Plastics recycling is a critical ecological and economic solution to manage plastic waste, yet a staggering proportion of plastics from daily use is landfilled or incinerated. A critical step to recycling plastics is our ability to sort plastics by type (HDPE, LDPE, PET, PP, PS, and PVC) at a mixed recycling facility. However, challenges such as sensor system cost, difficulty in data collection, and the dense sampling required for model fine-tuning continue to hinder reliable large-scale deployment and limit progress toward a sustainable circular plastic economy. In this work, we propose a novel physics-informed plastics classification system based on active thermal imaging. Additionally, we present a two-stage training strategy that uses a large quantity of easily generated PDE-based simulated samples for pretraining and fine-tunes the model to real-world data distributions using only a sparse set of samples. We validate the efficacy of the proposed approach on real-world plastic samples. Thus, we introduce Thermal Imaging based Plastic Sorting (TIPS), a system that achieves up to 100% and 94.7% accuracy in plastic type classification for black and white plastics, respectively.

Meng Chen, Philip Arthur, Qianyu Feng, Cong Duy Vu Hoang, Yu-Heng Hong, Mahdi Kazemi Moghaddam, Omid Nezami, Duc Thien Nguyen, Gioacchino Tangari, Duy Vu, Thanh Vu, Mark Johnson, Krishnaram Kenthapadi, Don Dharmasiri, Long Duong, Yuan-Fang Li. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Extending semantic parsing systems to new domains and languages is a highly expensive, time-consuming process, so making effective use of existing resources is critical.In this paper, we describe a transfer learning method using crosslingual word embeddings in a sequence-tosequence model.On the NLmaps corpus, our approach achieves state-of-the-art accuracy of 85.7% for English.Most importantly, we observed a consistent improvement for German compared with several baseline domain adaptation techniques.As a by-product of this approach, our models that are trained on a combination of English and German utterances perform reasonably well on codeswitching utterances which contain a mixture of English and German, even though the training data does not contain any code-switching.As far as we know, this is the first study of code-switching in semantic parsing.We manually constructed the set of code-switching test utterances for the NLmaps corpus and achieve 78.3% accuracy on this dataset.

Long Duong, Hiroshi Kanayama, Tengfei Ma, Steven Bird, Trevor Cohn. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017.

For many low-resource languages, spoken language resources are more likely to be annotated with translations than with transcriptions. Translated speech data is potentially valuable for documenting endangered languages or for training speech translation systems. A first step towards making use of such data would be to automatically align spoken words with their translations. We present a model that combines Dyer et al.'s reparameterization of IBM Model 2 (fast-align) and k-means clustering using Dynamic Time Warping as a distance metric. The two components are trained jointly using expectation-maximization. In an extremely low-resource scenario, our model performs significantly better than both a neural model and a strong baseline.

Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual data or were unable to handle polysemy. We address these drawbacks in our method which takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages. Our model achieves state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive results on the monolingual word similarity and cross-lingual document classification task.

Long Duong, Antonios Anastasopoulos, David Chiang, Steven Bird, Trevor Cohn. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

Cross-lingual transfer has been shown to produce good results for dependency parsing of resource-poor languages.Although this avoids the need for a target language treebank, most approaches have still used large parallel corpora.However, parallel data is scarce for low-resource languages, and we report a new method that does not need parallel data.Our method learns syntactic word embeddings that generalise over the syntactic contexts of a bilingual vocabulary, and incorporates these into a neural network parser.We show empirical improvements over a baseline delexicalised parser on both the CoNLL and Universal Dependency Treebank datasets.We analyse the importance of the source languages, and show that combining multiple source-languages leads to a substantial improvement.

Accurate dependency parsing requires large treebanks, which are only available for a few languages. We propose a method that takes advantage of shared structure across languages to build a mature parser using less training data. We propose a model for learning a shared “univer-sal ” parser that operates over an inter-lingual continuous representation of lan-guage, along with language-specific map-ping components. Compared with super-vised learning, our methods give a con-sistent 8-10 % improvement across several treebanks in low-resource simulations. 1

by stating that they required an external tag dictionary.We have corrected these inaccuracies to reflect their modest data requirements.