More Like this

1. Cross-linguistic semantic annotation: reconciling the language-specific and the universal

   https://doi.org/10.18653/v1/W19-3301  

   Van Gysel, Jens E.; Vigus, Meagan; Kalm, Pavlína; Lee, Sook-kyung; Regan, Michael; Croft, William (January 2019, Proceedings of the First International Workshop on Designing Meaning Representations (DMR 2019))

   Xue, Nianwen; Croft, William; Hajic, Jan; Huang, Chu-Ren; Oepen, Stephan; Palmer, Martha; Pustejovsky, James (Ed.)

   Developers of cross-lingual semantic annotation schemes face a number of issues not encountered in monolingual annotation. This paper discusses four such issues, related to the establishment of annotation labels, and the treatment of languages with more fine-grained, more coarse-grained, and cross-cutting categories. We propose that a lattice-like architecture of the annotation categories can adequately handle all four issues, and at the same time remain both intuitive for annotators and faithful to typological insights. This position is supported by a brief annotation experiment. 

   more » « less
2. Synthetic Data Augmentation for Improving Low-Resource ASR

   https://doi.org/10.1109/WNYIPW.2019.8923082  

   Thai, Bao; Jimerson, Robert; Arcoraci, Dominic; Prud'hommeaux, Emily; Ptucha, Raymond (October 2019, 2019 IEEE Western New York Image and Signal Processing Workshop (WNYISPW))

   Although the application of deep learning to automatic speech recognition (ASR) has resulted in dramatic reductions in word error rate for languages with abundant training data, ASR for languages with few resources has yet to benefit from deep learning to the same extent. In this paper, we investigate various methods of acoustic modeling and data augmentation with the goal of improving the accuracy of a deep learning ASR framework for a low-resource language with a high baseline word error rate. We compare several methods of generating synthetic acoustic training data via voice transformation and signal distortion, and we explore several strategies for integrating this data into the acoustic training pipeline. We evaluate our methods on an indigenous language of North America with minimal training resources. We show that training initially via transfer learning from an existing high-resource language acoustic model, refining weights using a heavily concentrated synthetic dataset, and finally fine-tuning to the target language using limited synthetic data reduces WER by 15% over just transfer learning using deep recurrent methods. Further, we show improvements over traditional frameworks by 19% using a similar multistage training with deep convolutional approaches. 

   more » « less
3. Expanding Universal Dependencies for Polysynthetic Languages: A Case of St. Lawrence Island Yupik

   https://doi.org/10.18653/v1/2021.americasnlp-1.14  

   Park, Hyunji; Schwartz, Lane; Tyers, Francis (June 2021, Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas)

   null (Ed.)

   This paper describes the development of the first Universal Dependencies (UD) treebank for St. Lawrence Island Yupik, an endangered language spoken in the Bering Strait region. While the UD guidelines provided a general framework for our annotations, language-specific decisions were made necessary by the rich morphology of the polysynthetic language. Most notably, we annotated a corpus at the morpheme level as well as the word level. The morpheme level annotation was conducted using an existing morphological analyzer and manual disambiguation. By comparing the two resulting annotation schemes, we argue that morpheme-level annotation is essential for polysynthetic languages like St. Lawrence Island Yupik. Word-level annotation results in degenerate trees for some Yupik sentences and often fails to capture syntactic relations that can be manifested at the morpheme level. Dependency parsing experiments provide further support for morpheme-level annotation. Implications for UD annotation of other polysynthetic languages are discussed. 

   more » « less
4. Multilingual acoustic word embedding models for processing zero-resource languages

   Kamper, Herman; Matusevych, Yevgen; Goldwater, Sharon (April 2020, Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing)

   Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing and discovery systems. Here we propose to train a single supervised embedding model on labelled data from multiple well-resourced languages and then apply it to unseen zero-resource languages. For this transfer learning approach, we consider two multilingual recurrent neural network models: a discriminative classifier trained on the joint vocabularies of all training languages, and a correspondence autoencoder trained to reconstruct word pairs. We test these using a word discrimination task on six target zero-resource languages. When trained on seven well-resourced languages, both models perform similarly and outperform unsupervised models trained on the zero-resource languages. With just a single training language, the second model works better, but performance depends more on the particular training--testing language pair. 

   more » « less
5. Choosing Transfer Languages for Cross-Lingual Learning

   Lin, Yu-Hsiang; Chen, Chian-Yu; Lee, Jean; Li, Zirui; Zhang, Yuyan; Xia, Mengzhou; Rijhwani, Shruti; He, Junxian; Zhang, Zhisong; Ma, Xuezhe; et al (July 2019, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics)

   Cross-lingual transfer, where a high-resource transfer language is used to improve the accuracy of a low-resource task language, is now an invaluable tool for improving performance of natural language processing (NLP) on lowresource languages. However, given a particular task language, it is not clear which language to transfer from, and the standard strategy is to select languages based on ad hoc criteria, usually the intuition of the experimenter. Since a large number of features contribute to the success of cross-lingual transfer (including phylogenetic similarity, typological properties, lexical overlap, or size of available data), even the most enlightened experimenter rarely considers all these factors for the particular task at hand. In this paper, we consider this task of automatically selecting optimal transfer languages as a ranking problem, and build models that consider the aforementioned features to perform this prediction. In experiments on representative NLP tasks, we demonstrate that our model predicts good transfer languages much better than ad hoc baselines considering single features in isolation, and glean insights on what features are most informative for each different NLP tasks, which may inform future ad hoc selection even without use of our method. 

   more » « less