Results 1 - 10
of
10
STATISTICAL LANGUAGE MODELS BASED ON NEURAL NETWORKS
, 2012
"... Statistical language models are crucial part of many successful applications, such as automatic speech recognition and statistical machine translation (for example well-known ..."
Abstract
-
Cited by 49 (6 self)
- Add to MetaCart
Statistical language models are crucial part of many successful applications, such as automatic speech recognition and statistical machine translation (for example well-known
Learning Structured Embeddings of Knowledge Bases
"... Many Knowledge Bases (KBs) are now readily available and encompass colossal quantities of information thanks to either a long-term funding effort (e.g. WordNet, OpenCyc) or a collaborative process (e.g. Freebase, DBpedia). However, each of them is based on a different rigorous symbolic framework whi ..."
Abstract
-
Cited by 40 (4 self)
- Add to MetaCart
Many Knowledge Bases (KBs) are now readily available and encompass colossal quantities of information thanks to either a long-term funding effort (e.g. WordNet, OpenCyc) or a collaborative process (e.g. Freebase, DBpedia). However, each of them is based on a different rigorous symbolic framework which makes it hard to use their data in other systems. It is unfortunate because such rich structured knowledge might lead to a huge leap forward in many other areas of AI like natural language processing (word-sense disambiguation, natural language understanding,...), vision (scene classification, image semantic annotation,...) or collaborative filtering. In this paper, we present a learning process based on an innovative neural network architecture designed to embed any of these symbolic representations into a more flexible continuous vector space in which the original knowledge is kept and enhanced. These learnt embeddings would allow data from any KB to be easily used in recent machine learning methods for prediction and information retrieval. We illustrate our method on WordNet and Freebase and also present a way to adapt it to knowledge extraction from raw text.
Memory networks.
- In International Conference on Learning Representations (ICLR),
, 2015
"... Abstract We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network ..."
Abstract
-
Cited by 9 (1 self)
- Add to MetaCart
(Show Context)
Abstract We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network
Phrase based English – Tamil Translation System by Concept Labeling using Translation Memory
"... In this paper, we present a novel framework for phrase based translation system using translation memory by concept labeling. The concepts are labeled on the input text, followed by the conversion of text into phrases. The phrase is searched throughout the translation memory, where the parallel corp ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
In this paper, we present a novel framework for phrase based translation system using translation memory by concept labeling. The concepts are labeled on the input text, followed by the conversion of text into phrases. The phrase is searched throughout the translation memory, where the parallel corpus is stored. The translation memory displays all source and target phrases, wherever the input phrase is present in them. Target phrase corresponding to the output source phrase having the same concept as that of input source phrase, is chosen as the best translated phrase. The system is implemented for English to Tamil translation.
Noname manuscript No. (will be inserted by the editor) Interactive Relational Reinforcement Learning of Concept Semantics
"... the date of receipt and acceptance should be inserted later Abstract We present a framework for the machine learning of denotational concept semantics using a simple form of symbolic interaction of machines with human users. The capability of software agents and robots to learn how to communicate ve ..."
Abstract
- Add to MetaCart
(Show Context)
the date of receipt and acceptance should be inserted later Abstract We present a framework for the machine learning of denotational concept semantics using a simple form of symbolic interaction of machines with human users. The capability of software agents and robots to learn how to communicate verbally with human users would obviously be highly useful in several real-world applications, and our framework is meant to provide a further step towards this goal. Whereas the large majority of existing approaches to the machine learning of word sense and other language aspects focuses on learning using text corpora, our framework allows for the interactive learning of concepts in a dialog of human and agent, using an approach in the area of Relational Reinforcement Learning. Such an approach has a wide range of possible applications, e.g., the interactive acquisition of semantic categories for the Semantic Web, Human-Computer Interaction, (interactive)
Light Textual Inference for Semantic Parsing K yle Richardson
"... There has been a lot of recent interest in Semantic Parsing, centering on using data-driven techniques for mapping natural language to full semantic representations (Mooney, 2007). One particular focus has been on learning with ambiguous supervision (Chen and Mooney, 2008; Kim and Mooney, 2012), whe ..."
