DE eng

Search in the Catalogues and Directories

Hits 1 – 16 of 16

1
Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement
Miyao, Yusuke; Poerner, Nina; Roth, Benjamin. - : Ludwig-Maximilians-Universität München, 2018
BASE
Show details
2
Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing
Yaghoobzadeh, Yadollah; Schütze, Hinrich; Riloff, Ellen. - : Ludwig-Maximilians-Universität München, 2018
BASE
Show details
3
Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms
In: Transactions of the Association for Computational Linguistics (2018)
BASE
Show details
4
A Stronger Baseline for Multilingual Word Embeddings
BASE
Show details
5
Embedding Learning Through Multilingual Concept Induction
Fraser, Alexander; Zhao, Mengjie; Dufter, Philipp. - : Ludwig-Maximilians-Universität München, 2018
BASE
Show details
6
Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs
Isabelle, Pierre; Bender, Emily M.; Schütze, Hinrich. - : Ludwig-Maximilians-Universität München, 2018
BASE
Show details
7
Embedding Learning Through Multilingual Concept Induction ...
BASE
Show details
8
Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging ...
BASE
Show details
9
Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages ...
BASE
Show details
10
Multilingual Embeddings Jointly Induced from Contexts and Concepts: Simple, Strong and Scalable ...
BASE
Show details
11
Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing ...
BASE
Show details
12
A Stronger Baseline for Multilingual Word Embeddings ...
Dufter, Philipp; Schütze, Hinrich. - : Universitätsbibliothek der Ludwig-Maximilians-Universität München, 2018
Abstract: Levy, Søgaard and Goldberg’s (2017) S-ID (sentence ID) method applies word2vec on tuples containing a sentence ID and a word from the sentence. It has been shown to be a strong baseline for learning multilingual embeddings. Inspired by recent work on concept based embedding learning we propose SC-ID, an extension to S-ID: given a sentence aligned corpus, we use sampling to extract concepts that are then processed in the same manner as S-IDs. We perform experiments on the Parallel Bible Corpus across 1000+ languages and show that SC-ID yields up to 6% performance increase in a word translation task. In ad- dition, we provide evidence that SC-ID is easily and widely applicable by reporting competitive results across 8 tasks on a EuroParl based corpus. ...
Keyword: 000; 004; 400; 410
URL: https://epub.ub.uni-muenchen.de/id/eprint/61864
https://dx.doi.org/10.5282/ubm/epub.61864
BASE
Hide details
13
Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing ...
Yaghoobzadeh, Yadollah; Schütze, Hinrich. - : Universitätsbibliothek der Ludwig-Maximilians-Universität München, 2018
BASE
Show details
14
Embedding Learning Through Multilingual Concept Induction ...
Dufter, Philipp; Zhao, Mengjie; Schmitt, Martin. - : Universitätsbibliothek der Ludwig-Maximilians-Universität München, 2018
BASE
Show details
15
Replicated Siamese LSTM in Ticketing System for Similarity Learning and Retrieval in Asymmetric Texts ...
BASE
Show details
16
Joint Bootstrapping Machines for High Confidence Relation Extraction ...
BASE
Show details

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
16
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern