1 |
Is Information Density Uniform in Task-Oriented Dialogues? ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Analysing Human Strategies of Information Transmission as a Function of Discourse Context ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection ...
|
|
|
|
Abstract:
We apply contextualised word embeddings to lexical semantic change detection in the SemEval-2020 Shared Task 1. This paper focuses on Subtask 2, ranking words by the degree of their semantic drift over time. We analyse the performance of two contextualising architectures (BERT and ELMo) and three change detection algorithms. We find that the most effective algorithms rely on the cosine similarity between averaged token embeddings and the pairwise distances between token embeddings. They outperform strong baselines by a large margin (in the post-evaluation phase, we have the best Subtask 2 submission for SemEval-2020 Task 1), but interestingly, the choice of a particular algorithm depends on the distribution of gold scores in the test set. ... : To appear in Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval-2020) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2005.00050 https://arxiv.org/abs/2005.00050
|
|
BASE
|
|
Hide details
|
|
6 |
Analysing Lexical Semantic Change with Contextualised Word Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Semi-supervised emotion lexicon expansion with label propagation and specialized word embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|