Agoda is an online travel booking platform for accommodations, flights, and more. We build and deploy cutting-edge technology that connects travelers with more than 2.5 million accommodations globally. Based in Asia and part of Booking Holdings, our 6,000 employees representing 90 nationalities foster a work environment rich in diversity, creativity, and collaboration. We innovate through a culture of experimentation and ownership, enhancing the ability for our customers to experience the world. In this role, you'll get to: Strategy: Conduct analyses to identify growth opportunities and prioritize investment areas in APAC for Strategic Partnerships team based on analytical insights, industry trends, and changing competitive landscape.

Three Australian-US scientific teams will set their sights on minimising the impact of health pandemics, harmful environmental emissions and drought using AI approaches. Minister for Industry and Science Ed Husic welcomed the announcement that the US National Science Foundation and Australia's national science agency CSIRO have awarded grants under their Collaboration Opportunities in Responsible and Ethical AI initiative. The grants total $1.8 million on the US side and $2.3 million on the Australian side, and include researchers from the University of NSW, RMIT University, University of Technology Sydney and the University of Melbourne. "These grants will support valuable research in ethical artificial intelligence, while strengthening relationships between US and Australian research organisations," Minister Husic said. "The NSF-CSIRO initiative will bring the best Australian and US researchers together from a range of disciplinary backgrounds, to share knowledge and learn from each other. "AI is an important driver of new scientific discoveries and economic prosperity, while also safeguarding national wellbeing.

Modern deep learning techniques have illustrated their excellent capabilities in many areas, but relies on large training data. Optimization-based meta-learning train a model on a variety tasks, such that it can solve new learning tasks using only a small number of training samples.However, these methods assumes that training and test dataare identically and independently distributed. To overcome such limitation, in this paper, we propose invariant meta learning for out-of-distribution tasks. Specifically, invariant meta learning find invariant optimal meta-initialization,and fast adapt to out-of-distribution tasks with regularization penalty. Extensive experiments demonstrate the effectiveness of our proposed invariant meta learning on out-of-distribution few-shot tasks.

Open domain conversational agents can answer a broad range of targeted queries. However, the sequential nature of interaction with these systems makes knowledge exploration a lengthy task which burdens the user with asking a chain of well phrased questions. In this paper, we present a retrieval based system and associated dataset for predicting the next questions that the user might have. Such a system can proactively assist users in knowledge exploration leading to a more engaging dialog. The retrieval system is trained on a dataset which contains ~14K multi-turn information-seeking conversations with a valid follow-up question and a set of invalid candidates. The invalid candidates are generated to simulate various syntactic and semantic confounders such as paraphrases, partial entity match, irrelevant entity, and ASR errors. We use confounder specific techniques to simulate these negative examples on the OR-QuAC dataset and develop a dataset called the Follow-up Query Bank (FQ-Bank). Then, we train ranking models on FQ-Bank and present results comparing supervised and unsupervised approaches. The results suggest that we can retrieve the valid follow-ups by ranking them in higher positions compared to confounders, but further knowledge grounding can improve ranking performance.

Smart devices, such as smart speakers, are becoming ubiquitous, and users expect these devices to act in accordance with their preferences. In particular, since these devices gather and manage personal data, users expect them to adhere to their privacy preferences. However, the current approach of gathering these preferences consists in asking the users directly, which usually triggers automatic responses failing to capture their true preferences. In response, in this paper we present a collaborative filtering approach to predict user preferences as norms. These preference predictions can be readily adopted or can serve to assist users in determining their own preferences. Using a dataset of privacy preferences of smart assistant users, we test the accuracy of our predictions.

