| 41 |
Negated adjectives and antonyms in distributional semantics: not similar?
|
|
|
|
BASE
|
|
Show details
|
|
|
| 45 |
The LAMBADA dataset: word prediction requiring a broad discourse context
|
|
|
|
BASE
|
|
Show details
|
|
|
| 46 |
Short-term meaning shift: a distributional exploration
|
|
|
|
Abstract:
Comunicació presentada a la Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), celebrada els dies 2 a 7 de juny de 2019 a Minneapolis, Estats Units d'Amèrica. ; We present the first exploration of meaning shift over short periods of time in online communities using distributional representations. We create a small annotated dataset and use it to assess the performance of a standard model for meaning shift detection on shortterm meaning shift. We find that the model has problems distinguishing meaning shift from referential phenomena, and propose a measure of contextual variability to remedy this. ; The research carried out by the Amsterdam section of the team was partially funded by the Netherlands Organisation for Scientific Research (NWO) under VIDI grant no. 276-89-008, Asymmetry in Conversation. This project has received funding from the European Research Council (ERC) under the European Unions Horizon 2020 research and innovation programme (grant agreement No 715154), and from the Spanish Ramón y Cajal programme (grant RYC-2015-18907).
|
|
Keyword:
Computational linguistics; Computational semantics; Deep learning; Distributional semantics; Meaning shift; Online communities; Semantic change; Short-time meaning shift
|
|
URL: http://hdl.handle.net/10230/42449
|
|
BASE
|
|
Hide details
|
|
|
|
|
