11091. |
|
|
11092. |
|
|
11093. |
|
|
11094. |
- Hong, Xudong, et al.
(författare)
-
A surprisal oracle for active curriculum language modeling
- 2023
-
Ingår i: Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, December 6-7, 2023, Singapore / Alex Warstadt, Aaron Mueller, Leshem Choshen, Ethan Wilcox, Chengxu Zhuang, Juan Ciro, Rafael Mosquera, Bhargavi Paranjabe, Adina Williams, Tal Linzen, Ryan Cotterell (Editors). - : Association for Computational Linguistics. - 9781952148026
-
Konferensbidrag (refereegranskat)abstract
- We investigate the viability of surprisal in an active curriculum learning framework to train transformer-based language models in the context of the BabyLM Challenge. In our approach, the model itself selects the data to label (active learning) and schedules data samples based on a surprisal oracle (curriculum learning). We show that the models learn across all the tasks and datasets evaluated, making the technique a promising alternative approach to reducing the data requirements of language models. Our code is available at https://github.com/asayeed/ActiveBaby
|
|
11095. |
|
|
11096. |
- Hong, X., et al.
(författare)
-
Learning distributed event representations with a multi-task approach
- 2018
-
Ingår i: Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, New Orleans, June 5-6, 2018.. - Stroudsburg, PA, USA : Association for Computational Linguistics. - 9781948087223
-
Konferensbidrag (refereegranskat)abstract
- Human world knowledge contains information about prototypical events and their participants and locations. In this paper, we train the first models using multi-task learning that can both predict missing event participants and also perform semantic role classification based on semantic plausibility. Our best-performing model is an improvement over the previous state-of-the-art on thematic fit modelling tasks. The event embeddings learned by the model can additionally be used effectively in an event similarity task, also outperforming the state-of-the-art.
|
|
11097. |
- Hong, Xudong, et al.
(författare)
-
Visual Coherence Loss for Coherent and Visually Grounded Story Generation
- 2023
-
Ingår i: Proceedings of the Annual Meeting of the Association for Computational Linguistics. - 0736-587X. - 9781959429777
-
Konferensbidrag (refereegranskat)abstract
- Local coherence is essential for text generation models. We identify two important aspects of local coherence within the visual storytelling task: (1) the model needs to represent re-occurrences of characters within the image sequence in order to mention them correctly in the story; (2) character representations should enable us to find instances of the same characters and distinguish different characters. In this paper, we propose a loss function inspired by a linguistic theory of coherence for learning image sequence representations. We further propose combining features from an object detector and a face detector to construct stronger character features. To evaluate visual grounding that current reference-based metrics do not measure, we propose a character matching metric to check whether the models generate referring expressions correctly for characters in input image sequences. Experiments on a visual story generation dataset show that our proposed features and loss function are effective for generating more coherent and visually grounded stories. Our code is available at https://github.com/vwprompt/vcl.
|
|
11098. |
|
|
11099. |
|
|
11100. |
- Hookway, Samantha, 1982, et al.
(författare)
-
AI & Design
- 2019
-
Ingår i: Panel Discussion - Gothenburg Design Festival.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- A two-hours artwork-based conversation moderated by Elena Raviola, Professor of Business Design Lab around AI and design work with invited designers and experts working in the field. This was a panel discussion, held publicly at the Academy of Design and Crafts during 2019 Gothenburg Design Festival. Panelists included Palle Dahlstedt, Studio Alight (Samantha Hookway, Fredrik Garneij & Christofer Kanljung), and Ateljé Schultz Lindberg (Kristina Schultz & Johan Lindberg).
|
|