no code implementations • Findings (ACL) 2022 • Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen
Scaling dialogue systems to a multitude of domains, tasks and languages relies on costly and time-consuming data annotation for different domain-task-language configurations.
no code implementations • ACL 2022 • Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo Ponti, Ivan Vulić
In this tutorial, we will thus discuss and demonstrate the importance of (building) multilingual ToD systems, and then provide a systematic overview of current research gaps, challenges and initiatives related to multilingual ToD systems, with a particular focus on their connections to current research and challenges in multilingual and low-resource NLP.
no code implementations • 4 Mar 2024 • Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen
Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning.
no code implementations • 16 Nov 2023 • Evgeniia Razumovskaia, Ivan Vulić, Pavle Marković, Tomasz Cichy, Qian Zheng, Tsung-Hsien Wen, Paweł Budzianowski
Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system.
1 code implementation • 16 Nov 2023 • Evgeniia Razumovskaia, Goran Glavaš, Anna Korhonen, Ivan Vulić
Task-oriented dialogue (ToD) systems help users execute well-defined tasks across a variety of domains (e. g., $\textit{flight booking}$ or $\textit{food ordering}$), with their Natural Language Understanding (NLU) components being dedicated to the analysis of user utterances, predicting users' intents ($\textit{Intent Detection}$, ID) and extracting values for informational slots ($\textit{Value Extraction}$, VE).
no code implementations • 22 May 2023 • Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen
It is especially effective for the most challenging transfer-free few-shot setups, paving the way for quick and data-efficient bootstrapping of multilingual slot labelers for ToD.
no code implementations • 20 Dec 2022 • Evgeniia Razumovskaia, Joshua Maynez, Annie Louis, Mirella Lapata, Shashi Narayan
Previous work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English.
no code implementations • 20 Dec 2022 • Nikita Moghe, Evgeniia Razumovskaia, Liane Guillou, Ivan Vulić, Anna Korhonen, Alexandra Birch
We use MULTI3NLU++ to benchmark state-of-the-art multilingual models for the NLU tasks of intent detection and slot labelling for TOD systems in the multilingual setting.
no code implementations • 31 Jan 2022 • Olga Majewska, Evgeniia Razumovskaia, Edoardo Maria Ponti, Ivan Vulić, Anna Korhonen
Through this process we annotate a new large-scale dataset for training and evaluation of multilingual and cross-lingual ToD systems.
no code implementations • 17 Apr 2021 • Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo M. Ponti, Anna Korhonen, Ivan Vulić
We find that the most critical factor preventing the creation of truly multilingual ToD systems is the lack of datasets in most languages for both training and evaluation.
no code implementations • ACL 2019 • Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao, Maxine Eskenazi
This paper examines various unsupervised pretraining objectives for learning dialog context representations.
no code implementations • 20 Jan 2019 • Maxine Eskenazi, Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao
Most research on intelligent agents centers on the agent and not on the user.