Incorporating Contextual Information for Language-Independent, Dynamic Disambiguation Tasks

Humans resolve various kinds of linguistic ambiguities by exploiting available external evidence that has been acquired from modalities besides the linguistic one. This behavior can be observed for several languages, for English or German for example. In contrast, most natural language processing systems, parsers for example, rely on linguistic information only without taking further knowledge into account. While those systems are expected to correctly handle syntactically unambiguous cases, they cannot resolve syntactic ambiguities reliably. This paper hypothesizes that parsers would be able to find non-canonical interpretations of ambiguous sentences, if they exploited external, contextual information. The proposed multi-modal system, which combines data-driven and grammar-based approaches, confirmed this hypothesis in experiments on syntactically ambiguous sentences. This work focuses on the scarcely investigated relative clause attachment ambiguity instead of prepositional phrase attachment ambiguities, which are already well known in the literature. Experiments were conducted for English, German and Turkish and dynamic, i. e. highly dissimilar, contexts.

[1]  Wolfgang Menzel,et al.  An architecture for incremental information fusion of cross-modal representations , 2012, 2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[2]  Marshall R. Mayberry,et al.  A Connectionist Model of the Coordinated Interplay of Scene, Utterance, and World Knowledge , 2006 .

[3]  Wolfgang Menzel,et al.  Predictive Incremental Parsing and its Evaluation , 2011, DepLing.

[4]  Wolfgang Menzel,et al.  Towards a Systematic Analysis of Linguistic and Visual Complexity in Disambiguation and Structural Prediction , 2017, SIMBig.

[5]  Regina Barzilay,et al.  Low-Rank Tensors for Scoring Dependency Structures , 2014, ACL.

[6]  V. Vemuri,et al.  Artificial neural networks: an introduction , 1988 .

[7]  Jeffrey L. Elman,et al.  Activating Verbs from Typical Agents, Patients, Instruments, and Locations via Event Schemas , 2001 .

[8]  Regina Barzilay,et al.  Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees , 2014, ACL.

[9]  Patrick McCrae.  A Model for the Cross-Modal Influence of Visual Context upon Language Procesing , 2009, RANLP.

[10]  Julie C. Sedivy,et al.  Subject Terms: Linguistics Language Eyes & eyesight Cognition & reasoning , 1995 .

[11]  Moreno I. Coco,et al.  The interaction of visual and linguistic saliency during syntactic ambiguity resolution , 2015, Quarterly journal of experimental psychology.

[12]  Noah A. Smith,et al.  Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers , 2013, ACL.

[13]  P. Knoeferle,et al.  The role of visual scenes in spoken language comprehension : evidence from eye-tracking , 2005 .

[14]  G. Altmann,et al.  Incremental interpretation at verbs: restricting the domain of subsequent reference , 1999, Cognition.

[15]  Gordon Christie,et al.  Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes , 2016, EMNLP.

[16]  C. Clifton,et al.  Relative clause attachment in German, English, Spanish and French: Effects of position and length , 2015 .

[17]  Dilek Z. Hakkani-Tür,et al.  Building a Turkish Treebank , 2003 .

[18]  Wolfgang Menzel,et al.  Towards a System Architecture for Integrating Cross-modal Context in Syntactic Disambiguation , 2018 .

[19]  Ann Bies,et al.  The Penn Treebank: Annotating Predicate Argument Structure , 1994, HLT.

[20]  Shimon Ullman,et al.  Do You See What I Mean? Visual Resolution of Linguistic Ambiguities , 2015, EMNLP.

[21]  Cícero Nogueira dos Santos,et al.  Semantic Role Labeling , 2012 .

[22]  Richard Johansson,et al.  Extended Constituent-to-Dependency Conversion for English , 2007, NODALIDA.

[23]  Wolfgang Menzel,et al.  A Multi-modal Data-Set for Systematic Analyses of Linguistic Ambiguities in Situated Contexts , 2017, SIMBig.

[24]  Wolfgang Menzel,et al.  Because Size Does Matter: The Hamburg Dependency Treebank , 2014, LREC.

[25]  Yuji Matsumoto.  MaltParser: A language-independent system for data-driven dependency parsing , 2005 .