Lexical substitution (LS) aims at finding appropriate substitutes for a target word in a sentence. Recently, LS methods based on pretrained language models have made remarkable progress, generating potential substitutes for a target word through analysis of its contextual surroundings. However, these methods tend to overlook the preservation of the sentence's meaning when generating the substitutes. This study explores how to generate the substitute candidates from a paraphraser, as the generated paraphrases from a paraphraser contain variations in word choice and preserve the sentence's meaning. Since we cannot directly generate the substitutes via commonly used decoding strategies, we propose two simple decoding strategies that focus on the variations of the target word during decoding. Experimental results show that our methods outperform state-of-the-art LS methods based on pre-trained language models on three benchmarks.

We argue that such frameworks should satisfy the following requirements at least. Alertness They should detect potential problems with extremely high recall (i.e., near-zero misses), while appropriately crediting the benefits of the conversational systems. Moreover, when aiming for high recall, different people involved (i.e., not just users, but also workers who label data for training the system, etc.) should be taken into account; in particular, if the evaluation framework ignores some negative impacts on marginalised people, it does not satisfy the alertness requirement. Specificity By this we mean that the evaluation framework should be specific when locating the problem(s) within conversations. For example, an evaluation result that says"There is a problem somewhere inside this conversation session" is less useful than one that says"There is a problem in this particular system turn," which in turn is less useful than one that says "There is a problem in this particular claim within this system turn."

Determining multi-robot motion policies for persistently monitoring a region with limited sensing, communication, and localization constraints in non-GPS environments is a challenging problem. To take the localization constraints into account, in this paper, we consider a heterogeneous robotic system consisting of two types of agents: anchor agents with accurate localization capability and auxiliary agents with low localization accuracy. To localize itself, the auxiliary agents must be within the communication range of an {anchor}, directly or indirectly. The robotic team's objective is to minimize environmental uncertainty through persistent monitoring. We propose a multi-agent deep reinforcement learning (MARL) based architecture with graph convolution called Graph Localized Proximal Policy Optimization (GALOPP), which incorporates the limited sensor field-of-view, communication, and localization constraints of the agents along with persistent monitoring objectives to determine motion policies for each agent. We evaluate the performance of GALOPP on open maps with obstacles having a different number of anchor and auxiliary agents. We further study (i) the effect of communication range, obstacle density, and sensing range on the performance and (ii) compare the performance of GALOPP with non-RL baselines, namely, greedy search, random search, and random search with communication constraint. For its generalization capability, we also evaluated GALOPP in two different environments -- 2-room and 4-room. The results show that GALOPP learns the policies and monitors the area well. As a proof-of-concept, we perform hardware experiments to demonstrate the performance of GALOPP.

Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms. Due to the non-identifiability of the instance-dependent noise transition matrix, most existing algorithms address the problem by assuming the noisy label generation process to be independent of the instance features. Unfortunately, noisy labels in real-world applications often depend on both the true label and the features. In this work, we tackle instance-dependent label noise with a novel deep generative model that avoids explicitly modeling the noise transition matrix. Our algorithm leverages casual representation learning and simultaneously identifies the high-level content and style latent factors from the data. By exploiting the supervision information of noisy labels with structural causal models, our empirical evaluations on a wide range of synthetic and real-world instance-dependent label noise datasets demonstrate that the proposed algorithm significantly outperforms the state-of-the-art counterparts.

Empathetic conversation is psychologically supposed to be the result of conscious alignment and interaction between the cognition and affection of empathy. However, existing empathetic dialogue models usually consider only the affective aspect or treat cognition and affection in isolation, which limits the capability of empathetic response generation. In this work, we propose the CASE model for empathetic dialogue generation. It first builds upon a commonsense cognition graph and an emotional concept graph and then aligns the user's cognition and affection at both the coarse-grained and fine-grained levels. Through automatic and manual evaluation, we demonstrate that CASE outperforms state-of-the-art baselines of empathetic dialogues and can generate more empathetic and informative responses.

