1. Hongrae Lee - Google Scholar
Researching and revising what language models say, using language models L Gao, Z Dai, P Pasupat, A Chen, AT Chaganty, Y Fan, VY Zhao, N Lao
Google - Cited by 3,237 - Deep learning - generation - NLP - summarization
2. Hongrae Lee - Google Research
Research Areas: Algorithms and Theory, Data Management, Data Mining and Modeling, Distributed Systems and Parallel Computing, Human-Computer Interaction and ...
Research Areas
3. Hongrae Lee - DBLP
10 aug 2024 · List of computer science publications by Hongrae Lee.
List of computer science publications by Hongrae Lee
4. Hongrae Lee | IEEE Xplore Author Details
A public charity, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright ...
Your support ID is: 8203162003988393522.
5. Hongrae Lee - Google Scholar
Natural language to SQL: Where are we today? H Kim, BH So, WS Han, H Lee. Proceedings of the VLDB Endowment 13 (10), 1737-1750, 2020.
Google - 3.237 lần trích dẫn - Deep learning - generation - NLP - summarization
6. Hongrae Lee - ACL Anthology
Language models (LMs) now excel at many tasks such as question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading ...
pdf bib abs RARR: Researching and Revising What Language Models Say, Using Language ModelsLuyu Gao | Zhuyun Dai | Panupong Pasupat | Anthony Chen | Arun Tejasvi Chaganty | Yicheng Fan | Vincent Zhao | Ni Lao | Hongrae Lee | Da-Cheng Juan | Kelvin GuuProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
7. Hongrae Lee - Facebook
Bevat niet: outfit | Resultaten tonen met:outfit
See posts, photos and more on Facebook.
8. Hongrae Lee - Home - ACM Digital Library
... set of publication metrics. The Author Profile Pages reveal the first result of these efforts. Normalization: ACM uses normalization algorithms to weigh ...
See AlsoOwlsdaily Message BoardSearch ACM Digital Library
9. Oceanside Film Fest showcases films, music and more | KPBS Public Media
19 feb 2024 · Hong-rae Lee's "Those Were the Good Days" is an international ... We'll be in touch if we look into your question. Sign up for the KPBS ...
The five-day festival kicks off with musician and film composer Jason Hill in conversation
10. Carbon electrode obtained via pyrolysis of plasma-deposited ...
Zhiquan Song,a Jun-Hee Park,a Hong-Rae Kim,a Ga-Yeon Lee,ad Min-Jung Kang, ORCID logo b Moo-Hwan Kimc and Jae-Chul Pyun · ORCID logo *a. Author affiliations.
In this study, parylene-C films from plasma deposition as well as thermal deposition were pyrolyzed to prepare a carbon electrode for application in electrochemical immunoassays. Plasma deposition could prepare parylene-C in a faster deposition rate and more precise control over the thickness in comparison w
11. [PDF] contents - :: Immune Network ::
Sung-Sook Lee and In-Hong Choi ... Juyang Kim, Hong Rae Cho and Byungsuk Kwon ...
12. The Cosmopolitan Vision in Chang-rae Lee's A Gesture Life
Cosmopolitanism is the idea that human beings regardless of their racial origins and national affiliation can break up entrenched stereotypes set ... rae Lee's A ...
Chang-rae Lee, a contemporary Korean-American writer, is renowned in the literary world for his rich imagination, delicate emotional expression, unique transcultural perspective and idiosyncratic narrative technique. He is one of the representatives who succeeds in transcending the classical paradigm of ethnic literature. Cosmopolitanism stems from ancient Greek philosophy, further developing in the age of Enlightenment and thriving in the era of globalization. Taking close reading as the primary methodology and cosmopolitanism as the major theoretical framework, this research attempts to provide a multi-dimensional, interdisciplinary and in-depth interpretation of Lee’s A Gesture Life, and finds that Lee has expressed his ideal vision that rejects the essentialist paradigm of unchanging cultural identity and upholds cosmopolitanism which embraces cultural diversity and heterogeneity. Additionally, through the depiction of cosmopolitan community, Lee has expressed his expectation for peaceful coexistence, communal solidarity, and mutual assistance among various ethnicities, and he has visualized a picture that different ethnic groups engage in transcultural communication in a harmonious way. In conclusion, A Gesture Life has widened the boundaries of Korean-American literature, and the cosmopolitan vision in the text has contributed to the development and prosperity of American ethnic literature.
13. [PDF] Braden Hancock, Hongrae Lee, Cong Yu
Failed Attempts: Before paying crowdworkers to generate our training set, we attempted to build training sets using heuristics: • Heuristic 1: Use as titles ...
14. Selectivity estimation of approximate predicates on text - UBC ...
Selectivity estimation of approximate predicates on text Lee, Hongrae ... We propose a set of related summary structures ... We propose a set of related ...
This dissertation studies selectivity estimation of approximate predicates on text. Intuitively, we aim to count the number of strings that are similar to a given query string. This type of problem is crucial in handling text in RDBMSs in an error-tolerant way. A common difficu
15. [2201.08239] LaMDA: Language Models for Dialog Applications - arXiv
20 jan 2022 · ... Hongrae Lee, Huaixiu Steven Zheng, Amin Ghafouri, Marcelo Menegali ... The first challenge, safety, involves ensuring that the model's responses ...
We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and are pre-trained on 1.56T words of public dialog data and web text. While model scaling alone can improve quality, it shows less improvements on safety and factual grounding. We demonstrate that fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding. The first challenge, safety, involves ensuring that the model's responses are consistent with a set of human values, such as preventing harmful suggestions and unfair bias. We quantify safety using a metric based on an illustrative set of human values, and we find that filtering candidate responses using a LaMDA classifier fine-tuned with a small amount of crowdworker-annotated data offers a promising approach to improving model safety. The second challenge, factual grounding, involves enabling the model to consult external knowledge sources, such as an information retrieval system, a language translator, and a calculator. We quantify factuality using a groundedness metric, and we find that our approach enables the model to generate responses grounded in known sources, rather than responses that merely sound plausible. Finally, we explore the use of LaMDA in the domains of education and content recommendations, and a...