Topic
Word embedding
About: Word embedding is a research topic. Over the lifetime, 4683 publications have been published within this topic receiving 153378 citations. The topic is also known as: word embeddings.
Papers
More filters
TL;DR: This paper aims to use capsule neural networks in the fake news detection task, using different embedding models for news items of different lengths and outperforming the state-of-the-art methods on ISOT and LIAR.
74 citations
TL;DR: This work introduces the largest, reproducible and detailed experimental survey of OM measures and THE AUTHORS models reported in the literature, based on the evaluation of both families of methods on a same software platform, with the aim of elucidating what is the state of the problem.
74 citations
01 Oct 2016
TL;DR: A word spotting system based on convolutional neural networks that outperforms the previous state-of-the-art for word spotting on standard datasets and can perform word spotting using both query- by-string and query-by-example in a variety of word embedding spaces.
Abstract: In the last few years, deep convolutional neural networks have become ubiquitous in computer vision, achieving state-of-the-art results on problems like object detection, semantic segmentation, and image captioning. However, they have not yet been widely investigated in the document analysis community. In this paper, we present a word spotting system based on convolutional neural networks. We train a network to extract a powerful image representation, which we then embed into a word embedding space. This allows us to perform word spotting using both query-by-string and query-by-example in a variety of word embedding spaces, both learned and handcrafted, for verbatim as well as semantic word spotting. Our novel approach is versatile and the evaluation shows that it outperforms the previous state-of-the-art for word spotting on standard datasets.
74 citations
Posted Content•
TL;DR: This paper proposes to contextualize the word embedding vectors using a nonlinear bag-of-words representation of the source sentence and proposes to represent special tokens with typed symbols to facilitate translating those words that are not well-suited to be translated via continuous vectors.
Abstract: We first observe a potential weakness of continuous vector representations of symbols in neural machine translation. That is, the continuous vector representation, or a word embedding vector, of a symbol encodes multiple dimensions of similarity, equivalent to encoding more than one meaning of the word. This has the consequence that the encoder and decoder recurrent networks in neural machine translation need to spend substantial amount of their capacity in disambiguating source and target words based on the context which is defined by a source sentence. Based on this observation, in this paper we propose to contextualize the word embedding vectors using a nonlinear bag-of-words representation of the source sentence. Additionally, we propose to represent special tokens (such as numbers, proper nouns and acronyms) with typed symbols to facilitate translating those words that are not well-suited to be translated via continuous vectors. The experiments on En-Fr and En-De reveal that the proposed approaches of contextualization and symbolization improves the translation quality of neural machine translation systems significantly.
72 citations
TL;DR: This work offers an automatic exploring words and characters level features approach: a recurrent neural network using bidirectional long short-term memory (L STM) with Conditional Random Fields decoding (LSTM-CRF), which outperforms the best system in the DDI2013 challenge.
Abstract: Drug-Named Entity Recognition (DNER) for biomedical literature is a fundamental facilitator of Information Extraction. For this reason, the DDIExtraction2011 (DDI2011) and DDIExtraction2013 (DDI2013) challenge introduced one task aiming at recognition of drug names. State-of-the-art DNER approaches heavily rely on hand-engineered features and domain-specific knowledge which are difficult to collect and define. Therefore, we offer an automatic exploring words and characters level features approach: a recurrent neural network using bidirectional long short-term memory (LSTM) with Conditional Random Fields decoding (LSTM-CRF). Two kinds of word representations are used in this work: word embedding, which is trained from a large amount of text, and character-based representation, which can capture orthographic feature of words. Experimental results on the DDI2011 and DDI2013 dataset show the effect of the proposed LSTM-CRF method. Our method outperforms the best system in the DDI2013 challenge.
72 citations