Xiaoyu Shen, Akari Asai, Bill Byrne, Adria De Gispert. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track). 2023.
There are a number of techniques that can be used in Adobe Illustrator to add depth to your work. Is Illustrator an application like Photoshop with tons of tools designed to go to 3D software? No, not at all, but there are plenty of uses that we will discuss throughout this book. First, Illustrator allows us to quickly outline text, which allows us a great deal of creative control of our type. Second, the vector line art can jump from Illustrator to a 3D host quickly and painlessly.
The process of creating 3D objects is called modeling. In 2D digital art, we have the option either to take a photograph or to draw the object needed. With a 3D object we have to do a few more things. Before we can concern ourselves with the texture of an object, we have to define its shape. So in order to define a shape, we start by working with what are called primitives.
In conversational QA, models have to leverage information in previous turns to answer upcoming questions. Current approaches, such as Question Rewriting, struggle to extract relevant information as the conversation unwinds. We introduce the Common Ground (CG), an approach to accumulate conversational information as it emerges and select the relevant information at every turn. We show that CG offers a more efficient and human-like way to exploit conversational information compared to existing approaches, leading to improvements on Open Domain Conversational QA.
Neural Machine Translation (NMT) on logographic source languages struggles when translating `unseen' characters, which never appear in the training data. One possible approach to this problem uses sub-character decomposition for training and test sentences. However, this approach involves complete retraining, and its effectiveness for unseen character translation to non-logographic languages has not been fully explored. We investigate existing ideograph-based sub-character decomposition approaches for Chinese-to-English and Japanese-to-English NMT, for both high-resource and low-resource domains. For each language pair and domain we construct a test set where all source sentences contain at least one unseen logographic character. We find that complete sub-character decomposition often harms unseen character translation, and gives inconsistent results generally. We offer a simple alternative based on decomposition before inference for unseen characters only. Our approach allows flexible application, achieving translation adequacy improvements and requiring no additional models or training.