Papers by Evgeniia Razumovskaia
Transfer-Free Data-Efficient Multilingual Slot Labeling (2023.emnlp-main)
Copied to clipboard
| Challenge: | Slot labeling (SL) is a key component of task-oriented dialogue systems . extending the system to any new language-domain-task configuration requires expensive data annotation . |
| Approach: | They propose a two-stage slot labeling approach which transforms sentence encoders into effective slot labels. |
| Outcome: | The proposed approach is especially effective for the most challenging transfer-free few-shot setups. |
Multi3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue (2023.findings-acl)
Copied to clipboard
| Challenge: | Task-oriented dialogue systems are typically constructed for a single domain or language and do not generalise well beyond this. |
| Approach: | They constructed a multilingual, multi-intent, multi domain dataset to support work on Natural Language Understanding (NLU) in ToD across multiple languages and domains simultaneously. |
| Outcome: | The proposed dataset extends the English-only dataset to include manual translations into a range of high, medium, and low resource languages in two domains (banking and hotels). |
Pretraining Methods for Dialog Context Representation Learning (P19-1)
Copied to clipboard
| Challenge: | Existing methods for pretraining dialog context encoders are still in their infancy. |
| Approach: | They propose to use unsupervised pretraining objectives for dialog context representations to fine-tune and evaluate them on a set of downstream dialog tasks. |
| Outcome: | The proposed methods improve performance on a set of dialog tasks and are less data hungry. |
Little Red Riding Hood Goes around the Globe: Crosslingual Story Planning and Generation with Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English. |
| Approach: | They propose a task of crosslingual story generation with planning to leverage the creative and reasoning capabilities of large pretrained language models to generate stories in multiple languages. |
| Outcome: | The proposed task combines planning and planning in a monolingual setting and demonstrates that plans which structure stories into three acts lead to more coherent and interesting narratives while allowing to explicitly control their content and structure. |
Dial BeInfo for Faithfulness: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning (2024.findings-emnlp)
Copied to clipboard
Evgeniia Razumovskaia, Ivan Vulić, Pavle Marković, Tomasz Cichy, Qian Zheng, Tsung-Hsien Wen, Paweł Budzianowski
| Challenge: | Pretrained large language models (LLMs) are prone to hallucinations, that is, they generate incoherent or generic responses to queries. |
| Approach: | They propose a method that applies 'behavioural tuning' on the LLMs to aid information-seeking dialogue by comparing three standard datasets. |
| Outcome: | The proposed method improves accuracy on real-life conversations with real users by allowing the models to perform better on the data. |
Data Augmentation and Learned Layer Aggregation for Improved Multilingual Language Understanding in Dialogue (2022.findings-acl)
Copied to clipboard
| Challenge: | Multi-SentAugment and LayerAgg are self-training methods that augment available training data with similar (automatically labelled) in-domain sentences from large monolingual Web-scale corpora. |
| Approach: | They propose to use multi-sentaugment and layeragg to improve dialogue natural language understanding across multiple languages. |
| Outcome: | The proposed methods generalise well in zero- and few-shot scenarios and leverage external unannotated data sources. |
SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU (2024.naacl-long)
Copied to clipboard
| Challenge: | Task-oriented dialogue (TOD) systems support users in execution of specific, well-defined tasks through natural language interaction. |
| Approach: | They propose a framework for dialog NLU based on instruction tuning and question-answering-based formulation of ID and VE tasks. |
| Outcome: | The proposed framework surpasses existing models in training and cross-domain transfer and significantly outperforms existing large language models in performance and inference efficiency. |
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation (2023.tacl-1)
Copied to clipboard
| Challenge: | Multilingual task-oriented dialogue (ToD) datasets suffer from severe limitations, such as being small in scale and lacking naturalness and cultural specificity in the target language. |
| Approach: | They propose a novel outline-based annotation process where domain-specific abstract schemata of dialogue are mapped into natural language outlines. |
| Outcome: | The proposed approach improves understanding, dialogue state tracking, and end-to-end dialogue evaluation in Arabic, Indonesian, Russian, and Kiswahili. |
Natural Language Processing for Multilingual Task-Oriented Dialogue (2022.acl-tutorials)
Copied to clipboard
| Challenge: | a tutorial will examine the challenges and gaps in multilingual ToD research . multilingual systems are difficult to build, and are limited to English and other languages . |
| Approach: | This tutorial will discuss the importance of multilingual task-oriented dialogue systems . it will provide an 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. |
| Outcome: | This tutorial will provide an overview of current research gaps, challenges and initiatives related to multilingual ToD systems. |
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking (2026.findings-acl)
Copied to clipboard
Songbo Hu, Yinhong Liu, Ej Zhou, Evgeniia Razumovskaia, Xiaobin Wang, Alexander Fraser, Ivan Vulić, Anna Korhonen
| Challenge: | Creating spoken dialogue datasets is methodologically challenging due to the personally identifiable nature of speech signals. |
| Approach: | They propose a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation-based spoken dialogue systems. |
| Outcome: | The proposed dataset includes 6,000 information-seeking dialogues and 163 hours of user speech recorded from native speakers of four official WHO languages. |