Diego Mollá

Diego Mollá

This paper presents Macquarie University's participation to the two most recent BioASQ Synergy Tasks (as per June 2022), and to the BioASQ10 Task~B (BioASQ10b), Phase~B. In these tasks, participating systems are expected to generate complex answers to biomedical questions, where the answers may contain more than one sentence. We apply query-focused extractive summarisation techniques. In particular, we follow a sentence classification-based approach that scores each candidate sentence associated to a question, and the $n$ highest-scoring sentences are returned as the answer. The Synergy Task corresponds to an end-to-end system that requires document selection, snippet selection, and finding the final answer, but it has very limited training data. For the Synergy task, we selected the candidate sentences following two phases: document retrieval and snippet retrieval, and the final answer was found by using a DistilBERT/ALBERT classifier that had been trained on the training data of BioASQ9b. Document retrieval was achieved as a standard search over the CORD-19 data using the search API provided by the BioASQ organisers, and snippet retrieval was achieved by re-ranking the sentences of the top retrieved documents, using the cosine similarity of the question and candidate sentence. We observed that vectors represented via sBERT have an edge over tf.idf. BioASQ10b Phase B focuses on finding the specific answers to biomedical questions. For this task, we followed a data-centric approach. We hypothesised that the training data of the first BioASQ years might be biased and we experimented with different subsets of the training data. We observed an improvement of results when the system was trained on the second half of the BioASQ10b training data.

Diego Mollá

This paper reports on the use of prompt engineering and GPT-3.5 for biomedical query-focused multi-document summarisation. Using GPT-3.5 and appropriate prompts, our system achieves top ROUGE-F1 results in the task of obtaining short-paragraph-sized answers to biomedical questions in the 2023 BioASQ Challenge (BioASQ 11b). This paper confirms what has been observed in other domains: 1) Prompts that incorporated few-shot samples generally improved on their counterpart zero-shot variants; 2) The largest improvement was achieved by retrieval augmented generation. The fact that these prompts allow our top runs to rank within the top two runs of BioASQ 11b demonstrate the power of using adequate prompts for Large Language Models in general, and GPT-3.5 in particular, for query-focused summarisation.

Gregory Baker, Diego Molla-Aliod

A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.

Greg Baker, Diego Molla-Aliod

The LEAFTOP (language extracted automatically from thousands of passages) dataset consists of nouns that appear in multiple places in the four gospels of the New Testament. We use a naive approach -- probabilistic inference -- to identify likely translations in 1480 other languages. We evaluate this process and find that it provides lexiconaries with accuracy from 42% (Korafe) to 99% (Runyankole), averaging 72% correct across evaluated languages. The process translates up to 161 distinct lemmas from Koine Greek (average 159). We identify nouns which appear to be easy and hard to translate, language families where this technique works, and future possible improvements and extensions. The claims to novelty are: the use of a Koine Greek New Testament as the source language; using a fully-annotated manually-created grammatically parse of the source text; a custom scraper for texts in the target languages; a new metric for language similarity; a novel strategy for evaluation on low-resource languages.

Yelaman Abdullin, Diego Molla-Aliod, Bahadorreza Ofoghi et al.

Linear programming (LP) problems are pervasive in real-life applications. However, despite their apparent simplicity, an untrained user may find it difficult to determine the linear model of their specific problem. We envisage the creation of a goal-oriented conversational agent that will engage in conversation with the user to elicit all information required so that a subsequent agent can generate the linear model. In this paper, we present an approach for the generation of sample dialogues that can be used to develop and train such a conversational agent. Using prompt engineering, we develop two agents that "talk" to each other, one acting as the conversational agent, and the other acting as the user. Using a set of text descriptions of linear problems from NL4Opt available to the user only, the agent and the user engage in conversation until the agent has retrieved all key information from the original problem description. We also propose an extrinsic evaluation of the dialogues by assessing how well the summaries generated by the dialogues match the original problem descriptions. We conduct human and automatic evaluations, including an evaluation approach that uses GPT-4 to mimic the human evaluation metrics. The evaluation results show an overall good quality of the dialogues, though research is still needed to improve the quality of the GPT-4 evaluation metrics. The resulting dialogues, including the human annotations of a subset, are available to the research community. The conversational agent used for the generation of the dialogues can be used as a baseline.

