Katharina Kann

Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge

2020 · arXiv (Cornell University)

How does knowledge of one language's morphology influence learning of inflection rules in a second one? In order to investigate this question in artificial neural network models, we perform experiments with a sequence-to-sequence architecture, which …

Tackling the Low-resource Challenge for Canonical Segmentation

2020

Canonical morphological segmentation consists of dividing words into their standardized morphemes. Here, we are interested in approaches for the task when training data is limited. We compare model performance in a simulated low-resource setting for …

BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Morphologically-rich polysynthetic languages present a challenge for NLP systems due to data sparsity, and a common strategy to handle this issue is to apply subword segmentation. We investigate a wide variety of supervised and unsupervised …

Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems

2022 · arXiv (Cornell University)

Many dialogue systems (DSs) lack characteristics humans have, such as emotion perception, factuality, and informativeness. Enhancing DSs with knowledge alleviates this problem, but, as many ways of doing so exist, keeping track of all proposed …

Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers

2023

In recent years machine translation has become very successful for high-resource language pairs. This has also sparked new interest in research on the automatic translation of low-resource languages, including Indigenous languages. However, the latter are …

Comparative Study of CNN and RNN for Natural Language Processing

2017 · arXiv (Cornell University)

Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP). Convolutional neural network (CNN) and recurrent neural network (RNN), the two main types of DNN architectures, are widely explored to handle various …

Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!

2018

Motivated by recent findings on the probabilistic modeling of acceptability judgments, we propose syntactic log-odds ratio (SLOR), a normalized language model score, as a metric for referenceless fluency evaluation of natural language generation output at …

Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?

2020 · arXiv (Cornell University)

While pretrained models such as BERT have shown large gains across natural language understanding tasks, their performance can be improved by further training the model on a data-rich intermediate task, before fine-tuning it on a …

Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?

2020

Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut, Xiaoyi Zhang, Richard Yuanzhe Pang, Clara Vania, Katharina Kann, Samuel R. Bowman. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.