promote their chances to be elected. One choice focuses on conducting a positive campaign that highlights the candidate's achievements, leadership skills, and future programs. The alternative is to focus on a negative campaign that emphasizes the \textit{negative aspects of the competing person} and is aimed at\textit{ offending opponents or the opponent’s supporters}. In this proposal, we concentrate on negative campaigns in Israeli elections. 
This work introduces an empirical case study on automatic detection of negative campaigns, using machine learning and natural language processing approaches, applied to the Hebrew-language data from Israeli municipal elections. 
Our contribution is multi-fold: (1) We provide TONIC---daTaset fOr Negative polItical Campaign in Hebrew---which consists of annotated posts from Facebook related to Israeli municipal elections; (2) We introduce results of a case study, that explored several research questions. RQ1: Which classifier and representation perform best for this task? We employed several traditional classifiers which are known for their excellent performance in IR tasks and two pre-trained models based on BERT architecture; several standard representations were employed with traditional ML models. RQ2: Does a negative campaign always contain offensive language? Can a model, trained to detect offensive language, also detect negative campaigns? We are trying to answer this question by reporting results for the transfer learning from a dataset annotated with offensive language to our dataset. 
RQ3: Does a negative campaign necessarily express negative sentiment? Can sentiment analysis help to detect negative campaigns? We experiment with sentiment labels to enrich data representation and report our findings. 

Our dataset and pre-trained models will be freely available for researchers.

Detection of Negative Campaign in Israeli Municipal Elections

Standard approaches to hate speech detection rely on sufficient available hate speech annotations. Extending previous work that repurposes natural language inference (NLI) models for zero-shot text classification, we propose a simple approach that combines multiple hypotheses to improve English NLI-based zero-shot hate speech detection. We first conduct an error analysis for vanilla NLI-based zero-shot hate speech detection and then develop four strategies based on this analysis. The strategies use multiple hypotheses to predict various aspects of an input text and combine these predictions into a final verdict. We find that the zero-shot baseline used for the initial error analysis already outperforms commercial systems and fine-tuned BERT-based hate speech detection models on HateCheck. The combination of the proposed strategies further increases the zero-shot accuracy of 79.4% on HateCheck by 7.9 percentage points (pp), and the accuracy of 69.6% on ETHOS by 10.0pp.

Hypothesis Engineering for Zero-Shot and Few-Shot Hate Speech Detection

In this presentation, we discuss an interpretable frame-
work to integrate toxic language annotations.
Most data sets address only one aspect of the
complex relationship in toxic communication
and are inconsistent with each other. Enrich-
ing annotations with more details and infor-
mation is, however, of great importance in or-
der to develop high-performing and compre-
hensive explainable language models. Such
systems should recognize and interpret both
expressions that are toxic as well as expres-
sions that make reference to specific targets to
combat toxic language. We, therefore, create
a crowd-annotation task to mark the spans of
words that refer to target communities as an ex-
tension of the HateXplain data set. We present
a quantitative and qualitative analysis of the
annotations. We also fine-tune RoBERTa-base
on our data and experiment with different USQ (Media Unit Quality Score)
thresholds to measure their effect on the clas-
sification. The F1-score of our best model on
the test set is 79%. The annotations are freely
available and can be combined with the exist-
ing HateXplain annotations to build richer and
more complete models.

Annotating targets of toxic language at the span level

Annotating abusive language is expensive, logistically complex and creates a risk of psychological harm. However, most machine learning research has prioritized maximizing effectiveness (i.e., F1 or accuracy score) rather than data efficiency (i.e., minimizing the amount of data that is annotated). In this paper, we use simulated experiments over two datasets at varying percentages of abuse to demonstrate that transformers-based active learning is a promising approach to substantially raise efficiency whilst still maintaining high effectiveness, especially when abusive content is a smaller percentage of the dataset. This approach requires a fraction of labeled data to reach performance equivalent to training over the full dataset.

Premium content

Detecting generated scientific papers using an ensemble of transformer models

Downloads

Next from COLING 2022

Benchmark for Research Theme Classification of Scholarly Documents

Similar lecture

PetroBERT: a domain adaptation language model for oil and gas applications in Portuguese

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES