18 citations · 62 across the 14 of their papers we have counts for
16 papers
Improving the Evaluation of Biomedical Question Answering with Few Human Preference Signals
Shakila Mahjabin Tonni, Xiang Dai, Sarvnaz Karimi +3
Retrieval-Augmented Generation (RAG) systems are increasingly used for biomedical Question Answering (QA). However, evaluating their effectiveness remains challenging due to the la…
Can AI Extract Antecedent Factors of Human Trust in AI? An Application of Information Extraction for Scientific Literature in Behavioural and Computer Sciences
Melanie McGrath, Harrison Bailey, Necva Bölücü +3
Information extraction from the scientific literature is one of the main techniques to transform unstructured knowledge hidden in the text into structured data which can then be us…
A Critical Look at Meta-evaluating Summarisation Evaluation Metrics
Xiang Dai, Sarvnaz Karimi, Biaoyan Fang
Effective summarisation evaluation metrics enable researchers and practitioners to compare different summarisation systems efficiently. Estimating the effectiveness of an automatic…
MultiADE: A Multi-domain Benchmark for Adverse Drug Event Extraction
Xiang Dai, Sarvnaz Karimi, Abeed Sarker +2
Active adverse event surveillance monitors Adverse Drug Events (ADE) from different data sources, such as electronic health records, medical literature, social media and search eng…
Identifying Health Risks from Family History: A Survey of Natural Language Processing Techniques
Xiang Dai, Sarvnaz Karimi, Nathan O'Callaghan
Electronic health records include information on patients' status and medical history, which could cover the history of diseases and disorders that could be hereditary. One importa…
Detecting Entities in the Astrophysics Literature: A Comparison of Word-based and Span-based Entity Recognition Methods
Xiang Dai, Sarvnaz Karimi
Information Extraction from scientific literature can be challenging due to the highly specialised nature of such text. We describe our entity recognition methods developed as part…
An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification
Ilias Chalkidis, Xiang Dai, Manos Fergadiotis +2
Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to thes…
Revisiting Transformer-based Models for Long Document Classification
Xiang Dai, Ilias Chalkidis, Sune Darkner +1
The recent literature in text classification is biased towards short text sequences (e.g., sentences or paragraphs). In real-world applications, multi-page multi-paragraph document…
MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model
Rasmus Kær Jørgensen, Mareike Hartmann, Xiang Dai +1
Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the…
Recognising Biomedical Names: Challenges and Solutions
Xiang Dai
The growth rate in the amount of biomedical documents is staggering. Unlocking information trapped in these documents can enable researchers and practitioners to operate confidentl…
NLNDE at CANTEMIST: Neural Sequence Labeling and Parsing Approaches for Clinical Concept Extraction
Lukas Lange, Xiang Dai, Heike Adel +1
The recognition and normalization of clinical information, such as tumor morphology mentions, is an important, but complex process consisting of multiple subtasks. In this paper, w…
An Analysis of Simple Data Augmentation for Named Entity Recognition
Xiang Dai, Heike Adel
Simple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks. Inspired by these efforts, we design an…
Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media
Xiang Dai, Sarvnaz Karimi, Ben Hachey +1
Recent studies on domain-specific BERT models show that effectiveness on downstream tasks can be improved when models are pretrained on in-domain data. Often, the pretraining data…
An Effective Transition-based Model for Discontinuous NER
Xiang Dai, Sarvnaz Karimi, Ben Hachey +1
Unlike widely used Named Entity Recognition (NER) data sets in generic domains, biomedical NER data sets often contain mentions consisting of discontinuous spans. Conventional sequ…
NNE: A Dataset for Nested Named Entity Recognition in English Newswire
Nicky Ringland, Xiang Dai, Ben Hachey +3
Named entity recognition (NER) is widely used in natural language processing applications and downstream tasks. However, most NER tools target flat annotation from popular datasets…
Using Similarity Measures to Select Pretraining Data for NER
Xiang Dai, Sarvnaz Karimi, Ben Hachey +1
Word vectors and Language Models (LMs) pretrained on a large amount of unlabelled data can dramatically improve various Natural Language Processing (NLP) tasks. However, the measur…