Code-mixing on sesame street: Dawn of the adversarial polyglots

S Tan, S Joty - arXiv preprint arXiv:2103.09593, 2021 - arxiv.org
Multilingual models have demonstrated impressive cross-lingual transfer performance.
However, test sets like XNLI are monolingual at the example level. In multilingual …

Leveraging bilingual-view parallel translation for code-switched emotion detection with adversarial dual-channel encoder

X Zhu, Y Lou, H Deng, D Ji - Knowledge-based systems, 2022 - Elsevier
Code-switched emotion detection, a task analyzing the emotion in code-switched texts, has
gain increasing research attention within recent years. Prior works utilize various neural …

Optimizing alignment of speech and language latent spaces for end-to-end speech recognition and understanding

W Wang, S Ren, Y Qian, S Liu, Y Shi… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
The advances in attention-based encoder-decoder (AED) networks have brought great
progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further …

Advances and challenges in unsupervised neural machine translation

R Wang, H Zhao - Proceedings of the 16th Conference of the …, 2021 - aclanthology.org
Unsupervised cross-lingual language representation initialization methods, together with
mechanisms such as denoising and back-translation, have advanced unsupervised neural …

niksss at HinglishEval: Language-agnostic BERT-based Contextual Embeddings with Catboost for Quality Evaluation of the Low-Resource Synthetically Generated …

N Singh - arXiv preprint arXiv:2206.08910, 2022 - arxiv.org
This paper describes the system description for the HinglishEval challenge at INLG 2022.
The goal of this task was to investigate the factors influencing the quality of the code-mixed …

Linguistically-Inclusive Natural Language Processing

TMR Samson - 2022 - search.proquest.com
Abstract Language is a largely social construct, shaped by each community's lived
experiences, culture, and language repertoire. However, current natural language …