3 |
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Visually Grounded and Textual Semantic Models Differentially Decode Brain Activity Associated with Concrete and Abstract Nouns ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Modelling metaphor with attribute-based semantics
|
|
Bulat, L; Clark, Stephen; Shutova, Ekaterina. - : Association for Computational Linguistics, 2017. : Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017
|
|
BASE
|
|
Show details
|
|
7 |
Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Comparing Data Sources and Architectures for Deep Visual Representation Learning in Semantics ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Multi-Modal Representations for Improved Bilingual Lexicon Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Multi-Modal Representations for Improved Bilingual Lexicon Learning
|
|
Vulić, I; Kiela, D; Clark, Stephen. - : Association for Computational Linguistics, 2016. : http://acl2016.org/, 2016. : Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016
|
|
BASE
|
|
Show details
|
|
11 |
Comparing Data Sources and Architectures for Deep Visual Representation Learning in Semantics
|
|
Kiela, D; Vero, Anita; Clark, Stephen. - : Association for Computational Linguistics, 2016. : Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016
|
|
BASE
|
|
Show details
|
|
12 |
RELPRON: A Relative Clause Evaluation Dataset for Compositional Distributional Semantics
|
|
|
|
Abstract:
This is the author accepted manuscript. The final version is available from MIT Press via http://dx.doi.org/10.1162/COLI_a_00263 ; This article introduces RELPRON, a large dataset of subject and object relative clauses, for the evaluation of methods in compositional distributional semantics. RELPRON targets an intermediate level of grammatical complexity between content-word pairs and full sentences. The task involves matching terms, such as ‘wisdom’, with representative properties, such as ‘quality that experience teaches’. A unique feature of RELPRON is that it is built from attested properties, but without the need for them to appear in relative clause format in the source corpus. The article also presents some initial experiments on RELPRON, using a variety of composition methods including simple baselines, arithmetic operators on vectors, and finally more complex methods in which argument-taking words are represented as tensors. The latter methods are based on the Categorial framework, which is described in detail. The results show that vector addition is difficult to beat — in line with the existing literature — but that an implementation of the Categorial framework based on the Practical Lexical Function model is able to match the performance of vector addition. The article finishes with an in-depth analysis of RELPRON, showing how results vary across subject and object relative clauses, across different head nouns, and how the methods perform on the subtasks necessary for capturing relative clause semantics, as well as providing a qualitative analysis highlighting some of the more common errors. Our hope is that the competitive results presented here, in which the best systems are on average ranking one out of every two properties correctly for a given term, will inspire new approaches to the RELPRON ranking task and other tasks based on linguistically interesting constructions. ; Laura Rimell and Stephen Clark were supported by EPSRC grant EP/I037512/1. Jean Maillard is supported by an EPSRC Doctoral Training Grant and a St John’s Scholarship. Laura Rimell, Tamara Polajnar and Stephen Clark are supported by ERC Starting Grant DisCoTex (306920).
|
|
URL: https://doi.org/10.17863/CAM.380 https://www.repository.cam.ac.uk/handle/1810/256438
|
|
BASE
|
|
Hide details
|
|
13 |
Vision and Feature Norms: Improving automatic feature norm learning through cross-modal maps
|
|
Bulat, L; Kiela, D; Clark, Stephen. - : Association for Computational Linguistics, 2016. : http://www.aclweb.org/anthology/N/N16/, 2016. : Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016
|
|
BASE
|
|
Show details
|
|
14 |
Expected F-Measure Training for Shift-Reduce Parsing with Recurrent Neural Networks
|
|
Xu, W; Auli, M; Clark, Stephen. - : Association for Computational Linguistics, 2016. : Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016
|
|
BASE
|
|
Show details
|
|
15 |
Using Sentence Plausibility to Learn the Semantics of Transitive Verbs ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
The Frobenius anatomy of word meanings I: subject and object relative pronouns ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Participant Reference in Narrative Discourse: A Comparison of Three Methodologies
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Concrete Sentence Spaces for Compositional Distributional Models of Meaning ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|