Korea, Republic of

In this presentation, we introduce the pipeline of creating a personalized dialogue dataset using GPT-3. Our pipeline consists of three main parts: (1) ProfileGen creation, (2) Persona Set creation using CoNL, and (3) PersonaChatGen creation. Through experiments, we found that GPT-3 can generate meaningful results which leads to improving the performance compared to the baseline.

COLING 2022

PersonaChatGen: Generating Personalized Dialogues using GPT-3

persona-based dialogue generation

persona-chat

gpt-3

# 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). 

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!

To gain access to this event page you are required to register. 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.

Despite achieving state-of-the-art zero-shot performance, existing vision-language models still fall short of few-shot transfer ability on domain-specific problems. Classical fine-tuning often fails to prevent highly expressive models from exploiting spurious correlations. Although model-agnostic meta-learning (MAML) presents as a natural alternative for few-shot transfer learning, the expensive computation due to implicit second-order optimization limits its use on large-scale vision-language models such as CLIP. While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML. To show the impact of task sampling, we propose a simple algorithm, Model-Agnostic Multitask Fine-tuning (MAMF), which differentiates classical fine-tuning only on uniformly sampling multiple tasks. Despite its simplicity, we show that MAMF consistently outperforms classical fine-tuning on five few-shot image classification tasks. We further show that the effectiveness of the bi-level optimization in MAML is highly sensitive to the zero-shot performance of a task in the context of few-shot vision-language classification. The goal of this paper is to provide new insights on what makes few-shot learning work, and encourage more research into investigating better task sampling strategies.

Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning

Language education has been shown to benefit from computational argumentation, for example, from methods that assess quality dimensions of language learners' argumentative essays, such as their organization and argument strength. So far, however, little attention has been paid to cultural differences in learners' argument structures originating from different origins and language capabilities. This paper extends prior studies of learner argumentation by analyzing differences in the argument structure of essays from culturally diverse learners. Based on the ICLE corpus containing essays written by English learners of 16 different mother tongues, we train natural language processing models to mine argumentative discourse units (ADUs) as well as to assess the essays' quality in terms of organization and argument strength. The extracted ADUs and the predicted quality scores enable us to look into the similarities and differences of essay argumentation across different English learners. In particular, we analyze the ADUs from learners with different mother tongues, different levels of arguing proficiency, and different context cultures.

Analyzing Culture-Specific Argument Structures in Learner Essays

Identifying claims in text is a crucial first step in argument mining. In this paper, we investigate factors for the composition of training corpora to improve cross-domain claim detection. To this end, we use four recent argumentation corpora annotated with claims and submit them to several experimental scenarios. Our results
indicate that the "ideal" composition of training corpora is characterized by a large corpus size, homogeneous claim proportions, and less formal text domains.

On Selecting Training Corpora for Cross-Domain Claim Detection

We develop a novel unified representation for the argumentation mining task facilitating the extracting from text and the labelling of the non-argumentative units and argumentation components---premises, claims, and major claims---and the argumentative relations---premise to claim or premise in a support or attack relation, and claim to major-claim in a for or against relation---in an end-to-end machine learning pipeline. This tightly integrated representation combines the component and relation identification sub-problems and enables a unitary solution for detecting argumentation structures. This new representation together with a new deep learning architecture composed of a mixed embedding method, a multi-head attention layer, two biLSTM layers, and a final linear layer obtain state-of-the-art accuracy on the Persuasive Essays dataset. Also, we have introduced a decoupled solution to identify the entities and relations first, and on top of that a second model is used to detect distance between the detected related components. An augmentation of the corpus (paragraph version) by including copies of major claims has further increased the performance.

A Unified Representation and a Decoupled Deep Learning Architecture for Argumentation Mining of Students' Persuasive Essays

The successful application of argument mining in the legal domain can dramatically impact many disciplines related to law. For this purpose, we present Demosthenes, a novel corpus for argument mining in legal documents, composed of 40 decisions of the Court of Justice of the European Union on matters of fiscal state aid. The annotation specifies three hierarchical levels of information: the argumentative elements, their types, and their argument schemes. In our experimental evaluation, we address 4 different classification tasks, combining advanced language models and traditional classifiers.

