A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New models improve morpheme segmentation in low-resource languages.
This research creates and classifies datasets for Setswana and Sepedi news headlines.
Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and languages. In this study, we propose a multilingual neural language model archite…
Study introduces KorFinMTEB for Korean financial texts, revealing model limitations.
We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We use 1920 isolated keywords (40 types, 34 minutes)…
Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…
Unified model for sequence labeling and classification.
Given that South African education is in crisis, strategies for improvement and sustainability of high-quality, up-to-date education must be explored. In the migration of education online, inclusion of machine translation for low-resourced local languages becomes necessary. This paper aims to spur the use of current ne…
Among the six challenges of neural machine translation (NMT) coined by (Koehn and Knowles, 2017), rare-word problem is considered the most severe one, especially in translation of low-resource languages. In this paper, we propose three solutions to address the rare words in neural machine translation systems. First, we…
Paper develops a new unsupervised scoring function for cross-lingual document alignment.
The paper presents a neural machine translation system for Wolof.
Unlike major Western languages, most African languages are very low-resourced. Furthermore, the resources that do exist are often scattered and difficult to obtain and discover. As a result, the data and code for existing research has rarely been shared. This has lead a struggle to reproduce reported results, and few p…
Study shows multilingual LLM calibration effects improve model confidence but not accuracy.
Edge language models show bias over time, especially on resource-constrained devices.
Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels often contain more errors which can deteriorate a classifier's performance when …
End-to-end Sanskrit TTS developed with limited data, achieving good quality.
The quality of neural machine translation can be improved by leveraging additional monolingual resources to create synthetic training data. Source-side monolingual data can be (forward-)translated into the target language for self-training; target-side monolingual data can be back-translated. It has been widely reporte…
Survey on using large models to train smaller datasets in NLP.
Investigates upsampling vs. upweighting for balanced training on skewed datasets.
We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is …
This study compresses BERT to make it suitable for low-capability devices.
To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we explore different task scheduling approaches. We first consider existing non-adapti…
Generative models predict page quality without training, useful for low-resource settings.
Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation. Yet these neural networks are very sensitive to architecture and hyperparameter settings. Optimizing these settings by grid or random search is computationally expensive because it requires many training r…
African languages are numerous, complex and low-resourced. The datasets required for machine translation are difficult to discover, and existing research is hard to reproduce. Minimal attention has been given to machine translation for African languages so there is scant research regarding the problems that arise when …
Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language cues, training a model with a small set of labeled datasets is still a challeng…
Physics-inspired methods optimize SVD compression of LLMs.
Multi-language speech datasets are scarce and often have small sample sizes in the medical domain. Robust transfer of linguistic features across languages could improve rates of early diagnosis and therapy for speakers of low-resource languages when detecting health conditions from speech. We utilize out-of-domain, unp…
This study improves the performance of neural named entity recognition by a margin of up to 11% in F-score on the example of a low-resource language like German, thereby outperforming existing baselines and establishing a new state-of-the-art on each single open-source dataset. Rather than designing deeper and wider hy…
GP-TS optimizes TLM pre-training hyperparameters efficiently.
Optimus pre-trains sentences in a latent space for various NLP tasks.
We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts improved translation quality. The resulting system significantly outperformed a linguis…
FinGPT is an open-source financial LLM for democratizing financial data.
Develops a cross-lingual hate speech detection model using pre-trained Transformers.
Introduces challenges and techniques for creating machine translation for indigenous languages.
In this paper, we introduce an approach for leveraging available data across multiple locales sharing the same language to 1) improve domain classification model accuracy in Spoken Language Understanding and user experience even if new locales do not have sufficient data and 2) reduce the cost of scaling the domain cla…
Paper benchmarks Bengali language classification tasks using MConv-LSTM network.
Introduces MLM dataset for multitask learning across multiple languages and modalities.
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this work, we revisit adversarial autoe…
NukeBERT improves performance on nuclear domain Q&A with less training data.
We compare features for dynamic time warping (DTW) when used to bootstrap keyword spotting (KWS) in an almost zero-resource setting. Such quickly-deployable systems aim to support United Nations (UN) humanitarian relief efforts in parts of Africa with severely under-resourced languages. Our objective is to identify aco…
Natural Language Processing (NLP) and especially natural language text analysis have seen great advances in recent times. Usage of deep learning in text processing has revolutionized the techniques for text processing and achieved remarkable results. Different deep learning architectures like CNN, LSTM, and very recent…
Optimizes query routing to LLMs under cost and resource constraints.
IMPACT optimizes LLM compression by focusing on activation importance, reducing model size up to 55.4%.
Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint of these large LMs makes them difficult to deploy in many scenarios (e.g. on mobi…
ATD measures language distance using neural models, recovering linguistic groupings.
User interaction with voice-powered agents generates large amounts of unlabeled utterances. In this paper, we explore techniques to efficiently transfer the knowledge from these unlabeled utterances to improve model performance on Spoken Language Understanding (SLU) tasks. We use Embeddings from Language Model (ELMo) t…
Review of efficient neural networks for TinyML on resource-constrained devices.