Previous works related to automatic personality recognition focus on using traditional classification models with linguistic features. However, attentive neural networks with contextual embeddings, which have achieved huge success in text classification, are rarely explored for this task. In this project, we have two major contributions. First, we create the first dialogue-based personality dataset, FriendsPersona, by annotating 5 personality traits of speakers from Friends TV Show through crowdsourcing. Second, we present a novel approach to automatic personality recognition using pre-trained contextual embeddings (BERT and RoBERTa) and attentive neural networks. Our models largely improve the state-of-art results on the monologue Essays dataset by 2.49%, and establish a solid benchmark on our FriendsPersona. By comparing results in two datasets, we demonstrate the challenges of modeling personality in multi-party dialogue.

Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding other users' privacy. In this work, we take a fresh perspective, and present PRINCE: a provider-side mechanism to produce tangible explanations for end-users, where an explanation is defined to be a set of minimal actions performed by the user that, if removed, changes the recommendation to a different item. Given a recommendation, PRINCE uses a polynomial-time optimal algorithm for finding this minimal set of a user's actions from an exponential search space, based on random walks over dynamic graphs. Experiments on two real-world datasets show that PRINCE provides more compact explanations than intuitive baselines, and insights from a crowdsourced user-study demonstrate the viability of such action-based explanations. We thus posit that PRINCE produces scrutable, actionable, and concise explanations, owing to its use of counterfactual evidence, a user's own actions, and minimal sets, respectively.

We investigate the complexity of learning query inseparable ELH ontologies in a variant of Angluin's exact learning model. Given a fixed data instance A* and a query language Q, we are interested in computing an ontology H that entails the same queries as a target ontology T on A*, that is, H and T are inseparable w.r.t. A* and Q. The learner is allowed to pose two kinds of questions. The first is `Does (T,A)\models q?', with A an arbitrary data instance and q and query in Q. An oracle replies this question with `yes' or `no'. In the second, the learner asks `Are H and T inseparable w.r.t. A* and Q?'. If so, the learning process finishes, otherwise, the learner receives (A*,q) with q in Q, (T,A*)\models q and (H,A*)\not\models q (or vice-versa). Then, we analyse conditions in which query inseparability is preserved if A* changes. Finally, we consider the PAC learning model and a setting where the algorithms learn from a batch of classified data, limiting interactions with the oracles.

Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods consider these two problems as independent, resulting in a classical two-stage paradigm: first learn the environment dynamics and then plan accordingly. This approach, however, disconnects the two problems and can consequently lead to algorithms that are sample inefficient and time consuming. In this paper, we propose a novel algorithm that combines learning and planning together. Our algorithm is closely related to the spectral learning algorithm for predicitive state representations and offers appealing theoretical guarantees and time complexity. We empirically show on two domains that our approach is more sample and time efficient compared to classical methods.

Ontology-Mediated Query Answering (OMQA) is a well-established framework to answer queries over an RDFS or OWL Knowledge Base (KB). OMQA was originally designed for unions of conjunctive queries (UCQs), and based on certain answers. More recently, OMQA has been extended to SPARQL queries, but to our knowledge, none of the efforts made in this direction (either in the literature, or the so-called SPARQL entailment regimes) is able to capture both certain answers for UCQs and the standard interpretation of SPARQL over a plain graph. We formalize these as requirements to be met by any semantics aiming at conciliating certain answers and SPARQL answers, and define three additional requirements, which generalize to KBs some basic properties of SPARQL answers. Then we show that a semantics can be defined that satisfies all requirements for SPARQL queries with SELECT, UNION, and OPTIONAL, and for DLs with the canonical model property. We also investigate combined complexity for query answering under such a semantics over DL-Lite R KBs. In particular, we show for different fragments of SPARQL that known upper-bounds for query answering over a plain graph are matched.

Textual entailment is a fundamental task in natural language processing. Most approaches for solving the problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task. However, the proposed models do not fully exploit the information in the usually large and noisy KGs, and it is not clear how it can be effectively encoded to be useful for entailment. We present an approach that complements text-based entailment models with information from KGs by (1) using Personalized PageR- ank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture KG structure. Our technique extends the capability of text models exploiting structural and semantic information found in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps improve prediction accuracy. This is particularly evident in the challenging BreakingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models.

While most of humanity is suddenly on the net, the value of this singularity is hampered by the lack of credible digital identities: Social networking, person-to-person transactions, democratic conduct, cooperation and philanthropy are all hampered by the profound presence of fake identities, as illustrated by Facebook's removal of 5.4Bn fake accounts since the beginning of 2019. Here, we introduce the fundamental notion of a \emph{genuine personal identifier}---a globally unique and singular identifier of a person---and present a foundation for a decentralized, grassroots, bottom-up process in which every human being may create, own, and protect the privacy of a genuine personal identifier. The solution employs mutual sureties among owners of personal identifiers, resulting in a mutual-surety graph reminiscent of a web-of-trust. Importantly, this approach is designed for a distributed realization, possibly using distributed ledger technology, and does not depend on the use or storage of biometric properties. For the solution to be complete, additional components are needed, notably a mechanism that encourages honest behavior and a sybil-resilient governance system.

Could the same computer algorithms that teach autonomous cars to drive safely help identify nearby asteroids or discover life in the universe? NASA scientists are trying to figure that out by partnering with pioneers in artificial intelligence (AI)--companies such as Intel, IBM and Google--to apply advanced computer algorithms to problems in space science. Machine learning is a type of AI. It describes the most widely used algorithms and other tools that allow computers to learn from data in order to make predictions and categorize objects much faster and more accurately than a human being can. Consequently, machine learning is widely used to help technology companies recognize faces in photos or predict what movies people would enjoy.

San Diego, Calif., November 14, 2019 -- From companies worth billions of dollars to startups employing a small number of people, UC San Diego engineering alumni are at the core of the robotics ecosystem here in San Diego County. This was clearly evident at the sixth annual robotics forum organized by the UC San Diego Contextual Robotics Institute Nov. 7. The forum focused exclusively on local companies this year and was dubbed the San Diego Robotics Forum for the occasion. The goal was to showcase the breadth and depth of the region's robotics strengths, and solidify San Diego's reputation as Robot Beach. "We have an important mission here to showcase how strong San Diego is in the area of robotics," said Henrik Christensen, director of the UC San Diego Contextual Robotics Institute.

CAIML #9 took place on November 14 at factor-a – part of Dept, demonstrating how AI can be used for social good and to address societal challenges. "Aid organizations and governments are applying great effort in resolving the negative impacts of food insecurity induced crisis like famines or mass migration. One of the most limiting resources these actors face is the lack of preparation time for consistent and sustainable planning for emergency relief like setting refugee camps or securing supply with food and energy. Hence, increasing the lead time for preparation is an essential step and will result in saving many lives. The aim of this research is to increase the lead time by developing a ML based mathematical prediction model that is able to compute the probability for food insecure areas by learning from historical data. For performing such computations, our prediction model is developed and trained on historic open access data for the Horn of Africa (2009-2018). We used precipitation and vegetation data derived by remote sensing, as well as socio-economic, medical, armed conflict and disaster data. To overcome spatial inconsistencies in the input data and to meet the requirements of spatially homogenous input for neural networks, all data has been converted to geo-referenced raster maps. Disaster and armed conflict data has been fitted to districts while local food market prices have been interpolated. The IPC has been used as the food security label. In order to find a prediction model, deep learning methods have been used. Several analyses were applied on the collected data such as multicollinearity checks and principal component analyses. Preliminary cross-validated results have encouraged us to further investigate the detection of food insecure areas using open access data."