DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 33

1
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
In: https://hal.archives-ouvertes.fr/hal-01856176 ; 2018 (2018)
BASE
Show details
2
Unsupervised Cross-Lingual Information Retrieval using Monolingual Data Only ...
BASE
Show details
3
Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only ...
Litschko, Robert; Glavas, Goran; Ponzetto, Simone Paolo. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
4
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing ...
BASE
Show details
5
On the Limitations of Unsupervised Bilingual Dictionary Induction ...
BASE
Show details
6
Fully Statistical Neural Belief Tracking ...
Mrkšić, Nikola; Vulić, Ivan. - : arXiv, 2018
BASE
Show details
7
Bio-SimVerb ...
Chiu, Hon Wing; Pyysalo, Sampo; Vulic, Ivan. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
8
Scoring Lexical Entailment with a Supervised Directional Similarity Network ...
BASE
Show details
9
Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization ...
BASE
Show details
10
Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources ...
BASE
Show details
11
Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP ...
Ponti, Edoardo; Reichart, Roi; Korhonen, Anna-Leena. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
12
Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction ...
Gerz, Daniela; Vulić, Ivan; Ponti, Edoardo. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
13
A deep learning approach to bilingual lexicon induction in the biomedical domain ...
Heyman, Geert; Vulić, Ivan; Moens, Marie-Francine. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
14
Injecting Lexical Contrast into Word Vectors by Guiding Vector Space Specialisation ...
Vulic, Ivan; Korhonen, Anna-Leena; Linguist, Assoc Computat. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
15
Investigating the cross-lingual translatability of VerbNet-style classification. ...
Majewska, Olga; Vulić, Ivan; McCarthy, Diana. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
16
Specialising Word Vectors for Lexical Entailment ...
Vulic, Ivan; Mrk�I?, Nikola. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
17
A deep learning approach to bilingual lexicon induction in the biomedical domain. ...
Heyman, Geert; Vulić, Ivan; Moens, Marie-Francine. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
18
Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources ...
Vulic, Ivan; Glavaš, Goran; Mrkšić, Nikola. - : Apollo - University of Cambridge Repository, 2018
BASE
Show details
19
A deep learning approach to bilingual lexicon induction in the biomedical domain.
Heyman, Geert; Vulić, Ivan; Moens, Marie-Francine. - : Springer Science and Business Media LLC, 2018. : BMC Bioinformatics, 2018
BASE
Show details
20
Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction
Gerz, Daniela; Vulić, Ivan; Ponti, Edoardo; Naradowsky, Jason; Reichart, Roi; Korhonen, Anna-Leena. - : MIT Press - Journals, 2018. : Transactions of the Association for Computational Linguistics, 2018
Abstract: Neural architectures are prominent in the construction of language models (LMs). However, word-level prediction is typically agnostic of subword-level information (characters and character sequences) and operates over a closed vocabulary, consisting of a limited word set. Indeed, while subword-aware models boost performance across a variety of NLP tasks, previous work did not evaluate the ability of these models to assist next-word prediction in language modeling tasks. Such subword-level informed models should be particularly effective for morphologically-rich languages (MRLs) that exhibit high type-to-token ratios. In this work, we present a large-scale LM study on 50 typologically diverse languages covering a wide variety of morphological systems, and offer new LM benchmarks to the community, while considering subword-level information. The main technical contribution of our work is a novel method for injecting subword-level information into semantic word vectors, integrated into the neural language modeling training, to facilitate word-level prediction. We conduct experiments in the LM setting where the number of infrequent words is large, and demonstrate strong perplexity gains across our 50 languages, especially for morphologically-rich languages. Our code and data sets are publicly available. ; This work is supported by the ERC Consolidator Grant LEXICAL (648909)
URL: https://www.repository.cam.ac.uk/handle/1810/279936
https://doi.org/10.17863/CAM.27304
BASE
Hide details

Page: 1 2

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
33
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern