Көптілді деректер
Related Papers
The GIVE-2 Corpus of Giving Instructions in Virtual Environments
AbstractWe present the GIVE-2 Corpus, a new corpus of human instruction giving. The corpus was collected by asking one person in each pair of subjects to guide the other person …...
A Hierarchical Dirichlet Process Model for Joint Part-of-Speech and Morphology Induction
In this paper we present a fully unsupervised nonparametric Bayesian model that jointly in- duces POS tags and morphological segmen- tations. The model is essentially an infi- nite HMM that …...
Semi Supervised Preposition-Sense Disambiguation using Multilingual Data
AbstractPrepositions are very common and very ambiguous, and understanding their sense is critical for understanding the meaning of the sentence. Supervised corpora for the preposition-sense disambiguation task are small, suggesting …...
Typology of Adjectives Benchmark for Compositional Distributional Models
AbstractIn this paper we present a novel application of compositional distributional semantic models (CDSMs): prediction of lexical typology. The paper introduces the notion of typological closeness, which is a novel …...
Preparation and Usage of Xhosa Lexicographical Data for a Multilingual, Federated Environment
The South African linguistic landscape is characterised by multilingualism and the influence between their eleven official and some local languages. Unfortunately, for most of the languages the amount and quality …...
Cross-Lingual Knowledge Transfer for Clinical Phenotyping
AbstractClinical phenotyping enables the automatic extraction of clinical conditions from patient records, which can be beneficial to doctors and clinics worldwide. However, current state-of-the-art models are mostly applicable to clinical …...
Wiktextract: Wiktionary as Machine-Readable Structured Data
AbstractWe present a machine-readable structured data version of Wiktionary. Unlike previous Wiktionary extractions, the new extractor, Wiktextract, fully interprets and expands templates and Lua modules in Wiktionary. This enables it …...
Improving Low-Resource Speech Recognition through Multilingual Fine-Tuning with Language Identifiers and Self-Training
Previous work has demonstrated that multilin- gual fine-tuning of a pretrained multilingual speech representation model can lead to im- proved speech recognition accuracy when there is extremely little target language …...