Results 21 to 30 of about 5,397 (57)
Text-based Adventures of the Golovin AI Agent
, 2017 The domain of text-based adventure games has been recently established as a new challenge of creating the agent that is both able to understand natural language, and acts intelligently in text-described environments.
Kostka, Bartosz +3 more
core +1 more source
An end-to-end convolutional selective autoencoder approach to Soybean Cyst Nematode eggs detection [PDF]
, 2016 This paper proposes a novel selective autoencoder approach within the framework of deep convolutional networks. The crux of the idea is to train a deep convolutional autoencoder to suppress undesired parts of an image frame while allowing the desired ...
Akintayo, Adedotun +12 more
core +3 more sources
Analysing Errors of Open Information Extraction Systems
, 2017 We report results on benchmarking Open Information Extraction (OIE) systems using RelVis, a toolkit for benchmarking Open Information Extraction systems.
Gers, Felix A. +4 more
core +1 more source
Using Multi-Sense Vector Embeddings for Reverse Dictionaries [PDF]
, 2019 Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings instead provide different vectors for each sense of a word.
de Melo, G. +3 more
core +1 more source
Towards a query language for annotation graphs [PDF]
, 2000 The multidimensional, heterogeneous, and temporal nature of speech databases raises interesting challenges for representation and query. Recently, annotation graphs have been proposed as a general-purpose representational framework for speech databases ...
Bird, Steven +2 more
core +5 more sources
Geometric representations for minimalist grammars
, 2012 We reformulate minimalist grammars as partial functions on term algebras for strings and trees. Using filler/role bindings and tensor product representations, we construct homomorphisms for these data structures into geometric vector spaces.
A. K Joshi +38 more
core +1 more source
The Google Similarity Distance
, 2007 Words and phrases acquire meaning from the way they are used in society, from their relative semantics to other words and phrases. For computers the equivalent of `society' is `database,' and the equivalent of `use' is `way to search the database.' We ...
Cilibrasi, Rudi, Vitanyi, Paul M. B.
core +2 more sources
Temiar Reduplication in One-Level Prosodic Morphology
, 2000 Temiar reduplication is a difficult piece of prosodic morphology. This paper presents the first computational analysis of Temiar reduplication, using the novel finite-state approach of One-Level Prosodic Morphology originally developed by Walther (1999b,
Walther, Markus
core +3 more sources
"May I borrow Your Filter?" Exchanging Filters to Combat Spam in a Community [PDF]
, 2005 Leveraging social networks in computer systems can be effective in dealing with a number of trust and security issues. Spam is one such issue where the "wisdom of crowds" can be harnessed by mining the collective knowledge of ordinary individuals.
Battiti, Roberto +2 more
core
A Simple Joint Model for Improved Contextual Neural Lemmatization
, 2020 English verbs have multiple forms. For instance, talk may also appear as talks, talked or talking, depending on the context. The NLP task of lemmatization seeks to map these diverse forms back to a canonical one, known as the lemma.
Cotterell, Ryan +2 more
core