natural-language-processing   374

« earlier    

Cornell NLVR
Cornell Natural Language Visual Reasoning (NLVR) is a language grounding dataset. It contains 92,244 pairs of natural language statements grounded in synthetic images. The task is to determine whether a sentence is true or false about an image.
ai  natural-language-processing 
9 days ago by HighCharisma
[1707.05589] On the State of the Art of Evaluation in Neural Language Models
Ongoing innovations in recurrent neural network architectures have provided a steady influx of apparently state-of-the-art results on language modelling benchmarks. However, these have been evaluated using differing code bases and limited computational resources, which represent uncontrolled sources of experimental variation. We reevaluate several popular architectures and regularisation methods with large-scale automatic black-box hyperparameter tuning and arrive at the somewhat surprising conclusion that standard LSTM architectures, when properly regularised, outperform more recent models. We establish a new state of the art on the Penn Treebank and Wikitext-2 corpora, as well as strong baselines on the Hutter Prize dataset.
natural-language-processing  representation  machine-learning  deep-learning  to-write-about 
12 days ago by Vaguery
[1706.04902] A Survey Of Cross-lingual Word Embedding Models
Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.
natural-language-processing  representation  review  rather-interesting  to-write-about  to-do  algorithms  feature-extraction 
21 days ago by Vaguery
Neural Language Modeling From Scratch (Part 1)
Language models assign probability values to sequences of words. Those three words that appear right above your keyboard on your phone that try to predict the next word you’ll type are one of the uses of language modeling. In the case shown below, the language model is predicting that “from”, “on” and “it” have a high probability of being the next word in the given sentence. Internally, for each word in its vocabulary, the language model computes the probability that it will be the next word, but the user only gets to see the top three most probable words.
machine-learning  natural-language-processing  deep-learning  blog-post 
21 days ago by doneata
Bixby 2.0: The Start of the Next Paradigm Shift in Devices By Eui-Suk Chung, EVP, Head of Service Intelligence of Mobile Communications Business
Samsung announced the next version of Bixby, their digital voice assistant. Like other companies offering an assistant service, Samsung view the assistant as the control centre for connected smart and IOT devices.
@Samsung  Bixby-Samsung  Bixby-2.0  digital-voice-assistant  natural-language-processing  Bixby-SDK  Samsung-Developer-Conference  SDC-2017  connected-devices  #IOT  person:Eui-Suk-Chung 
5 weeks ago by elliottbledsoe
Corporate Gibberish Generator on
Welcome to the Corporate Gibberish Generator™ by Andrew Davidson. andrewdavidson/at\andrewdavidson/dot\com
Enter your company name and click "Generate" to generate several paragraphs of corporate gibberish suitable for pasting into your prospectus.
(The gibberish is geared more toward Internet and technology companies.)
branding  corporatism  humor  algorithms  natural-language-processing  generative-art 
7 weeks ago by Vaguery
A New Tool for Deep-Down Data Mining - Eos
User applications have focused on text-based information [e.g., Liu et al., 2016; Peters et al., 2017], but a large amount of data resides in tables and figures. We are working to allow users to write applications that read the full text of documents, identify specific tables and figures of interest, and then extract data from them
library  natural-language-processing  data-mining  journals 
7 weeks ago by hschilling
Unsupervised Sentiment Neuron
It’s interesting to note that the system also makes large updates after the completion of sentences and phrases. For example, in “And about 99.8 percent of that got lost in the film”, there’s a negative update after “lost” and a larger update at the sentence’s end, even though “in the film” has no sentiment content on its own.
sentiment-analysis  neural-networks  machine-learning  natural-language-processing  rather-interesting  to-write-about  consider:cause-and-effect  consider:feature-discovery 
7 weeks ago by Vaguery
[1709.06309] Aspect-Based Relational Sentiment Analysis Using a Stacked Neural Network Architecture
Sentiment analysis can be regarded as a relation extraction problem in which the sentiment of some opinion holder towards a certain aspect of a product, theme or event needs to be extracted. We present a novel neural architecture for sentiment analysis as a relation extraction problem that addresses this problem by dividing it into three subtasks: i) identification of aspect and opinion terms, ii) labeling of opinion terms with a sentiment, and iii) extraction of relations between opinion terms and aspect terms. For each subtask, we propose a neural network based component and combine all of them into a complete system for relational sentiment analysis. The component for aspect and opinion term extraction is a hybrid architecture consisting of a recurrent neural network stacked on top of a convolutional neural network. This approach outperforms a standard convolutional deep neural architecture as well as a recurrent network architecture and performs competitively compared to other methods on two datasets of annotated customer reviews. To extract sentiments for individual opinion terms, we propose a recurrent architecture in combination with word distance features and achieve promising results, outperforming a majority baseline by 18% accuracy and providing the first results for the USAGE dataset. Our relation extraction component outperforms the current state-of-the-art in aspect-opinion relation extraction by 15% F-Measure.
sentiment-analysis  natural-language-processing  deep-learning  neural-networks  machine-learning  architecture  nudge-targets  consider:representation 
8 weeks ago by Vaguery
[1705.01991] Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU
Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on efficient decoding, with a goal of achieving accuracy close the state-of-the-art in neural machine translation (NMT), while achieving CPU decoding speed/throughput close to that of a phrasal decoder.
We approach this problem from two angles: First, we describe several techniques for speeding up an NMT beam search decoder, which obtain a 4.4x speedup over a very efficient baseline decoder without changing the decoder output. Second, we propose a simple but powerful network architecture which uses an RNN (GRU/LSTM) layer at bottom, followed by a series of stacked fully-connected layers applied at every timestep. This architecture achieves similar accuracy to a deep recurrent model, at a small fraction of the training and decoding cost. By combining these techniques, our best system achieves a very competitive accuracy of 38.3 BLEU on WMT English-French NewsTest2014, while decoding at 100 words/sec on single-threaded CPU. We believe this is the best published accuracy/speed trade-off of an NMT system.
machine-learning  representation  algorithms  deep-learning  neural-networks  approximation  nudge-targets  consider:performance-measures  consider:representation  natural-language-processing 
8 weeks ago by Vaguery
[1608.02025] Boundary-based MWE segmentation with text partitioning
This work presents a fine-grained, text-chunking algorithm designed for the task of multiword expressions (MWEs) segmentation. As a lexical class, MWEs include a wide variety of idioms, whose automatic identification are a necessity for the handling of colloquial language. This algorithm's core novelty is its use of non-word tokens, i.e., boundaries, in a bottom-up strategy. Leveraging boundaries refines token-level information, forging high-level performance from relatively basic data. The generality of this model's feature space allows for its application across languages and domains. Experiments spanning 19 different languages exhibit a broadly-applicable, state-of-the-art model. Evaluation against recent shared-task data places text partitioning as the overall, best performing MWE segmentation algorithm, covering all MWE classes and multiple English domains (including user-generated text). This performance, coupled with a non-combinatorial, fast-running design, produces an ideal combination for implementations at scale, which are facilitated through the release of open-source software.
natural-language-processing  algorithms  parsing  nudge-targets  consider:looking-to-see  consider:representation  consider:performance-measures 
8 weeks ago by Vaguery
What every software engineer should know about search
Ask a software engineer: “How would you add search functionality to your product?” or “How do I build a search engine?” You’ll probably immediately hear back something like: “Oh, we’d just launch an…
search  architecture  artificial-intelligence  natural-language-processing  programming  ai 
10 weeks ago by e2b

