Case Report Forms (CRFs) are largely used in medical research as they ensure accuracy, reliability, and validity of results in clinical studies. However, publicly available, well-annotated CRF datasets are scarce, limiting the development of CRF slot filling systems able to fill in a CRF from clinical notes. To mitigate the scarcity of CRF datasets, we propose to take advantage of available datasets annotated for information extraction tasks and to convert them into structured CRFs. We present a semi-automatic conversion methodology, which has been applied to the E3C dataset in two languages (English and Italian), resulting in a new, high-quality dataset for CRF slot filling. Through several experiments on the created dataset, we report that slot filling achieves 59.7% for Italian and 67.3% for English on a closed Large Language Models (zero-shot) and worse performances on three families of open-source models, showing that filling CRFs is challenging even for recent state-of-the-art LLMs.

While the popularity of large, versatile language models like ChatGPT continues to rise, the landscape shifts when considering open-source models tailored to specific domains. Moreover, many areas, such as clinical documents, suffer from a scarcity of training data, often amounting to only a few hundred instances. Additionally, in certain settings, such as hospitals, cloud-based solutions pose privacy concerns, necessitating the deployment of language models on traditional hardware, such as single GPUs or powerful CPUs. To address these complexities, we conduct extensive experiments on both clinical entity detection and relation extraction in clinical documents using 1B parameter models. Our study delves into traditional fine-tuning, continuous pre-training in the medical domain, and instruction-tuning methods, providing valuable insights into their effectiveness in a multilingual setting. Our results underscore the importance of domain-specific models and pre-training for clinical natural language processing tasks. Furthermore, data augmentation using cross-lingual information improves performance in most cases, highlighting the potential for multilingual enhancements.

This paper introduces IDRE (Italian Dataset for Rephrasing with Empathy), a novel automatically generated Italian linguistic dataset. IDRE comprises typical chatbot user utterances in the healthcare domain, corresponding chatbot responses, and empathetically enhanced chatbot responses. The dataset was generated using the Llama2 language model and evaluated by human raters based on predefined metrics. The IDRE dataset offers a comprehensive and realistic collection of Italian chatbot-user interactions suitable for training and refining chatbot models in the healthcare domain. This facilitates the development of chatbots capable of natural and productive conversations with healthcare users. Notably, the dataset incorporates empathetically enhanced chatbot responses, enabling researchers to investigate the effects of empathetic language on fostering more positive and engaging human-machine interactions within healthcare settings. The methodology employed for the construction of the IDRE dataset can be extended to generate phrases in additional languages and domains, thereby expanding its applicability and utility. The IDRE dataset is publicly available for research purposes.

Research on language technology for the development of medical applications is currently a hot topic in Natural Language Understanding and Generation. Thus, a number of large language models (LLMs) have recently been adapted to the medical domain, so that they can be used as a tool for mediating in human-AI interaction. While these LLMs display competitive performance on automated medical texts benchmarks, they have been pre-trained and evaluated with a focus on a single language (English mostly). This is particularly true of text-to-text models, which typically require large amounts of domain-specific pre-training data, often not easily accessible for many languages. In this paper, we address these shortcomings by compiling, to the best of our knowledge, the largest multilingual corpus for the medical domain in four languages, namely English, French, Italian and Spanish. This new corpus has been used to train Medical mT5, the first open-source text-to-text multilingual model for the medical domain. Additionally, we present two new evaluation benchmarks for all four languages with the aim of facilitating multilingual research in this domain. A comprehensive evaluation shows that Medical mT5 outperforms both encoders and similarly sized text-to-text models for the Spanish, French, and Italian benchmarks, while being competitive with current state-of-the-art LLMs in English.

Sharing datasets and benchmarks has been crucial for rapidly improving Natural Language Processing models and systems. Documenting datasets’ characteristics (and any modification introduced over time) is equally important to avoid confusion and make comparisons reliable. Here, we describe the case of BigPatent, a dataset for patent summarization that exists in at least two rather different versions under the same name. While previous literature has not clearly distinguished among versions, their differences do not only lay on a surface level but also modify the dataset’s core nature and, thus, the complexity of the summarization task. While this paper describes a specific case, we aim to shed light on new challenges that might emerge in resource sharing and advocate for comprehensive documentation of datasets and models.

We present a comparison between deep learning and traditional machine learning methods for various NLP tasks in Italian. We carried on experiments using available datasets (e.g., from the Evalita shared tasks) on two sequence tagging tasks (i.e., named entities recognition and nominal entities recognition) and four classification tasks (i.e., lexical relations among words, semantic relations among sentences, sentiment analysis and text classification). We show that deep learning approaches outperform traditional machine learning algorithms in sequence tagging, while for classification tasks that heavily rely on semantics approaches based on feature engineering are still competitive. We think that a similar analysis could be carried out for other languages to provide an assessment of machine learning / deep learning models across different languages.

This paper describes a classifier for tweets that mention medications or supplements, based on a pretrained transformer. We developed such a system for our participation in Subtask 1 of the Social Media Mining for Health Application workshop, which featured an extremely unbalanced dataset. The model showed promising results, with an F1 of 0.8 (task mean: 0.66).

