Results 101 to 110 of about 145,637 (201)

The Dissecting Power of Regular Languages [PDF]

open access: yesInformation Processing Letters, Vol.113, pp.116-122, 2013, 2012
A recent study on structural properties of regular and context-free languages has greatly promoted our basic understandings of the complex behaviors of those languages. We continue the study to examine how regular languages behave when they need to cut numerous infinite languages.
arxiv  

Hernán Núñez (1555) e Gonzalo de Correas (1627): os primeiros refraneiros galegos [PDF]

open access: yesCadernos de Fraseoloxía Galega, 2004
En 1555 publicouse en Salamanca Refranes o Proverbios en Romance, obra póstuma de Hernán Núñez de Toledo y Guzmán (1475-1553), voluminoso traballo no que se documentan 8.557 formas sentenciosas, das cales 134 son galegas.
Germán Conde Tarrío
doaj  

Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens [PDF]

open access: yesarXiv
While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the pre-training data.
arxiv  

Language Report Galician [PDF]

open access: hybrid, 2023
José Manuel Ramírez Sánchez   +2 more
openalex   +1 more source

Truth Knows No Language: Evaluating Truthfulness Beyond English [PDF]

open access: yesarXiv
We introduce a professionally translated extension of the TruthfulQA benchmark designed to evaluate truthfulness in Basque, Catalan, Galician, and Spanish. Truthfulness evaluations of large language models (LLMs) have primarily been conducted in English. However, the ability of LLMs to maintain truthfulness across languages remains under-explored.
arxiv  

Home - About - Disclaimer - Privacy