Diego Mollá, Qiongkai Xu, Zijie Zeng et al.

The ALTA shared tasks have been running annually since 2010. In 2024, the purpose of the task is to detect machine-generated text in a hybrid setting where the text may contain portions of human text and portions machine-generated. In this paper, we present the task, the evaluation criteria, and the results of the systems participating in the shared task.

Dima Galat, Diego Molla-Aliod

Biomedical question answering (QA) poses significant challenges due to the need for precise interpretation of specialized knowledge drawn from a vast, complex, and rapidly evolving corpus. In this work, we explore how large language models (LLMs) can be used for information retrieval (IR), and an ensemble of zero-shot models can accomplish state-of-the-art performance on a domain-specific Yes/No QA task. Evaluating our approach on the BioASQ challenge tasks, we show that ensembles can outperform individual LLMs and in some cases rival or surpass domain-tuned systems - all while preserving generalizability and avoiding the need for costly fine-tuning or labeled data. Our method aggregates outputs from multiple LLM variants, including models from Anthropic and Google, to synthesize more accurate and robust answers. Moreover, our investigation highlights a relationship between context length and performance: while expanded contexts are meant to provide valuable evidence, they simultaneously risk information dilution and model disorientation. These findings emphasize IR as a critical foundation in Retrieval-Augmented Generation (RAG) approaches for biomedical QA systems. Precise, focused retrieval remains essential for ensuring LLMs operate within relevant information boundaries when generating answers from retrieved documents. Our results establish that ensemble-based zero-shot approaches, when paired with effective RAG pipelines, constitute a practical and scalable alternative to domain-tuned systems for biomedical question answering.

Jiyu Chen, Necva Bölücü, Sarvnaz Karimi et al.

Detecting emotions across different languages is challenging due to the varied and culturally nuanced ways of emotional expressions. The \textit{Semeval 2025 Task 11: Bridging the Gap in Text-Based emotion} shared task was organised to investigate emotion recognition across different languages. The goal of the task is to implement an emotion recogniser that can identify the basic emotional states that general third-party observers would attribute to an author based on their written text snippet, along with the intensity of those emotions. We report our investigation of various task-adaptation strategies for LLMs in emotion recognition. We show that the most effective method for this task is to fine-tune a pre-trained multilingual LLM with LoRA setting separately for each language.

Urvashi Khanna, Diego Mollá

In this work, we describe our experiments and participating systems in the BioASQ Task 9b Phase B challenge of biomedical question answering. We have focused on finding the ideal answers and investigated multi-task fine-tuning and gradual unfreezing techniques on transformer-based language models. For factoid questions, our ALBERT-based systems ranked first in test batch 1 and fourth in test batch 2. Our DistilBERT systems outperformed the ALBERT variants in test batches 4 and 5 despite having 81% fewer parameters than ALBERT. However, we observed that gradual unfreezing had no significant impact on the model's accuracy compared to standard fine-tuning.

Diego Mollá, Urvashi Khanna, Dima Galat et al.

This paper presents Macquarie University's participation to the BioASQ Synergy Task, and BioASQ9b Phase B. In each of these tasks, our participation focused on the use of query-focused extractive summarisation to obtain the ideal answers to medical questions. The Synergy Task is an end-to-end question answering task on COVID-19 where systems are required to return relevant documents, snippets, and answers to a given question. Given the absence of training data, we used a query-focused summarisation system that was trained with the BioASQ8b training data set and we experimented with methods to retrieve the documents and snippets. Considering the poor quality of the documents and snippets retrieved by our system, we observed reasonably good quality in the answers returned. For phase B of the BioASQ9b task, the relevant documents and snippets were already included in the test data. Our system split the snippets into candidate sentences and used BERT variants under a sentence classification setup. The system used the question and candidate sentence as input and was trained to predict the likelihood of the candidate sentence being part of the ideal answer. The runs obtained either the best or second best ROUGE-F1 results of all participants to all batches of BioASQ9b. This shows that using BERT in a classification setup is a very strong baseline for the identification of ideal answers.