Empathy is an important characteristic to be considered when building a more intelligent and humanized dialogue agent. However, existing methods did not fully comprehend empathy as a complex process involving three aspects: cognition, affection and behavior. In this paper, we propose CAB, a novel framework that takes a comprehensive perspective of cognition, affection and behavior to generate empathetic responses. For cognition, we build paths between critical keywords in the dialogue by leveraging external knowledge. This is because keywords in a dialogue are the core of sentences. Building the logic relationship between keywords, which is overlooked by the majority of existing works, can improve the understanding of keywords and contextual logic, thus enhance the cognitive ability. For affection, we capture the emotional dependencies with dual latent variables that contain both interlocutors' emotions. The reason is that considering both interlocutors' emotions simultaneously helps to learn the emotional dependencies. For behavior, we use appropriate dialogue acts to guide the dialogue generation to enhance the empathy expression. Extensive experiments demonstrate that our multi-perspective model outperforms the state-of-the-art models in both automatic and manual evaluation.

Recent advances in the capacity of large language models to generate human-like text have resulted in their increased adoption in user-facing settings. In parallel, these improvements have prompted a heated discourse around the risks of societal harms they introduce, whether inadvertent or malicious. Several studies have explored these harms and called for their mitigation via development of safer, fairer models. Going beyond enumerating the risks of harms, this work provides a survey of practical methods for addressing potential threats and societal harms from language generation models. We draw on several prior works' taxonomies of language model risks to present a structured overview of strategies for detecting and ameliorating different kinds of risks/harms of language generators. Bridging diverse strands of research, this survey aims Figure 1: Overview of Intervention Strategies. A typical to serve as a practical guide for both LM researchers ML/NLP model development process involves data and practitioners, with explanations collection/curation, model training and design, inference, of different mitigation strategies' motivations, and finally application deployment.

Anticipating future actions in a video is useful for many autonomous and assistive technologies. Most prior action anticipation work treat this as a vision modality problem, where the models learn the task information primarily from the video features in the action anticipation datasets. However, knowledge about action sequences can also be obtained from external textual data. In this work, we show how knowledge in pretrained language models can be adapted and distilled into vision-based action anticipation models. We Figure 1: A model learning the action anticipation from show that a simple distillation technique can only the vision modality (video frames) is essentially achieve effective knowledge transfer and provide exposed to a very limited set of action sequences. Language consistent gains on a strong vision model models, which are pre-trained on large-scale text, (Anticipative Vision Transformer) for two action can learn this distribution from the task, and a much anticipation datasets (3.5% relative gain larger domain-relevant text. We propose distilling this on EGTEA-GAZE+ and 7.2% relative gain on knowledge from text modality models to vision modality EPIC-KITCHEN 55), giving a new state-of-theart model for video action anticipation task.

A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we learn an optimal model in training data, it could have better generalization performance in testing tasks. However, learning such a model is not possible in standard machine learning frameworks as the distribution of the test data is unknown. To tackle this challenge, we propose a novel robust meta-learning method, which is more robust to the image-based testing tasks which is unknown and has distribution shifts with training tasks. Our robust meta-learning method can provide robust optimal models even when data from each distribution are scarce. In experiments, we demonstrate that our algorithm not only has better generalization performance but also robust to different unknown testing tasks.

In this work, we further develop the Physics-informed Spectral Learning (PiSL) by Espath et al. \cite{Esp21} based on a discrete $L^2$ projection to solve the discrete Hodge--Helmholtz decomposition from sparse data. Within this physics-informed statistical learning framework, we adaptively build a sparse set of Fourier basis functions with corresponding coefficients by solving a sequence of minimization problems where the set of basis functions is augmented greedily at each optimization problem. Moreover, our PiSL computational framework enjoys spectral (exponential) convergence. We regularize the minimization problems with the seminorm of the fractional Sobolev space in a Tikhonov fashion. In the Fourier setting, the divergence- and curl-free constraints become a finite set of linear algebraic equations. The proposed computational framework combines supervised and unsupervised learning techniques in that we use data concomitantly with the projection onto divergence- and curl-free spaces. We assess the capabilities of our method in various numerical examples including the `Storm of the Century' with satellite data from 1993.