Pith. sign in

REVIEW 1 cited by

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.06268 v1 pith:J6CEA5MR submitted 2021-04-13 cs.CL cs.LGeess.AS

classification cs.CLcs.LGeess.AS
keywords learningmodelcode-switchingdatalanguageslinguisticmonolingualmulti-task
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information is judiciously extracted from high-resource monolingual speech data to the code-switching domain. The meta-transfer learning quickly adapts the model to the code-switching task from a number of monolingual tasks by learning to learn in a multi-task learning fashion. Second, we propose a novel multilingual meta-embeddings approach to effectively represent code-switching data by acquiring useful knowledge learned in other languages, learning the commonalities of closely related languages and leveraging lexical composition. The method is far more efficient compared to contextualized pre-trained multilingual models. Third, we introduce multi-task learning to integrate syntactic information as a transfer learning strategy to a language model and learn where to code-switch. To further alleviate the aforementioned issues, we propose a data augmentation method using Pointer-Gen, a neural network using a copy mechanism to teach the model the code-switch points from monolingual parallel sentences. We disentangle the need for linguistic theory, and the model captures code-switching points by attending to input words and aligning the parallel words, without requiring any word alignments or constituency parsers. More importantly, the model can be effectively used for languages that are syntactically different, and it outperforms the linguistic theory-based models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset

    cs.CL 2025-01 conditional novelty 4.0 of 10

    On a roughly 11-million-token Sepedi corpus, standard autoregressive pre-training gives lower validation loss and perplexity, while occlusion-based pre-training gives a slightly higher BLEU score on generated text.

Pith tools