Silvia Terragni


pdf bib
Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems
Ivan Sekulic | Silvia Terragni | Victor Guimarães | Nghia Khau | Bruna Guedes | Modestas Filipavicius | Andre Ferreira Manso | Roland Mathis
Proceedings of the 1st Workshop on Simulating Conversational Intelligence in Chat (SCI-CHAT 2024)

In the realm of dialogue systems, user simulation techniques have emerged as a game-changer, redefining the evaluation and enhancement of task-oriented dialogue (TOD) systems. These methods are crucial for replicating real user interactions, enabling applications like synthetic data augmentation, error detection, and robust evaluation. However, existing approaches often rely on rigid rule-based methods or on annotated data. This paper introduces DAUS, a Domain-Aware User Simulator. Leveraging large language models, we fine-tune DAUS on real examples of task-oriented dialogues. Results on two relevant benchmarks showcase significant improvements in terms of user goal fulfillment. Notably, we have observed that fine-tuning enhances the simulator’s coherence with user goals, effectively mitigating hallucinations—a major source of inconsistencies in simulator responses.


pdf bib
BETOLD: A Task-Oriented Dialog Dataset for Breakdown Detection
Silvia Terragni | Bruna Guedes | Andre Manso | Modestas Filipavicius | Nghia Khau | Roland Mathis
Proceedings of the Second Workshop on When Creative AI Meets Conversational AI

Task-Oriented Dialog (TOD) systems often suffer from dialog breakdowns - situations in which users cannot or do not want to proceed with the conversation. Ideally TOD systems should be able to detect dialog breakdowns to prevent users from quitting a conversation and to encourage them to interact with the system again. In this paper, we present BETOLD, a privacy-preserving dataset for breakdown detection. The dataset consists of user and system turns represented by intents and entity annotations, derived from NLU and NLG dialog manager components. We also propose an attention-based model that detects potential breakdowns using these annotations, instead of the utterances’ text. This approach achieves a comparable performance to the corresponding utterance-only model, while ensuring data privacy.


pdf bib
An Empirical Analysis of Topic Models: Uncovering the Relationships between Hyperparameters, Document Length and Performance Measures
Silvia Terragni | Elisabetta Fersini
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)

Neural Topic Models are recent neural models that aim at extracting the main themes from a collection of documents. The comparison of these models is usually limited because the hyperparameters are held fixed. In this paper, we present an empirical analysis and comparison of Neural Topic Models by finding the optimal hyperparameters of each model for four different performance measures adopting a single-objective Bayesian optimization. This allows us to determine the robustness of a topic model for several evaluation metrics. We also empirically show the effect of the length of the documents on different optimized metrics and discover which evaluation metrics are in conflict or agreement with each other.

pdf bib
Cross-lingual Contextualized Topic Models with Zero-shot Learning
Federico Bianchi | Silvia Terragni | Dirk Hovy | Debora Nozza | Elisabetta Fersini
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either single-language or suffer from a huge, but extremely sparse vocabulary. Both issues can be addressed by transfer learning. In this paper, we introduce a zero-shot cross-lingual topic model. Our model learns topics on one language (here, English), and predicts them for unseen documents in different languages (here, Italian, French, German, and Portuguese). We evaluate the quality of the topic predictions for the same document in different languages. Our results show that the transferred topics are coherent and stable across languages, which suggests exciting future research directions.

pdf bib
OCTIS: Comparing and Optimizing Topic models is Simple!
Silvia Terragni | Elisabetta Fersini | Bruno Giovanni Galuzzi | Pietro Tropeano | Antonio Candelieri
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

In this paper, we present OCTIS, a framework for training, analyzing, and comparing Topic Models, whose optimal hyper-parameters are estimated using a Bayesian Optimization approach. The proposed solution integrates several state-of-the-art topic models and evaluation metrics. These metrics can be targeted as objective by the underlying optimization procedure to determine the best hyper-parameter configuration. OCTIS allows researchers and practitioners to have a fair comparison between topic models of interest, using several benchmark datasets and well-known evaluation metrics, to integrate novel algorithms, and to have an interactive visualization of the results for understanding the behavior of each model. The code is available at the following link:

pdf bib
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence
Federico Bianchi | Silvia Terragni | Dirk Hovy
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret. Recently, neural topic models have shown improvements in overall coherence. Concurrently, contextual embeddings have advanced the state of the art of neural models in general. In this paper, we combine contextualized representations with neural topic models. We find that our approach produces more meaningful and coherent topics than traditional bag-of-words topic models and recent neural models. Our results indicate that future improvements in language models will translate into better topic models.


pdf bib
Which Matters Most? Comparing the Impact of Concept and Document Relationships in Topic Models
Silvia Terragni | Debora Nozza | Elisabetta Fersini | Messina Enza
Proceedings of the First Workshop on Insights from Negative Results in NLP

Topic models have been widely used to discover hidden topics in a collection of documents. In this paper, we propose to investigate the role of two different types of relational information, i.e. document relationships and concept relationships. While exploiting the document network significantly improves topic coherence, the introduction of concepts and their relationships does not influence the results both quantitatively and qualitatively.