Neural Networks For Negation Scope Detection

Automatic negation scope detection is a task that has been tackled using different classifiers and heuristics. Most systems are however 1) highly-engineered, 2) English-specific, and 3) only tested on the same genre they were trained on. We start by addressing 1) and 2) using a neural network architecture. Results obtained on data from the *SEM2012 shared task on negation scope detection show that even a simple feed-forward neural network using word-embedding features alone, performs on par with earlier classifiers, with a bi-directional LSTM outperforming all of them. We then address 3) by means of a specially-designed synthetic test set; in doing so, we explore the problem of detecting the negation scope more in depth and show that performance suffers from genre effects and differs with the type of negation considered.

[1]  Roser Morante,et al.  *SEM 2012 Shared Task: Resolving the Scope and Focus of Negation , 2012, *SEMEVAL.

[2]  Jorge Carrillo de Albornoz,et al.  UCM-I: A Rule-based Syntactic Approach for Resolving the Scope of Negation , 2012, *SEMEVAL.

[3]  Bonnie L. Webber,et al.  Applying the semantics of negation to SMT through n-best list re-ranking , 2014, EACL.

[4]  Md. Faisal Mahbub Chowdhury.  FBK: Exploiting Phrasal and Contextual Clues for Negation Scope Detection , 2012, *SEMEVAL.

[5]  Dan I. Moldovan,et al.  Some Issues on Detecting Negation from Text , 2011, FLAIRS.

[6]  Branimir Boguraev,et al.  Learning Structures of Negations from Flat Annotations , 2015, *SEMEVAL.

[7]  Johan Bos,et al.  UGroningen: Negation detection with Discourse Representation Structures , 2012, *SEM@NAACL-HLT.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Sophia Ananiadou,et al.  Developing a Robust Part-of-Speech Tagger for Biomedical Text , 2005, Panhellenic Conference on Informatics.

[10]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[11]  Virginia Francisco,et al.  UCM-2: a Rule-Based Approach to Infer the Scope of Negation via Dependency Parsing , 2012, *SEM@NAACL-HLT.

[12]  Stephan Oepen,et al.  Speculation and Negation: Rules, Rankers, and the Role of Syntax , 2012, CL.

[13]  Emily M. Bender,et al.  Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem , 2014, ACL.

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  Thamar Solorio,et al.  UABCoRAL: A Preliminary study for Resolving the Scope of Negation , 2012, *SEM@NAACL-HLT.

[16]  Bonnie Webber,et al.  Translating Negation: A Manual Error Analysis , 2015 .

[17]  Francis Bond,et al.  Enriching Parallel Corpora for Statistical Machine Translation with Semantic Negation Rephrasing , 2012, SSST@ACL.

[18]  James Paul White.  UWashington: Negation Resolution using Machine Learning Methods , 2012, *SEM@NAACL-HLT.

[19]  Dragomir R. Radev,et al.  UMichigan: A Conditional Random Field Model for Resolving the Scope of Negation , 2012, *SEMEVAL.

[20]  Erik Velldal,et al.  UiO 2: Sequence-labeling Negation Using Dependency Features , 2012, *SEMEVAL.

[21]  Stephan Oepen,et al.  UiO1: Constituent-Based Discriminative Ranking for Negation Resolution , 2012, *SEMEVAL.