Elvis S.

Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover useful insights in a large mass of information. Today scientific knowledge is accessed through search engines, but they are unable to organize scientific knowledge alone. In this paper we introduce Galactica: a large language model that can store, combine and reason about scientific knowledge. We train on a large scientific corpus of papers,… Show more

Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover useful insights in a large mass of information. Today scientific knowledge is accessed through search engines, but they are unable to organize scientific knowledge alone. In this paper we introduce Galactica: a large language model that can store, combine and reason about scientific knowledge. We train on a large scientific corpus of papers, reference material, knowledge bases and many other sources. We outperform existing models on a range of scientific tasks. On technical knowledge probes such as LaTeX equations, Galactica outperforms the latest GPT-3 by 68.2% versus 49.0%. Galactica also performs well on reasoning, outperforming Chinchilla on mathematical MMLU by 41.3% to 35.7%, and PaLM 540B on MATH with a score of 20.4% versus 8.8%. It also sets a new state-of-the-art on downstream tasks such as PubMedQA and MedMCQA dev of 77.6% and 52.9%. And despite not being trained on a general corpus, Galactica outperforms BLOOM and OPT-175B on BIG-bench. We believe these results demonstrate the potential for language models as a new interface for science. We open source the model for the benefit of the scientific community. Show less

Emotions are expressed in nuanced ways, which varies by collective or individual experiences, knowledge, and beliefs. Therefore, to understand emotion, as conveyed through text, a robust mechanism capable of capturing and modeling different linguistic nuances and phenomena is needed. We propose a semi-supervised, graph-based algorithm to produce rich structural descriptors which serve as the building blocks for constructing contextualized affect representations from text. The pattern-based… Show more

Emotions are expressed in nuanced ways, which varies by collective or individual experiences, knowledge, and beliefs. Therefore, to understand emotion, as conveyed through text, a robust mechanism capable of capturing and modeling different linguistic nuances and phenomena is needed. We propose a semi-supervised, graph-based algorithm to produce rich structural descriptors which serve as the building blocks for constructing contextualized affect representations from text. The pattern-based representations are further enriched with word embeddings and evaluated through several emotion recognition tasks. Our experimental results demonstrate that the proposed method outperforms state-of-the-art techniques on emotion recognition tasks. Show less

The rapid growth of social networks have enabled users to instantly share what is happening around them. With the character-limitation and other feature constraints imposed by microblogs, users are obliged to express their intentions in implicit forms. This behavior poses many challenges for contextual approaches that aim to identify user intentions. Furthermore, users have the tendency to display different degree of preferences towards specific interests, simultaneously in time, making it… Show more

The rapid growth of social networks have enabled users to instantly share what is happening around them. With the character-limitation and other feature constraints imposed by microblogs, users are obliged to express their intentions in implicit forms. This behavior poses many challenges for contextual approaches that aim to identify user intentions. Furthermore, users have the tendency to display different degree of preferences towards specific interests, simultaneously in time, making it difficult for models to rank the discovered interests. We propose a dynamic interest keyword model, a graph-based ranking mechanism, that identifies the different degrees of interests of a user. Our results show that the proposed system detects human-inferred interests, 94% of the time, showing that the model is feasible and contributes various insights that can be used to improve user intention identification systems. Show less

Recently, several news aggregation services have emerged to deal with the problem of information overload and news personalization. These news providers are able to organize news based on content similarity as a strategy to improve the user reading experience. However, organizing news solely on content fails to consider actual human reading behavior, and in turn ignores the importance of user perception in news personalization. We propose an enhanced news clustering technique based on an user… Show more

Recently, several news aggregation services have emerged to deal with the problem of information overload and news personalization. These news providers are able to organize news based on content similarity as a strategy to improve the user reading experience. However, organizing news solely on content fails to consider actual human reading behavior, and in turn ignores the importance of user perception in news personalization. We propose an enhanced news clustering technique based on an user affect model, which is a feasible framework for news categorization that can contribute to building more human-centric interactive systems. Empirical results demonstrate the effectiveness of clustering news articles through the enrichment of a user affect model when compared to traditional keyword-based clustering. Show less

Mental illnesses rank as some of the most disabling conditions, affecting millions of people, across the globe. In general, the main challenge of mental disorders is that they remain difficult to detect on suffering patients. In an online environment, the challenge extends to the collection of patients data and the implementation of proper algorithms to assist in the detection of such illnesses. In this paper, we propose a novel data collection mechanism and build predictive models that… Show more

Mental illnesses rank as some of the most disabling conditions, affecting millions of people, across the globe. In general, the main challenge of mental disorders is that they remain difficult to detect on suffering patients. In an online environment, the challenge extends to the collection of patients data and the implementation of proper algorithms to assist in the detection of such illnesses. In this paper, we propose a novel data collection mechanism and build predictive models that leverage language and behavioral patterns, used particularly on Twitter, to determine whether a user is suffering from a mental disorder. After training the predictive models, they are further pre-trained to serve as the backend for our demonstration, MIDAS. MIDAS offers an analytics web-service to explore several characteristics pertaining to user's linguistic and behavioral patterns on social media, with respect to mental illnesses. Show less

Mental disorders are currently affecting millions of people from different cultures, age groups and geographic regions. The challenge of mental disorders is that they are difficult to detect on suffering patients, thus presenting an alarming number of undetected cases and misdiagnosis. In this paper, we aim at building predictive models that leverage language and behavioral patterns, used particularly in social media, to determine whether a user is suffering from two cases of mental disorder… Show more

Mental disorders are currently affecting millions of people from different cultures, age groups and geographic regions. The challenge of mental disorders is that they are difficult to detect on suffering patients, thus presenting an alarming number of undetected cases and misdiagnosis. In this paper, we aim at building predictive models that leverage language and behavioral patterns, used particularly in social media, to determine whether a user is suffering from two cases of mental disorder. These predictive models are made possible by employing a novel data collection process, coined as Subconscious Crowdsourcing, which helps to collect a faster and more reliable dataset of patients. Our experiments suggest that extracting specific language patterns and social interaction features from reliable patient datasets can greatly contribute to further analysis and detection of mental disorders. Show less

The connected society we live in today has allowed online users to willingly share opinions on an unprecedented scale. Motivated by the advent of mass opinion sharing, it is then crucial to devise algorithms that efficiently identify the emotions expressed within the opinionated content. Traditional opinion-based classifiers require extracting high-dimensional feature representations, which become computationally expensive to process and can misrepresent or deteriorate the accuracy of a… Show more

The connected society we live in today has allowed online users to willingly share opinions on an unprecedented scale. Motivated by the advent of mass opinion sharing, it is then crucial to devise algorithms that efficiently identify the emotions expressed within the opinionated content. Traditional opinion-based classifiers require extracting high-dimensional feature representations, which become computationally expensive to process and can misrepresent or deteriorate the accuracy of a classifier. In this paper, we propose an unsupervised graph-based approach for extracting Twitter-specific emotion-bearing patterns to be used as features. By utilizing a more representative list of patterns, as features, we improved the precision and recall of a given emotion classification task. Due to its novel bootstrapping process, the full system is also adaptable to different domains and languages. The experimented results demonstrate that the extracted patterns are effective in identifying emotions for English, Spanish, and French Twitter streams. We also provide detailed experiments and offer an extended version of our algorithm to support the classification of Indonesian microblog posts. Overall, our empirical experimented results demonstrate that the proposed approach bears desirable characteristics such as accuracy, generality, adaptability, minimal supervision, and coverage. Show less

Social networks, which have become extremely popular in the twenty first century, contain a tremendous amount of user-generated content about real-world events. This user-generated content relays real-world events as they happen, and sometimes even ahead of the newswire. The goal of this work is to identify events from social streams. The proposed model utilizes sliding window-based statistical techniques to extract event candidates from social streams. Subsequently, the “Concept-based evolving… Show more

Social networks, which have become extremely popular in the twenty first century, contain a tremendous amount of user-generated content about real-world events. This user-generated content relays real-world events as they happen, and sometimes even ahead of the newswire. The goal of this work is to identify events from social streams. The proposed model utilizes sliding window-based statistical techniques to extract event candidates from social streams. Subsequently, the “Concept-based evolving graph sequences” approach is employed to verify information propagation trends of event candidates and to identify those events. The experimental results show the usefulness of our approach in identifying real-world events in social streams. Show less

Today, most personalized and recommendation services are built around interest extraction models but the outputs of these algorithms are ambiguous in nature. This makes it difficult to understand what users are personally interested in and more importantly what they are feeling towards these interests and how their interests transition through time. By studying both users' interests and emotions, simultaneously, one can further investigate the motivation behind these interests. Such findings… Show more

Today, most personalized and recommendation services are built around interest extraction models but the outputs of these algorithms are ambiguous in nature. This makes it difficult to understand what users are personally interested in and more importantly what they are feeling towards these interests and how their interests transition through time. By studying both users' interests and emotions, simultaneously, one can further investigate the motivation behind these interests. Such findings can be useful to build better interest extraction models and algorithms that leverage personalized and recommendation services (e.g., ads. targeting, e-commerce and dating sites). In this paper, we propose the demonstration of a web visualization tool - EmoViz - which facilitates the further exploration of users' interests and their emotions at a global scale. Such tool, through the use of various visual components, aims to alleviate the problem of understanding what users of the world are interested in and the motivations behind their interests and feelings. Show less