Diego Molla, Christopher Jones, Vincent Nguyen

This paper presents the participation of Macquarie University and the Australian National University for Task B Phase B of the 2020 BioASQ Challenge (BioASQ8b). Our overall framework implements Query focused multi-document extractive summarisation by applying either a classification or a regression layer to the candidate sentence embeddings and to the comparison between the question and sentence embeddings. We experiment with variants using BERT and BioBERT, Siamese architectures, and reinforcement learning. We observe the best results when BERT is used to obtain the word embeddings, followed by an LSTM layer to obtain sentence embeddings. Variants using Siamese architectures or BioBERT did not improve the results.

Diego Molla, Christopher Jones

Task B Phase B of the 2019 BioASQ challenge focuses on biomedical question answering. Macquarie University's participation applies query-based multi-document extractive summarisation techniques to generate a multi-sentence answer given the question and the set of relevant snippets. In past participation we explored the use of regression approaches using deep learning architectures and a simple policy gradient architecture. For the 2019 challenge we experiment with the use of classification approaches with and without reinforcement learning. In addition, we conduct a correlation analysis between various ROUGE metrics and the BioASQ human evaluation scores.

Diego Mollá

This paper describes Macquarie University's contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used $tf.idf$ features encoding the candidate sentence, question, and context.

Mandeep Kaur, Diego Mollá

The automation of text summarisation of biomedical publications is a pressing need due to the plethora of information available on-line. This paper explores the impact of several supervised machine learning approaches for extracting multi-document summaries for given queries. In particular, we compare classification and regression approaches for query-based extractive summarisation using data provided by the BioASQ Challenge. We tackled the problem of annotating sentences for training classification systems and show that a simple annotation approach outperforms regression-based summarisation.

Hamideh Hajiabadi, Diego Molla-Aliod, Reza Monsefi

Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one. As a meta learning framework, ensemble techniques can easily be applied to many machine learning techniques. In this paper we propose a neural network extended with an ensemble loss function for text classification. The weight of each weak loss function is tuned within the training phase through the gradient propagation optimization method of the neural network. The approach is evaluated on several text classification datasets. We also evaluate its performance in various environments with several degrees of label noise. Experimental results indicate an improvement of the results and strong resilience against label noise in comparison with other methods.

Diego Molla

Supervised approaches for text summarisation suffer from the problem of mismatch between the target labels/scores of individual sentences and the evaluation score of the final summary. Reinforcement learning can solve this problem by providing a learning mechanism that uses the score of the final summary as a guide to determine the decisions made at the time of selection of each sentence. In this paper we present a proof-of-concept approach that applies a policy-gradient algorithm to learn a stochastic policy using an undiscounted reward. The method has been applied to a policy consisting of a simple neural network and simple features. The resulting deep reinforcement learning system is able to learn a global policy and obtain encouraging results.

Abeed Sarker, Diego Molla, Cecile Paris

The practice of evidence-based medicine (EBM) urges medical practitioners to utilise the latest research evidence when making clinical decisions. Because of the massive and growing volume of published research on various medical topics, practitioners often find themselves overloaded with information. As such, natural language processing research has recently commenced exploring techniques for performing medical domain-specific automated text summarisation (ATS) techniques-- targeted towards the task of condensing large medical texts. However, the development of effective summarisation techniques for this task requires cross-domain knowledge. We present a survey of EBM, the domain-specific needs for EBM, automated summarisation techniques, and how they have been applied hitherto. We envision that this survey will serve as a first resource for the development of future operational text summarisation techniques for EBM.

Diego Molla-Aliod

Macquarie University's contribution to the BioASQ challenge (Task 5b Phase B) focused on the use of query-based extractive summarisation techniques for the generation of the ideal answers. Four runs were submitted, with approaches ranging from a trivial system that selected the first $n$ snippets, to the use of deep learning approaches under a regression framework. Our experiments and the ROUGE results of the five test batches of BioASQ indicate surprisingly good results for the trivial approach. Overall, most of our runs on the first three test batches achieved the best ROUGE-SU4 results in the challenge.

Diego Mollá, Iman Amini, David Martinez

This paper reports the use of a document distance-based approach to automatically expand the number of available relevance judgements when these are limited and reduced to only positive judgements. This may happen, for example, when the only available judgements are extracted from a list of references in a published review paper. We compare the results on two document sets: OHSUMED, based on medical research publications, and TREC-8, based on news feeds. We show that evaluations based on these expanded relevance judgements are more reliable than those using only the initially available judgements, especially when the number of available judgements is very limited.