no code implementations • 4 Apr 2024 • Jooyoung Lee, Fan Yang, Thanh Tran, Qian Hu, Emre Barut, Kai-Wei Chang, Chengwei Su
The Frozen large LM is then prompted to predict a task output based on the rationale generated by the lightweight LM.
1 code implementation • 7 Jan 2024 • Chau Nguyen, Phuong Nguyen, Thanh Tran, Dat Nguyen, An Trieu, Tin Pham, Anh Dang, Le-Minh Nguyen
The Competition on Legal Information Extraction/Entailment (COLIEE) is held annually to encourage advancements in the automatic processing of legal texts.
no code implementations • 23 Sep 2022 • Thanh Tran, Sebastian Bader, Jan Lundgren
The augmented dataset was created by combining these synthesized sounds with the original sounds.
no code implementations • 8 Aug 2022 • Thanh Tran, Sebastian Bader, Jan Lundgren
In the scope of this paper, we demonstrate the removal of generated noise with Gaussian distribution and the environmental noise with a specific example of the water sink faucet noise from the induction motor sounds.
no code implementations • 11 May 2022 • Kai Wei, Dillon Knox, Martin Radfar, Thanh Tran, Markus Muller, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris, Maurizio Omologo
Dialogue act classification (DAC) is a critical task for spoken language understanding in dialogue systems.
no code implementations • 22 Feb 2022 • Michiharu Yamashita, Jia Tracy Shen, Thanh Tran, Hamoon Ekhtiari, Dongwon Lee
In online job marketplaces, it is important to establish a well-defined job title taxonomy for various downstream tasks (e. g., job recommendation, users' career analysis, and turnover prediction).
no code implementations • 13 Dec 2021 • Kai Wei, Thanh Tran, Feng-Ju Chang, Kanthashree Mysore Sathyendra, Thejaswi Muniyappa, Jing Liu, Anirudh Raju, Ross McGowan, Nathan Susanj, Ariya Rastrow, Grant P. Strimel
Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio.
Natural Language Understanding Spoken Language Understanding
no code implementations • 7 Feb 2021 • Yifan Hu, Changwei Hu, Thanh Tran, Tejaswi Kasturi, Elizabeth Joseph, Matt Gillingham
Gender information is no longer a mandatory input when registering for an account at many leading Internet companies.
no code implementations • EMNLP 2020 • Thanh Tran, Yifan Hu, Changwei Hu, Kevin Yen, Fei Tan, Kyumin Lee, Serim Park
HABERTOR inherits BERT's architecture, but is different in four aspects: (i) it generates its own vocabularies and is pre-trained from the scratch using the largest scale hatespeech dataset; (ii) it consists of Quaternion-based factorized components, resulting in a much smaller number of parameters, faster training and inferencing, as well as less memory usage; (iii) it uses our proposed multi-source ensemble heads with a pooling layer for separate input sources, to further enhance its effectiveness; and (iv) it uses a regularized adversarial training with our proposed fine-grained and adaptive noise magnitude to enhance its robustness.
no code implementations • 31 Aug 2020 • Thanh Tran, Di You, Kyumin Lee
Quaternion space has brought several benefits over the traditional Euclidean space: Quaternions (i) consist of a real and three imaginary components, encouraging richer representations; (ii) utilize Hamilton product which better encodes the inter-latent interactions across multiple Quaternion components; and (iii) result in a model with smaller degrees of freedom and less prone to overfitting.
1 code implementation • 8 Jun 2019 • Thanh Tran, Renee Sweeney, Kyumin Lee
Our first approach uses user-playlist-song interactions, and combines Mahalanobis distance scores between (i) a target user and a target song, and (ii) between a target playlist and the target song to account for both the user's preference and the playlist's theme.
1 code implementation • 1 May 2019 • Thanh Tran, Xinyue Liu, Kyumin Lee, Xiangnan Kong
Personalized recommendation algorithms learn a user's preference for an item by measuring a distance/similarity between them.
2 code implementations • 31 Aug 2018 • Thanh Tran, Kyumin Lee, Yiming Liao, Dongwon Lee
Following recent successes in exploiting both latent factor and word embedding models in recommendation, we propose a novel Regularized Multi-Embedding (RME) based recommendation model that simultaneously encapsulates the following ideas via decomposition: (1) which items a user likes, (2) which two users co-like the same items, (3) which two items users often co-liked, and (4) which two items users often co-disliked.
1 code implementation • 15 Nov 2017 • Jacopo Acquarelli, Elena Marchiori, Lutgarde M. C. Buydens, Thanh Tran, Twan van Laarhoven
2) How is the performance of hyperspectral image classification methods affected when using disjoint train and test sets?
no code implementations • 12 Oct 2017 • Thanh Tran, Kyumin Lee, Nguyen Vo, Hongkyu Choi
In Crowdfunding platforms, people turn their prototype ideas into real products by raising money from the crowd, or invest in someone else's projects.