The BERT family of neural language models have become highly popular due to their ability to provide sequences of text with rich context-sensitive token encodings which are able to generalise well to many NLP tasks. We introduce gaBERT, a monolingual BERT model for the Irish language. We compare our gaBERT model to multilingual BERT and the monolingual Irish WikiBERT, and we show that gaBERT provides better representations for a downstream parsing task. We also show how different filtering criteria, vocabulary size and the choice of subword tokenisation model affect downstream performance. We compare the results of fine-tuning a gaBERT model with an mBERT model for the task of identifying verbal multiword expressions, and show that the fine-tuned gaBERT model also performs better at this task. We release gaBERT and related code to the community.

An increasing number of public datasets have shown a marked clinical impact on assessing anatomical structures. However, each of the datasets is small, partially labeled, and rarely investigates severe tumor subjects. Moreover, current models are limited to segmenting specific organs/tumors, which can not be extended to novel domains and classes. To tackle these limitations, we introduce embedding learned from Contrastive Language-Image Pre-training (CLIP) to segmentation models, dubbed the CLIP-Driven Universal Model. The Universal Model can better segment 25 organs and 6 types of tumors by exploiting the semantic relationship between abdominal structures. The model is developed from an assembly of 14 datasets with 3,410 CT scans and evaluated on 6,162 external CT scans from 3 datasets. We rank first on the public leaderboard of the Medical Segmentation Decathlon (MSD) and achieve the state-of-the-art results on Beyond The Cranial Vault (BTCV). Compared with dataset-specific models, the Universal Model is computationally more efficient (6x faster), generalizes better to CT scans from varying sites, and shows stronger transfer learning performance on novel tasks. The design of CLIP embedding enables the Universal Model to be easily extended to new classes without catastrophically forgetting the previously learned classes.

In this work, we tackle two vital tasks in automated driving systems, i.e., driver intent prediction and risk object identification from egocentric images. Mainly, we investigate the question: what would be good road scene-level representations for these two tasks? We contend that a scene-level representation must capture higher-level semantic and geometric representations of traffic scenes around ego-vehicle while performing actions to their destinations. To this end, we introduce the representation of semantic regions, which are areas where ego-vehicles visit while taking an afforded action (e.g., left-turn at 4-way intersections). We propose to learn scene-level representations via a novel semantic region prediction task and an automatic semantic region labeling algorithm. Extensive evaluations are conducted on the HDD and nuScenes datasets, and the learned representations lead to state-of-the-art performance for driver intention prediction and risk object identification.

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.

This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image, we treat the prompt as an extra and independent learnable component. We show that the strategy of reconciling the prompt and the image matters, and find that warping the prompt around a properly shrinked image empirically works the best. Second, we re-introduce two "old tricks" commonly used in building transferable adversarial examples, i.e., input diversity and gradient normalization, into visual prompting. These techniques improve optimization and enable the prompt to generalize better. We provide extensive experimental results to demonstrate the effectiveness of our method. Using a CLIP model, our prompting method sets a new record of 82.8% average accuracy across 12 popular classification datasets, substantially surpassing the prior art by +5.6%. It is worth noting that this prompting performance already outperforms linear probing by +2.1% and can even match fully fine-tuning in certain datasets. In addition, our prompting method shows competitive performance across different data scales and against distribution shifts. The code is publicly available at https://github.com/UCSC-VLAA/EVP.

Named Entity Recognition (NER) is an important and well-studied task in natural language processing. The classic CoNLL-2003 English dataset, published almost 20 years ago, is commonly used to train and evaluate named entity taggers. The age of this dataset raises the question of how well these models perform when applied to modern data. In this paper, we present CoNLL++, a new annotated test set that mimics the process used to create the original CoNLL-2003 test set as closely as possible, except with data collected from 2020. Using CoNLL++, we evaluate the generalization of 20+ different models to modern data. We observe that different models have very different generalization behavior. F\textsubscript{1} scores of large transformer-based models which are pre-trained on recent data dropped much less than models using static word embeddings, and RoBERTa-based and T5 models achieve comparable F\textsubscript{1} scores on both CoNLL-2003 and CoNLL++. Our experiments show that achieving good generalizability requires a combined effort of developing larger models and continuing pre-training with in-domain and recent data. These results suggest standard evaluation methodology may have under-estimated progress on named entity recognition over the past 20 years; in addition to improving performance on the original CoNLL-2003 dataset, we have also improved the ability of our models to generalize to modern data.

We present a human-in-the-loop evaluation framework for fact-checking novel misinformation claims and identifying social media messages that violate relevant policies. Our approach extracts structured representations of check-worthy claims, which are aggregated and ranked for review. Stance classifiers are then used to identify tweets supporting novel misinformation claims, which are further reviewed to determine whether they violate relevant policies. To demonstrate the feasibility of our approach, we develop a baseline system based on modern NLP methods for human-in-the-loop fact-checking in the domain of COVID-19 treatments. Using our baseline system, we show that human fact-checkers can identify 124 tweets per hour that violate Twitter's policies on COVID-19 misinformation. We will make our code, data, and detailed annotation guidelines available to support the evaluation of human-in-the-loop systems that identify novel misinformation directly from raw user-generated content.

In the process of materials discovery, chemists currently need to perform many laborious, time-consuming, and often dangerous lab experiments. To accelerate this process, we propose a framework for robots to assist chemists by performing lab experiments autonomously. The solution allows a general-purpose robot to perform diverse chemistry experiments and efficiently make use of available lab tools. Our system can load high-level descriptions of chemistry experiments, perceive a dynamic workspace, and autonomously plan the required actions and motions to perform the given chemistry experiments with common tools found in the existing lab environment. Our architecture uses a modified PDDLStream solver for integrated task and constrained motion planning, which generates plans and motions that are guaranteed to be safe by preventing collisions and spillage. We present a modular framework that can scale to many different experiments, actions, and lab tools. In this work, we demonstrate the utility of our framework on three pouring skills and two foundational chemical experiments for materials synthesis: solubility and recrystallization. More experiments and updated evaluations can be found at https://ac-rad.github.io/arc-icra2023.

Calculating an Air Quality Index (AQI) typically uses data streams from air quality sensors deployed at fixed locations and the calculation is a real time process. If one or a number of sensors are broken or offline, then the real time AQI value cannot be computed. Estimating AQI values for some point in the future is a predictive process and uses historical AQI values to train and build models. In this work we focus on gap filling in air quality data where the task is to predict the AQI at 1, 5 and 7 days into the future. The scenario is where one or a number of air, weather and traffic sensors are offline and explores prediction accuracy under such situations. The work is part of the MediaEval'2022 Urban Air: Urban Life and Air Pollution task submitted by the DCU-Insight-AQ team and uses multimodal and crossmodal data consisting of AQI, weather and CCTV traffic images for air pollution prediction.

As part of the MediaEval 2022 Predicting Video Memorability task we explore the relationship between visual memorability, the visual representation that characterises it, and the underlying concept portrayed by that visual representation. We achieve state-of-the-art memorability prediction performance with a model trained and tested exclusively on surrogate dream images, elevating concepts to the status of a cornerstone memorability feature, and finding strong evidence to suggest that the intrinsic memorability of visual content can be distilled to its underlying concept or meaning irrespective of its specific visual representational.