| 16 |
Odi et Amo. Creating, Evaluating and Extending Sentiment Lexicons for Latin
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
A New Latin Treebank for Universal Dependencies: Charters between Ancient Latin and Romance Languages
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Recognizing semantic relations by combining transformers and fully connected models
|
|
|
|
Abstract:
Automatically recognizing an existing semantic relation (e.g. "is a", "part of", "property of", "opposite of" etc.) between two words (phrases, concepts, etc.) is an important task affecting many NLP applications and has been subject of extensive experimentation and modeling. Current approaches to automatically telling if a relation exists between two given concepts X and Y can be grouped into two types: 1) those modeling word-paths connecting X and Y in text and 2) those modeling distributional properties of X and Y separately, not necessary in the proximity to each other. Here, we investigate how both types can be improved and combined. We suggest a distributional approach that is based on an attention-based transformer. We have also developed a novel word path model that combines useful properties of a convolutional network with a fully connected language model. While our transformer-based approach works better, both our models significantly outperform the state-of-the-art within their classes of approaches. We also demonstrate that combining the two approaches results in additional gains since they use somewhat different data sources.
|
|
Keyword:
Philology. Linguistics
|
|
URL: https://strathprints.strath.ac.uk/75898/1/Roussinov_etal_LREC_2021_Recognizing_semantic_relations_by_combining_transformers_and_fully_connected_models.pdf
https://strathprints.strath.ac.uk/75898/
https://www.aclweb.org/anthology/2020.lrec-1.715/
|
|
BASE
|
|
Hide details
|
|
|
|
|