Detecting Arguments in CJEU Decisions on Fiscal State Aid

Argument Unit Recognition and Classification aims at identifying argument units from text and classifying them as pro or against. One of the design choices that need to be made when developing systems for this task is what the unit of classification should be: segments of tokens or full sentences. Previous research suggests that fine-tuning language models on the token-level yields more robust results for clas- sifying sentences compared to training on sentences directly. We reproduce the study that originally made this claim and further investigate what exactly token-based systems learned better compared to sentence-based ones. We develop systematic tests for analysing the behavioural differences between the token-based and the sentence-based system. Our results show that token-based models are generally more robust than sentence-based models both on manually perturbed examples and on specific subpopulations of the data.

Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition

The growing interest in developing corpora of persuasive texts has promoted applications in automated systems, e.g., debating and essay scoring systems; however, there is little prior work mining image persuasiveness from an argumentative perspective. To expand persuasiveness mining into a multi-modal realm, we present a multi-modal dataset, ImageArg, consisting of annotations of image persuasiveness in tweets. The annotations are based on a persuasion taxonomy we developed to explore image functionalities and the means of persuasion. We benchmark image persuasiveness tasks on ImageArg using widely used multimodal learning methods. The experimental results show that our dataset offers a useful resource for this rich and challenging topic, and there is ample room for modeling improvement.

ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining

False medical information on social media poses harm to people's health.
While the need for biomedical fact-checking has been recognized in recent
years, user-generated medical content has received comparably little attention.
At the same time, models for other text genres might not be reusable, because
the claims they have been trained with are substantially different. For
instance, claims in the SciFact dataset are short and focused: "Side effects
associated with antidepressants increases risk of stroke". In contrast, social
media holds naturally-occurring claims, often embedded in additional context:
"`If you take antidepressants like SSRIs, you could be at risk of a condition
called serotonin syndrome' Serotonin syndrome nearly killed me in 2010. Had
symptoms of stroke and seizure." This showcases the mismatch between real-world
medical claims and the input that existing fact-checking systems expect. To
make user-generated content checkable by existing models, we propose to
reformulate the social-media input in such a way that the resulting claim
mimics the claim characteristics in established datasets. To accomplish this,
our method condenses the claim with the help of relational entity information
and either compiles the claim out of an entity-relation-entity triple or
extracts the shortest phrase that contains these elements. We show that the
reformulated input improves the performance of various fact-checking models as
opposed to checking the tweet text in its entirety.

Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweets

We propose a study on multimodal argument mining in the domain of political debates. We collate and extend existing corpora and provide an initial empirical study on multimodal architectures, with a special emphasis on input encoding methods. Our results provide interesting indications about future directions in this important domain.

Multimodal Argument Mining: A Case Study in Political Debates

We address the problem of automatically predicting the quality of a conclusion given a set of (textual) premises of an argument, focusing in particular on the task of predicting the validity and novelty of the argumentative conclusion. We propose a multi-task approach that jointly predicts the validity and novelty of the textual conclusion, relying on pre-trained language models fine-tuned on the task. As training data for this task is scarce and costly to obtain, we experimentally investigate the impact of data augmentation approaches for improving the accuracy of prediction compared to a baseline that relies on task-specific data only. We consider the generation of synthetic data as well as the integration of datasets from related argument tasks. We show that especially our synthetic data, combined with class-balancing and instance-specific learning rates, substantially improves classification results (+15.1 points in F1-score). Using only training data retrieved from related datasets by automatically labeling them for validity and novelty, combined with synthetic data, outperforms the baseline by 11.5 points in F1-score.
Demo at: https://huggingface.co/spaces/pheinisch/ConclusionValidityNoveltyClassifier-Augmentation

Premium content

PersonaChatGen: Generating Personalized Dialogues using GPT-3

Downloads

Next from COLING 2022

Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning

Similar lecture

Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text