1 |
Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings
|
|
|
|
BASE
|
|
Show details
|
|
4 |
I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Detect and Classify – Joint Span Detection and Classification for Health Outcomes ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
|
|
|
|
In: Comput Math Methods Med (2021)
|
|
BASE
|
|
Show details
|
|
8 |
RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding.
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction ...
|
|
|
|
Abstract:
Language-independent tokenisation (LIT) methods that do not require labelled language resources or lexicons have recently gained popularity because of their applicability in resource-poor languages. Moreover, they compactly represent a language using a fixed size vocabulary and can efficiently handle unseen or rare words. On the other hand, language-specific tokenisation (LST) methods have a long and established history, and are developed using carefully created lexicons and training resources. Unlike subtokens produced by LIT methods, LST methods produce valid morphological subwords. Despite the contrasting trade-offs between LIT vs. LST methods, their performance on downstream NLP tasks remain unclear. In this paper, we empirically compare the two approaches using semantic similarity measurement as an evaluation task across a diverse set of languages. Our experimental results covering eight languages show that LST consistently outperforms LIT when the vocabulary size is large, but LIT can produce ... : To appear in the 12th Language Resources and Evaluation (LREC 2020) Conference ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2002.11004 https://dx.doi.org/10.48550/arxiv.2002.11004
|
|
BASE
|
|
Hide details
|
|
17 |
Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction.
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Learning to Compose Relational Embeddings in Knowledge Graphs
|
|
|
|
BASE
|
|
Show details
|
|
|
|