« earlier    

related tags

#iot  @samsung  aesthetics  affect  ai  algorithms  amusing  api  approximation  architecture  article  artificial-intelligence  auto  bias  bioinformatics  bixby-2.0  bixby-samsung  bixby-sdk  blog-post  book  bots  branding  calculus  cfg  chatbot  chatterbot  classification  connected-devices  conservatism  consider:architecture  consider:cause-and-effect  consider:feature-discovery  consider:generative-art  consider:impossible-tasks  consider:looking-to-see  consider:other-applications  consider:performance-measures  consider:rediscovery  consider:representation  content-free-grammar  content-samurai  corporatism  corpus  course-notes  course  data-fusion  data-mining  data-science  data  dataset  deep-learning  dialog  digital-humanities  digital-voice-assistant  diss  documentation  ecommerce  embedded-systems  embeddings  emoji  encoders  english  essay  evolutionary-algorithms  feature-construction  feature-extraction  feature-selection  generative-art  generative-models  genetic-programming  gensim  google  grammar  have-read  history-of-science  humor  ia  image-analysis  image-processing  inference  interpretability  ios  javascript  journals  kinda-scary  language  latex  learning-by-doing  learning-by-watching  learning-from-data  lecture-notes  lecture  library  linear-algebra  linguistics  looking-to-see  machine-learning  mathematical-recreations  mathematics  max-grigorev  metaheuristics  metal  ml  music  natural-language-understanding  natural-language  neural-network  neural-networks  nlp  nlu  node.js  node  not-so-deep  nslinguistictagger  nudge-targets  ocr  open-source  optimization  package  parse  parser  parsey-mcparseface  parsing  part-of-speech  pattern-discovery  person:eui-suk-chung  pos  preprocessing  privacy  probability  programming  python  r  racism  rather-interesting  reference  reinforcement-learning  representation  review  rita  robustness  salesforce  samsung-developer-conference  sdc-2017  search  seeing-like-a-state  semantics  sentence  sentiment-analysis  sexism  skip-grams  social-networks  social-norms  sources  speech-recognition  speech  stanford  statistics  strings  stylometry  summarize  summarizer  summary  syntax  syntaxnet  system-of-professions  tensorflow  text-analysis  text-mining  tfidf  the-objective-truth-oh-right  theory-and-practice-sitting-in-a-tree  time-series  to-do  to-grok  to-read  to-share  to-understand  to-write-about  tools  topic-modeling  tree  treebanks  tutorial  twitter  type-systems  uni  universal-dependencies  unsupervised-learning  user-centric?  user-interface  video  voice-interface  wikipedia  word-frequency  word-nets  word-order 

Copy this bookmark: