2 |
Semantic Structural Decomposition for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
SemEval-2019 Task 1: Cross-lingual Semantic Parsing with UCCA ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Universal Dependency Parsing with a General Transition-Based DAG Parser ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
SemEval 2019 Shared Task: Cross-lingual Semantic Parsing with UCCA - Call for Participation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Simple and Effective Text Simplification Using Semantic and Neural Methods ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
BLEU is Not Suitable for the Evaluation of Text Simplification ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
A Transition-Based Directed Acyclic Graph Parser for UCCA ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations
|
|
|
|
Abstract:
This paper is concerned with identifying contexts useful for training word representation models for different word classes such as adjectives (A), verbs (V), and nouns (N). We introduce a simple yet effective framework for an automatic selection of {\em class-specific context configurations}. We construct a context configuration space based on universal dependency relations between words, and efficiently search this space with an adapted beam search algorithm. In word similarity tasks for each word class, we show that our framework is both effective and efficient. Particularly, it improves the Spearman's rho correlation with human scores on SimLex-999 over the best previously proposed class-specific contexts by 6 (A), 6 (V) and 5 (N) rho points. With our selected context configurations, we train on only 14% (A), 26.2% (V), and 33.6% (N) of all dependency-based contexts, resulting in a reduced training time. Our results generalise: we show that the configurations our algorithm learns for one English training setup outperform previously proposed context types in another training setup for English. Moreover, basing the configuration space on universal dependencies, it is possible to transfer the learned configurations to German and Italian. We also demonstrate improved per-class results over other context types in these two languages.
|
|
Keyword:
Context configurations; Context selection; Multilinguality; Transfer learning; Word representations
|
|
URL: https://doi.org/10.17863/CAM.10795 https://www.repository.cam.ac.uk/handle/1810/269692
|
|
BASE
|
|
Hide details
|
|
14 |
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Don’t Let Me Be #Misunderstood: Linguistically Motivated Algorithm for Predicting the Popularity of Textual Memes
|
|
|
|
In: Proceedings of the International AAAI Conference on Web and Social Media; Vol. 9 No. 1 (2015): Ninth International AAAI Conference on Web and Social Media ; 2334-0770 ; 2162-3449 (2015)
|
|
BASE
|
|
Show details
|
|
|
|