" Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking

L Jacqmin, LM Rojas-Barahona, B Favre - arxiv preprint arxiv:2207.14627, 2022‏ - arxiv.org
While communicating with a user, a task-oriented dialogue system has to track the user's
needs at each turn according to the conversation history. This process called dialogue state …

Evaluating token-level and passage-level dense retrieval models for math information retrieval

W Zhong, JH Yang, Y **e, J Lin - arxiv preprint arxiv:2203.11163, 2022‏ - arxiv.org
With the recent success of dense retrieval methods based on bi-encoders, studies have
applied this approach to various interesting downstream retrieval tasks with good efficiency …

One blade for one purpose: advancing math information retrieval using hybrid search

W Zhong, SC Lin, JH Yang, J Lin - … of the 46th International ACM SIGIR …, 2023‏ - dl.acm.org
Neural retrievers have been shown to be effective for math-aware search. Their ability to
cope with math symbol mismatches, to represent highly contextualized semantics, and to …

[HTML][HTML] On the instability of further pre-training: Does a single sentence matter to BERT?

L Bacco, G Minnema, T Caselli, F Dell'Orletta… - Natural Language …, 2023‏ - Elsevier
We observe a remarkable instability in BERT-like models: minimal changes in the internal
representations of BERT, as induced by one-step further pre-training with even a single …

Cross-lingual distillation for domain knowledge transfer with sentence transformers

R Piperno, L Bacco, F Dell'Orletta, M Merone… - Knowledge-Based …, 2025‏ - Elsevier
Abstract Recent advancements in Natural Language Processing (NLP) have substantially
enhanced language understanding. However, non-English languages, especially in …

Data augmentation based on large language models for radiological report classification

J Collado-Montañez, MT Martín-Valdivia… - Knowledge-Based …, 2025‏ - Elsevier
Abstract The International Classification of Diseases (ICD) is fundamental in the field of
healthcare as it provides a standardized framework for the classification and coding of …

Masked Modeling Duo: Towards a Universal Audio Pre-Training Framework

D Niizumi, D Takeuchi, Y Ohishi… - … on Audio, Speech …, 2024‏ - ieeexplore.ieee.org
Self-supervised learning (SSL) using masked prediction has made great strides in general-
purpose audio representation. This study proposes Masked Modeling Duo (M2D), an …

[HTML][HTML] From pre-training to fine-tuning: An in-depth analysis of Large Language Models in the biomedical domain

A Bonfigli, L Bacco, M Merone, F Dell'Orletta - Artificial Intelligence in …, 2024‏ - Elsevier
In this study, we delve into the adaptation and effectiveness of Transformer-based, pre-
trained Large Language Models (LLMs) within the biomedical domain, a field that poses …

IndoGovBERT: A Domain-Specific Language Model for Processing Indonesian Government SDG Documents

A Riyadi, M Kovacs, U Serdült, V Kryssanov - Big Data and Cognitive …, 2024‏ - mdpi.com
Achieving the Sustainable Development Goals (SDGs) requires collaboration among
various stakeholders, particularly governments and non-state actors (NSAs). This …

Bag of Lies: Robustness in Continuous Pre-training BERT

I Gevers, W Daelemans - arxiv preprint arxiv:2406.09967, 2024‏ - arxiv.org
This study aims to acquire more insights into the continuous pre-training phase of BERT
regarding entity knowledge, using the COVID-19 pandemic as a case study. Since the …