Abstract
- Add to MetaCart
(Show Context)
There has been a lot of recent interest in Semantic Parsing, centering on using data-driven techniques for mapping natural language to full semantic representations (Mooney, 2007). One particular focus has been on learning with ambiguous supervision (Chen and Mooney, 2008; Kim and Mooney, 2012), where the goal is to model language learning within broader perceptual contexts (Mooney, 2008). We look at learning light inference patterns for Semantic Parsing within this paradigm, focusing on detecting speaker commitments about events under discussion (Nairn et al., 2006; Karttunen, 2012). We adapt PCFG induction techniques (Börschinger et al., 2011; Johnson et al., 2012) for learning inference using event polarity and context as supervision, and demonstrate the effectiveness of our approach on a modified portion of the Grounded World corpus (Bordes et al., 2010).
In Language and Information Technologies
, 2012
"... Automated understanding of natural language is a challenging problem, which has remained open for decades. We have investigated its special case, focused on identifying relevant concepts in natural-language text in the context of a specific given task. We have developed a set of general-purpose lang ..."
Abstract
- Add to MetaCart
Automated understanding of natural language is a challenging problem, which has remained open for decades. We have investigated its special case, focused on identifying relevant concepts in natural-language text in the context of a specific given task. We have developed a set of general-purpose language interpretation techniques and applied them to the task of detecting malicious websites by analyzing comments of website visitors. In this context, concepts are related to behavior or contents of websites, such as presence of pop-ups and false testimonials. The developed algorithms are based on probabilistic topic models and other dimensionality reduction techniques applied to a special case of multi-label text classification, where concepts are output labels. We integrate information about the target task with other relevant information, including relations among concepts and external knowledge sources using a concept graph. The system iterates between training a topic model on the partially labeled data and optimizing the parameters and the label assignments. We analyze several alternative versions of this mechanism, such as one that measures the quality of separation among topics and eliminates words that are not discriminative. For the task of detecting malicious websites, we have developed an approach that applies
Revisiting knowledge-based Semantic Role Labeling
"... Semantic role labeling has seen tremendous progress in the last years, both for supervised and unsupervised approaches. The knowledge-based approaches have been neglected while they have shown to bring the best results to the related word sense disambiguation task. We contribute a simple knowledge-b ..."
Abstract
- Add to MetaCart
(Show Context)
Semantic role labeling has seen tremendous progress in the last years, both for supervised and unsupervised approaches. The knowledge-based approaches have been neglected while they have shown to bring the best results to the related word sense disambiguation task. We contribute a simple knowledge-based system with an easy to reproduce specification. We also present a novel approach to handle the passive voice in the context of semantic role labeling that reduces the error rate in F1 by 15.7%, showing that significant improvements can be brought while retaining the key advantages of the approach: a simple approach which facilitates analysis of individual errors, does not need any hand-annotated corpora and which is not domain-specific.
Heudiasyc UMR CNRS 6599
"... Many Knowledge Bases (KBs) are now readily available and encompass colossal quantities of information thanks to either a long-term funding effort (e.g. WordNet, OpenCyc) or a col-laborative process (e.g. Freebase, DBpedia). However, each of them is based on a different rigid symbolic framework which ..."
Abstract
- Add to MetaCart
Many Knowledge Bases (KBs) are now readily available and encompass colossal quantities of information thanks to either a long-term funding effort (e.g. WordNet, OpenCyc) or a col-laborative process (e.g. Freebase, DBpedia). However, each of them is based on a different rigid symbolic framework which makes it hard to use their data in other systems. It is unfortunate because such rich structured knowledge might lead to a huge leap forward in many other areas of AI like nat-ural language processing (word-sense disambiguation, natu-ral language understanding,...), vision (scene classification, image semantic annotation,...) or collaborative filtering. In this paper, we present a learning process based on an inno-vative neural network architecture designed to embed any of these symbolic representations into a more flexible continu-ous vector space in which the original knowledge is kept and enhanced. These learnt embeddings would allow data from any KB to be easily used in recent machine learning meth-ods for prediction and information retrieval. We illustrate our method on WordNet and Freebase and also present a way to adapt it to knowledge extraction from raw text.
