Search Results for author: Serra Sinem Tekiroglu

Found 11 papers, 6 papers with code

Benchmarking the Generation of Fact Checking Explanations

1 code implementation29 Aug 2023 Daniel Russo, Serra Sinem Tekiroglu, Marco Guerini

Results show that in justification production summarization benefits from the claim information, and, in particular, that a claim-driven extractive step improves abstractive summarization performances.

Abstractive Text Summarization Benchmarking +3

Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering

1 code implementation7 Nov 2022 Helena Bonaldi, Sara Dellantonio, Serra Sinem Tekiroglu, Marco Guerini

Fighting online hate speech is a challenge that is usually addressed using Natural Language Processing via automatic detection and removal of hate content.

Text Generation

Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study

no code implementations Findings (ACL) 2022 Serra Sinem Tekiroglu, Helena Bonaldi, Margherita Fanton, Marco Guerini

In this work, we present an extensive study on the use of pre-trained language models for the task of automatic Counter Narrative (CN) generation to fight online hate speech in English.

Automatic Post-Editing Language Modelling

Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech

1 code implementation ACL 2021 Margherita Fanton, Helena Bonaldi, Serra Sinem Tekiroglu, Marco Guerini

Undermining the impact of hateful content with informed and non-aggressive responses, called counter narratives, has emerged as a possible solution for having healthier online communities.

Language Modelling

Empowering NGOs in Countering Online Hate Messages

no code implementations6 Jul 2021 Yi-Ling Chung, Serra Sinem Tekiroglu, Sara Tonelli, Marco Guerini

In this paper, we introduce a novel ICT platform that NGO operators can use to monitor and analyze social media data, along with a counter-narrative suggestion tool.


Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

1 code implementation Findings (ACL) 2021 Yi-Ling Chung, Serra Sinem Tekiroglu, Marco Guerini

Tackling online hatred using informed textual responses - called counter narratives - has been brought under the spotlight recently.

Toward Stance-based Personas for Opinionated Dialogues

no code implementations Findings of the Association for Computational Linguistics 2020 Thomas Scialom, Serra Sinem Tekiroglu, Jacopo Staiano, Marco Guerini

In the context of chit-chat dialogues it has been shown that endowing systems with a persona profile is important to produce more coherent and meaningful conversations.

Text Generation

Generating Counter Narratives against Online Hate Speech: Data and Strategies

no code implementations ACL 2020 Serra Sinem Tekiroglu, Yi-Ling Chung, Marco Guerini

Recently research has started focusing on avoiding undesired effects that come with content moderation, such as censorship and overblocking, when dealing with hatred online.

Text Generation

Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play

no code implementations RANLP 2019 Sourabh Majumdar, Serra Sinem Tekiroglu, Marco Guerini

End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data.

CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech

1 code implementation ACL 2019 Yi-Ling Chung, Elizaveta Kuzmenko, Serra Sinem Tekiroglu, Marco Guerini

Although there is an unprecedented effort to provide adequate responses in terms of laws and policies to hate content on social media platforms, dealing with hatred online is still a tough problem.

Data Augmentation Translation

FASTDial: Abstracting Dialogue Policies for Fast Development of Task Oriented Agents

1 code implementation ACL 2019 Serra Sinem Tekiroglu, Bernardo Magnini, Marco Guerini

We present a novel abstraction framework called FASTDial for designing task oriented dialogue agents, built on top of the OpenDial toolkit.

Cannot find the paper you are looking for? You can Submit a new open access paper.