4 |
Neural Proof Nets
|
|
|
|
In: CoNLL 2020 - 24th Conference on Computational Natural Language Learning ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-02952267 ; CoNLL 2020 - 24th Conference on Computational Natural Language Learning, Nov 2020, Virtual, Dominican Republic. pp.26-40, ⟨10.18653/v1/2020.conll-1.3⟩ ; https://www.conll.org/ (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Putting a Spin on Language: A Quantum Interpretation of Unary Connectives for Linguistic Applications ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
A Fregean Restriction on Metarules
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
8 |
Deductive Parsing with an Unbounded Type Lexicon
|
|
|
|
In: 3rd Workshop on Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science ; SEMSPACE ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-02313572 ; SEMSPACE, Aug 2019, Riga, Latvia (2019)
|
|
Abstract:
« Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science (SemSpace2019) is the third in a series of workshops. Previous editions were held in 2016 (https://sites.google.com/site/semspworkshop/), co-located with the 13th International Conference on Quantum Physics and Logic (QPL2016) and in 2018 (https://sites.google.com/view/capns2018/home) co-located with the International Symposium on Quantum Interactions 2018This year we are very pleased to be part of ESSLLI 2019 (http://esslli2019.folli.info/)We also have a course at ESSLLI on Vector Space Models of Meaning: https://sites.google.com/view/vsmom/home » ; International audience ; We present a novel deductive parsing framework for categorial type logics, mo-deled as the composition of two components. The first is an attention-based neural supertagger, which assigns words dependency-decorated, contextually informed linear types. It requires no predefined type lexicon, instead utilizing the type syntax to construct types inductively, enabling the use of a richer and more precise typing environment. The type annotations produced are used by the second component, a computationally efficient hybrid system that emulates the inference process of the type logic, iteratively producing a bottom-up reconstruction of the input's derivation-proof and the associated program for compositional meaning assembly. Initial experiments yield promising results for each of the components.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://hal-lirmm.ccsd.cnrs.fr/lirmm-02313572/file/SEMSPACE2019_paper_4.pdf https://hal-lirmm.ccsd.cnrs.fr/lirmm-02313572 https://hal-lirmm.ccsd.cnrs.fr/lirmm-02313572/document
|
|
BASE
|
|
Hide details
|
|
10 |
Lexical and Derivational Meaning in Vector-Based Models of Relativisation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Proofs nets and the categorial flow of information
|
|
|
|
In: Logic and Interactive Rationality ; https://hal.archives-ouvertes.fr/hal-00759906 ; Logic and Interactive Rationality, 2012, Amsterdam, Netherlands (2012)
|
|
BASE
|
|
Show details
|
|
13 |
Proof nets for the Lambek-Grishin calculus
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-00759895 ; 2011 (2011)
|
|
BASE
|
|
Show details
|
|
18 |
Symmetric categorial grammar: residuation and Galois connections ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|