05 October 2018 - Paola Merlo: Seminar TITLE: Vectorial semantic spaces do not encode human judgements of intervention similarity ABSTRACT: Despite their practical success and impressive performances, neural-network-based and distributed semantics techniques have often been criticized as they remain fundamentally opaque and difficult to interpret. Several recent pieces of work have investigated the linguistic abilities of these representations, and shown that they can capture long agreement and thus hierarchical notions. In this vein, we study another core, defining and more challenging property of language: the ability to construe long-distance dependencies. Human languages exhibit the ability to interpret discontinuous elements distant from each other in the string as if they were adjacent. This ability is blocked if a similar, but estraneous, element intervenes between the discontinuous components. We present results that show that word embeddings and the similarity spaces they define do not correlate with experimental results on intervention similarity in long-distance dependencies narrowly defined. These results show that the linguistic encoding in distributed representations does not appear to be human-like, and it also brings evidence to the debate on narrow or broad definitions of similarity in syntax and sentence processing. BIOGRAPHY: Paola Merlo is associate professor in the Linguistics department of the University of Geneva. She is the head of the interdisciplinary research group Computational Learning and Computational Linguistics (CLCL). The group is concerned with interdisciplinary research combining linguistic modelling with machine learning techniques. Prof. Merlo has been editor of Computational Linguistics, published by MIT Press and a member of the executive committee of the ACL. Prof. Merlo studied theoretical linguistics at the University of Venice and holds a doctorate in Computational Linguistics from the University of Maryland, USA. She has been associate research fellow at the University of Pennsylvania, and visiting scholar at Rutgers, Edinburgh, and Stanford. Oct 05 2018 11.00 - 12.30 05 October 2018 - Paola Merlo: Seminar ILCC seminar by Paola Merlo in IF 4.31/4.33 Informatics Forum 4.31/4.33 Contact
05 October 2018 - Paola Merlo: Seminar TITLE: Vectorial semantic spaces do not encode human judgements of intervention similarity ABSTRACT: Despite their practical success and impressive performances, neural-network-based and distributed semantics techniques have often been criticized as they remain fundamentally opaque and difficult to interpret. Several recent pieces of work have investigated the linguistic abilities of these representations, and shown that they can capture long agreement and thus hierarchical notions. In this vein, we study another core, defining and more challenging property of language: the ability to construe long-distance dependencies. Human languages exhibit the ability to interpret discontinuous elements distant from each other in the string as if they were adjacent. This ability is blocked if a similar, but estraneous, element intervenes between the discontinuous components. We present results that show that word embeddings and the similarity spaces they define do not correlate with experimental results on intervention similarity in long-distance dependencies narrowly defined. These results show that the linguistic encoding in distributed representations does not appear to be human-like, and it also brings evidence to the debate on narrow or broad definitions of similarity in syntax and sentence processing. BIOGRAPHY: Paola Merlo is associate professor in the Linguistics department of the University of Geneva. She is the head of the interdisciplinary research group Computational Learning and Computational Linguistics (CLCL). The group is concerned with interdisciplinary research combining linguistic modelling with machine learning techniques. Prof. Merlo has been editor of Computational Linguistics, published by MIT Press and a member of the executive committee of the ACL. Prof. Merlo studied theoretical linguistics at the University of Venice and holds a doctorate in Computational Linguistics from the University of Maryland, USA. She has been associate research fellow at the University of Pennsylvania, and visiting scholar at Rutgers, Edinburgh, and Stanford. Oct 05 2018 11.00 - 12.30 05 October 2018 - Paola Merlo: Seminar ILCC seminar by Paola Merlo in IF 4.31/4.33 Informatics Forum 4.31/4.33 Contact
Oct 05 2018 11.00 - 12.30 05 October 2018 - Paola Merlo: Seminar ILCC seminar by Paola Merlo in IF 4.31/4.33
