Visualitza per autor "Ballesteros, Miguel"

Ordena per: Ordre: Resultats:

  • Ballesteros, Miguel; Wanner, Leo (ACL (Association for Computational Linguistics), 2016)
    Even syntactically correct sentences are perceived as awkward if they do not contain correct punctuation. Still, the problem of automatic generation of punctuation marks has been largely neglected for a long time. We/npresent ...
  • Ballesteros, Miguel; Bohnet, Bernd; Mille, Simon; Wanner, Leo (Cambridge University Press, 2016)
    ‘Deep-syntactic’ dependency structures that capture the argumentative, attributive and co-/nordinative relations between full words of a sentence have a great potential for a number/nof NLP-applications. The abstraction ...
  • Ballesteros, Miguel; Bohnet, Bernd; Mille, Simon; Wanner, Leo (ACL (Association for Computational Linguistics), 2015)
    Abstract structures from which the generation naturally starts often do not contain any functional nodes, while surface-syntactic structures or a chain of tokens in a linearized tree contain all of them. Therefore, data-driven ...
  • Padró, Muntsa; Ballesteros, Miguel; Martínez, Héctor; Bohnet, Bernd (ACL (Association for Computational Linguistics), 2013)
    This paper studies the performance of different parsers over a large Spanish treebank. The aim of this work is to assess the limitations of state-of-the-art parsers. We want to select the most appropriate parser for ...
  • Ballesteros, Miguel; Dyer, Chris; Smith, Noah A. (ACL (Association for Computational Linguistics), 2015)
    We present extensions to a continuousstate dependency parsing method that makes it applicable to morphologically rich languages. Starting with a highperformance transition-based parser that uses long short-term memory ...
  • Lample, Guillaume; Ballesteros, Miguel; Subramanian, Sandeep; Kawakami, Kazuya; Dyer, Chris (ACL (Association for Computational Linguistics), 2016)
    State-of-the-art named entity recognition systems/nrely heavily on hand-crafted features and/ndomain-specific knowledge in order to learn/neffectively from the small, supervised training/ncorpora that are available. In ...
  • Dyer, Chris; Kuncoro, Adhiguna; Ballesteros, Miguel; Smith, Noah A. (ACL (Association for Computational Linguistics), 2016)
    We introduce recurrent neural network grammars,/nprobabilistic models of sentences with/nexplicit phrase structure. We explain efficient/ninference procedures that allow application to/nboth parsing and language modeling. ...
  • Buckman, Jacob; Ballesteros, Miguel; Dyer, Chris (ACL (Association for Computational Linguistics), 2016)
    We introduce a novel approach to the decoding problem in transition-based parsing: heuristic backtracking. This algorithm uses a series of partial parses on the sentence to locate the best candidate parse, using confidence ...
  • Dyer, Chris; Ballesteros, Miguel; Ling, W; Matthews, A; Smith, Noah A. (ACL (Association for Computational Linguistics), 2015)
    We propose a technique for learning representations of parser states in transitionbased dependency parsers. Our primary innovation is a new control structure for sequence-to-sequence neural networks— the stack LSTM. Like ...
  • Ballesteros, Miguel; Carreras, Xavier (ACL (Association for Computational Linguistics), 2015)
    We present a transition-based arc-eager model to parse spinal trees, a dependencybased representation that includes phrasestructure information in the form of constituent spines assigned to tokens. As a main advantage, the ...
  • Soler Company, Juan; Ballesteros, Miguel; Bohnet, Bernd; Mille, Simon; Wanner, Leo (ACL (Association for Computational Linguistics), 2015)
    “Deep-syntactic” dependency structures bridge the gap between the surface-syntactic structures as produced by state-of-the-art dependency parsers and semantic logical forms in that they abstract away from surfacesyntactic ...