About
Building DAIR.AI wherein we are democratizing AI research, education, and technologies…
Articles by Elvis
Contributions
Activity
-
This Python tool looks super useful to crawl websites and convert data into LLM-ready markdown or structured data. I find myself doing this a lot…
This Python tool looks super useful to crawl websites and convert data into LLM-ready markdown or structured data. I find myself doing this a lot…
Shared by Elvis S.
-
Foundation Models for Music Provides a comprehensive overview of state-of-the-art pre-trained models and foundation models in music…
Foundation Models for Music Provides a comprehensive overview of state-of-the-art pre-trained models and foundation models in music…
Liked by Elvis S.
-
Foundation Models for Music Provides a comprehensive overview of state-of-the-art pre-trained models and foundation models in music…
Foundation Models for Music Provides a comprehensive overview of state-of-the-art pre-trained models and foundation models in music…
Shared by Elvis S.
Experience
Education
-
National Tsing Hua University
-
Activities and Societies: Phi Tau Phi Scholastic Honor
Focused on Machine Learning and NLP.
-
-
Focused on Data Mining and Text Mining.
-
-
Licenses & Certifications
Publications
-
Galactica: A Large Language Model for Science
arXiv
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,…
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.
-
CARER: Contextualized Affect Representations for Emotion Recognition
Empirical Methods in Natural Language Processing (EMNLP)
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…
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.
Other authors -
-
A Dynamic Influence Keyword Model for Identifying Implicit User Interests on Social Networks
ASONAM - IEEE
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…
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.
Other authors -
-
Clustering Social News Based on User Affection
Conference on Technologies and Applications of Artificial Intelligence (TAAI) - IEEE
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…
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.
Other authors -
-
MIDAS: Mental illness detection and analysis via social media
ASONAM - IEEE
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…
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.
Other authors -
-
Subconscious crowdsourcing: a feasible data collection mechanism for mental disorder detection on social media
ASONAM - IEEE
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…
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.
Other authors -
-
Unsupervised graph-based pattern extraction for multilingual emotion classification
Social Network Analysis and Mining - Springer
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…
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.
Other authors -
-
Concept-based event identification from social streams using evolving social graph sequences
Social Network Analysis and Mining - Springer
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…
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.
Other authors -
-
EmoViz: Mining the World's Interest through Emotion Analysis
ASONAM - IEEE
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…
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.
Other authors -
Projects
-
Prompt Engineering Guide
https://www.promptingguide.ai/
-
ML Papers of the Week
A newsletter to bring you the latest research developments in ML and LLMs.
https://www.linkedin.com/newsletters/top-ml-papers-of-the-week-7020865424875474944/ -
Modern Deep Learning Techniques Applied to Natural Language Processing
- Present
This project contains an overview of recent trends in deep learning based natural language processing (NLP). It covers the theoretical descriptions and implementation details behind deep learning models, such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), and reinforcement learning, used to solve various NLP tasks and applications. The overview also contains a summary of state of the art results for NLP tasks such as machine translation, question answering, and…
This project contains an overview of recent trends in deep learning based natural language processing (NLP). It covers the theoretical descriptions and implementation details behind deep learning models, such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), and reinforcement learning, used to solve various NLP tasks and applications. The overview also contains a summary of state of the art results for NLP tasks such as machine translation, question answering, and dialogue systems.
-
DAIR.ai
- Present
Democratizing Artificial Intelligence Research, Education, and Technologies
Honors & Awards
-
Phi Tau Phi Scholastic Honor
The Phi Tau Phi Scholastic Honor Society of the Republic of China
Awarded for achieving academic excellence during doctoral studies. This includes recognition for several research publications and a perfect GPA.
Languages
-
Spanish
Native or bilingual proficiency
-
Chinese
Elementary proficiency
-
English
Native or bilingual proficiency
-
Creoles and pidgins, English-based
Native or bilingual proficiency
More activity by Elvis
-
🌟 Excited to share that thanks to all of you, we've found the perfect name for our new Open Source LLM Evaluation product! 🌟 Big shoutout to…
🌟 Excited to share that thanks to all of you, we've found the perfect name for our new Open Source LLM Evaluation product! 🌟 Big shoutout to…
Liked by Elvis S.
-
I’m starting to suspect that the vast majority of people who are “working in AI” have never implemented a single ML model. Not even using a toy…
I’m starting to suspect that the vast majority of people who are “working in AI” have never implemented a single ML model. Not even using a toy…
Liked by Elvis S.
-
Earlier this year, we published our "Large Language Models: A Survey" paper. Six months and 150 citations later I still feel that the paper is pretty…
Earlier this year, we published our "Large Language Models: A Survey" paper. Six months and 150 citations later I still feel that the paper is pretty…
Liked by Elvis S.
-
After reading 100+ AI papers in the past couple of weeks, there has been a huge spike in research on RAG and AI agents. If you're looking for some…
After reading 100+ AI papers in the past couple of weeks, there has been a huge spike in research on RAG and AI agents. If you're looking for some…
Liked by Elvis S.
-
After reading 100+ AI papers in the past couple of weeks, there has been a huge spike in research on RAG and AI agents. If you're looking for some…
After reading 100+ AI papers in the past couple of weeks, there has been a huge spike in research on RAG and AI agents. If you're looking for some…
Shared by Elvis S.
-
By now, you might have seen that Grok-2 ranks #2 in the LMSYS Chatbot Arena. Insane how fast the xAI team has produced a strong frontier model that…
By now, you might have seen that Grok-2 ranks #2 in the LMSYS Chatbot Arena. Insane how fast the xAI team has produced a strong frontier model that…
Liked by Elvis S.
-
By now, you might have seen that Grok-2 ranks #2 in the LMSYS Chatbot Arena. Insane how fast the xAI team has produced a strong frontier model that…
By now, you might have seen that Grok-2 ranks #2 in the LMSYS Chatbot Arena. Insane how fast the xAI team has produced a strong frontier model that…
Shared by Elvis S.
-
Prompt caching seems extremely useful for efficient tool use, many-shot prompting, and multi-turn conversations, among other scenarios. If you are…
Prompt caching seems extremely useful for efficient tool use, many-shot prompting, and multi-turn conversations, among other scenarios. If you are…
Liked by Elvis S.
-
Prompt caching seems extremely useful for efficient tool use, many-shot prompting, and multi-turn conversations, among other scenarios. If you are…
Prompt caching seems extremely useful for efficient tool use, many-shot prompting, and multi-turn conversations, among other scenarios. If you are…
Shared by Elvis S.
-
🚀 The AI Scientist: A Glimpse into the Future of Research 🌐 A major milestone in AI just dropped—the fully autonomous AI Scientist. This…
🚀 The AI Scientist: A Glimpse into the Future of Research 🌐 A major milestone in AI just dropped—the fully autonomous AI Scientist. This…
Liked by Elvis S.
-
Better, steerable, and controllable text generation is key to applying LLMs in the real-world. While there are many issues with LLMs, there is…
Better, steerable, and controllable text generation is key to applying LLMs in the real-world. While there are many issues with LLMs, there is…
Shared by Elvis S.
-
Not sure why LLM compression is not discussed more often. Leveraging very large language models to build capable smaller LMs will be a huge win for…
Not sure why LLM compression is not discussed more often. Leveraging very large language models to build capable smaller LMs will be a huge win for…
Liked by Elvis S.
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Elvis S.
-
Elvis S
Graduate of Bachelors of Art in Human Resources Management at York University
-
Elvis S.
President owner Arielslimo Concierge,Luxury transportation,Security based out of New York City.
-
Elvis Ceballos S.
CEO
-
Elvis S.
-
Elvis Jerome S
Data Analyst
60 others named Elvis S. are on LinkedIn
See others named Elvis S.