Relation extraction (RE) is an important text mining task which is the basis for further complex and advanced tasks. In state-of-the-art RE approaches, syntactic information obtained through parsing plays a crucial role. In the context of biomedical RE previous studies report usage of various automatic preprocessing techniques applied before parsing the input text. However, these studies do not specify to what extent such techniques improve RE results and to what extent they are corpus specific as well as parser specific. In this paper, we aim at addressing these issues by using various preprocessing techniques, two syntactic tree kernel based RE approaches and two different parsers on 5 widely used benchmark biomedical corpora of the protein-protein interaction (PPI) extraction task. We also provide analyses of various corpus characteristics to verify whether there are correlations between these characteristics and the RE results obtained. These analyses of corpus characteristics can be exploited to compare the 5 PPI corpora.

The aim of this paper is to contribute to the debate on the issues raised by Morphologically Rich Languages, and more precisely to investigate, in a cross-paradigm perspective, the influence of the constituent order on the data-driven parsing of one of such languages(i.e. Italian). It shows therefore new evidence from experiments on Italian, a language characterized by a rich verbal inflection, which leads to a widespread diffusion of the pro―drop phenomenon and to a relatively free word order. The experiments are performed by using state-of-the-art data-driven parsers (i.e. MaltParser and Berkeley parser) and are based on an Italian treebank available in formats that vary according to two dimensions, i.e. the paradigm of representation (dependency vs. constituency) and the level of detail of linguistic information.

Uncertainty language permeates biomedical research and is fundamental for the computer interpretation of unstructured text. And yet, a coherent, cognitive-based theory to interpret Uncertainty language and guide Natural Language Processing is, to our knowledge, non-existing. The aim of our project was therefore to detect and annotate Uncertainty markers ― which play a significant role in building knowledge or beliefs in readers' minds ― in a biomedical research corpus. Our corpus includes 80 manually annotated articles from the British Medical Journal randomly sampled from a 168-year period. Uncertainty markers have been classified according to a theoretical framework based on a combined linguistic and cognitive theory. The corpus was manually annotated according to such principles. We performed preliminary experiments to assess the manually annotated corpus and establish a baseline for the automatic detection of Uncertainty markers. The results of the experiments show that most of the Uncertainty markers can be recognized with good accuracy.

As the interest of the NLP community grows to develop several treebanks also for languages other than English, we observe efforts towards evaluating the impact of different annotation strategies used to represent particular languages or with reference to particular tasks. This paper contributes to the debate on the influence of resources used for the training and development on the performance of parsing systems. It presents a comparative analysis of the results achieved by three different dependency parsers developed and tested with respect to two treebanks for the Italian language, namely TUT and ISST--TANL, which differ significantly at the level of both corpus composition and adopted dependency representations.

The EVALITA 2007 Parsing Task has been the first contest among parsing systems for Italian. It is the first attempt to compare the approaches and the results of the existing parsing systems specific for this language using a common treebank annotated using both a dependency and a constituency-based format. The development data set for this parsing competition was taken from the Turin University Treebank, which is annotated both in dependency and constituency format. The evaluation metrics were those standardly applied in CoNLL and PARSEVAL. The results of the parsing results are very promising and higher than the state-of-the-art for dependency parsing of Italian. An analysis of such results is provided, which takes into account other experiences in treebank-driven parsing for Italian and for other Romance languages (in particular, the CoNLL X & 2007 shared tasks for dependency parsing). It focuses on the characteristics of data sets, i.e. type of annotation and size, parsing paradigms and approaches applied also to languages other than Italian.

We survey the evaluation methodology adopted in Information Extraction (IE), as defined in the MUC conferences and in later independent efforts applying machine learning to IE. We point out a number of problematic issues that may hamper the comparison between results obtained by different researchers. Some of them are common to other NLP tasks: e.g., the difficulty of exactly identifying the effects on performance of the data (sample selection and sample size), of the domain theory (features selected), and of algorithm parameter settings. Issues specific to IE evaluation include: how leniently to assess inexact identification of filler boundaries, the possibility of multiple fillers for a slot, and how the counting is performed. We argue that, when specifying an information extraction task, a number of characteristics should be clearly defined. However, in the papers only a few of them are usually explicitly specified. Our aim is to elaborate a clear and detailed experimental methodology and propose it to the IE community. The goal is to reach a widespread agreement on such proposal so that future IE evaluations will adopt the proposed methodology, making comparisons between algorithms fair and reliable. In order to achieve this goal, we will develop and make available to the community a set of tools and resources that incorporate a standardized IE methodology.

In this paper we propose to use text chunking for controlling a bottom-up parser. As it is well known, during analysis such parsers produce many constituents not contributing to the final solution(s). Most of these constituents are introduced due to t he parser inability of checking the input context around them. Preliminary text chunking allows to focus directly on the constituents that seem more likely and to prune the search space in the case some satisfactory solutions are found. Preliminary experiments show that a CYK-like parser controlled through chunking is definitely more efficient than a traditional parser without significantly losing in correctness. Moreover the quality of possible partial results produced by the controlled parser is high. The strategy is particularly suited for tasks like Information Extraction from text (IE) where sentences are often long and complex and it is very difficult to have a complete coverage. Hence, there is a strong necessity of focusing on the most likely solutions; furthermore, in IE the quality of partial results is important .