It is imperative to discern the relationships between multiple time series for accurate forecasting. In particular, for stock prices, components are often divided into groups with the same characteristics, and a model that extracts relationships consistent with this group structure should be effective. Thus, we propose the concept of hierarchical permutation-equivariance, focusing on index swapping of components within and among groups, to design a model that considers this group structure. When the prediction model has hierarchical permutation-equivariance, the prediction is consistent with the group relationships of the components. Therefore, we propose a hierarchically permutation-equivariant model that considers both the relationship among components in the same group and the relationship among groups. The experiments conducted on real-world data demonstrate that the proposed method outperforms existing state-of-the-art methods.

When the epic open-world PlayStation 4 game Red Dead Redemption 2 was developed in 2013, it took 2,200 days to record the 1,200 voices in the game with 700 voice actors, who recited the 500,000 lines of dialogue. It was a massive feat that is nearly impossible for any other studio to replicate – let alone a games studio smaller than Rockstar Games. But with advances in artificial intelligence it is becoming easier and easier to recreate human voices to create automated real-time responses, near limitless dialogue options and speech tailored to a user's unique input. But the technology raises questions about the ethics of synthesising voices. The Australian software developer Replica Studios rolled out a voice synthesiser platform for games developers in 2019 – a tool used by Australian games developer PlaySide Studios in their game Age of Darkness: Final Stand.

A film production company was targeted by fraudsters using a voice'clone' of Benedict Cumberbatch created by AI, the company revealed to DailyMail.com. An eerily convincing Benedict Cumberbatch phoned the company to discuss a film deal, says Bob William, screenwriter and director at Peabody Films, a company based in Malaga, Spain. The AI Cumberbatch was '100 percent the voice', says Mr William, adding that the company was convinced it was the real actor at first. When'Cumberbatch' and his agent refused to meet in-person, they realized the ruse, saving themselves from losing money. But, many others have fallen for similar scams, as AI is opening the door for new tools that bad actors can use to steal money from unsuspecting people.

The rapid proliferation of information in the digital era underscores the importance of accurate historical representation and interpretation. While artificial intelligence has shown promise in various fields, its potential for historical fact-checking and gap-filling remains largely untapped. This study evaluates the performance of three large language models LLMs GPT 3.5, GPT 4, and GoogleBARD in the context of predicting and verifying historical events based on given data. A novel metric, Distance to Reality (DTR), is introduced to assess the models' outputs against established historical facts. The results reveal a substantial potential for AI in historical studies, with GPT 4 demonstrating superior performance. This paper underscores the need for further research into AI's role in enriching our understanding of the past and bridging historical knowledge gaps.

Machine learning (ML) in healthcare presents numerous opportunities for enhancing patient care, population health, and healthcare providers' workflows. However, the real-world clinical and cost benefits remain limited due to challenges in data privacy, heterogeneous data sources, and the inability to fully leverage multiple data modalities. In this perspective paper, we introduce "patchwork learning" (PL), a novel paradigm that addresses these limitations by integrating information from disparate datasets composed of different data modalities (e.g., clinical free-text, medical images, omics) and distributed across separate and secure sites. PL allows the simultaneous utilization of complementary data sources while preserving data privacy, enabling the development of more holistic and generalizable ML models. We present the concept of patchwork learning and its current implementations in healthcare, exploring the potential opportunities and applicable data sources for addressing various healthcare challenges. PL leverages bridging modalities or overlapping feature spaces across sites to facilitate information sharing and impute missing data, thereby addressing related prediction tasks. We discuss the challenges associated with PL, many of which are shared by federated and multimodal learning, and provide recommendations for future research in this field. By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models. This paradigm promises to strike a balance between personalization and generalizability, ultimately enhancing patient experiences, improving population health, and optimizing healthcare providers' workflows. Introduction Machine learning (ML) in healthcare is a rapidly evolving field, presenting numerous opportunities for progress. Active and passive patient data collection, both during and outside medical care, can be utilized to address health challenges. As a result, ML has become an essential tool for processing and analyzing these data in various domains, including natural language processing, computer vision, and more. ML systems have demonstrated their potential to enhance patient experiences, improve population health, reduce per capita healthcare costs, and optimize healthcare providers' workflows Data privacy is a major challenge facing the use of ML in healthcare, as it restricts the potential for pooling electronic health record (EHR) data from multiple sites. While single modality models exist (e.g., clinical notes, lab tests, omics, or medical images), systems that simultaneously leverage multiple modalities are relatively scarce. MML combines disparate data sources to capitalize on complementary information, thereby improving performance.