@inproceedings{kutuzov-pivovarova-2021-three,
title = "Three-part diachronic semantic change dataset for {R}ussian",
author = "Kutuzov, Andrey and
Pivovarova, Lidia",
booktitle = "Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change 2021",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.lchange-1.2",
doi = "10.18653/v1/2021.lchange-1.2",
pages = "7--13",
abstract = "We present a manually annotated lexical semantic change dataset for Russian: RuShiftEval. Its novelty is ensured by a single set of target words annotated for their diachronic semantic shifts across three time periods, while the previous work either used only two time periods, or different sets of target words. The paper describes the composition and annotation procedure for the dataset. In addition, it is shown how the ternary nature of RuShiftEval allows to trace specific diachronic trajectories: {}changed at a particular time period and stable afterwards{'} or {}was changing throughout all time periods{'}. Based on the analysis of the submissions to the recent shared task on semantic change detection for Russian, we argue that correctly identifying such trajectories can be an interesting sub-task itself.",
}
1. What is it?
They presented an annotated dataset for diachronic semantic change.
2. What is amazing compared to previous works?
Their dataset enables us to track the three types of semantic shifts over three time periods (pre-Soviet, Soviet, post-Soviet).
obtain a new sense in each time period
one sense disappeared (pre-Soviet, Soviet), then stable (Soviet, post-Soviet)
stable (pre-Soviet, Soviet), then obtain a new sense (Soviet, post-Soviet)
3. Where is the key to technologies and techniques?
They select target words as follows:
changed words: selected from dictionaries
stable words: selected randomly
TIme-bins:
RuShiftEval-1: pre-Soviet, Soviet
RuShiftEval-2: Soviet, post-Soviet
RuShiftEval-3: pre-Soviet, post-Soviet
They annotated these words as DURel format.
4. How did evaluate it?
5. Is there a discussion?
What is it different from RuSemShift?
RuSemShift is annotated the degree of change with a set of two time periods.
a1da4
commented
3 years ago
0. Paper
@inproceedings{kutuzov-pivovarova-2021-three, title = "Three-part diachronic semantic change dataset for {R}ussian", author = "Kutuzov, Andrey and Pivovarova, Lidia", booktitle = "Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change 2021", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.lchange-1.2", doi = "10.18653/v1/2021.lchange-1.2", pages = "7--13", abstract = "We present a manually annotated lexical semantic change dataset for Russian: RuShiftEval. Its novelty is ensured by a single set of target words annotated for their diachronic semantic shifts across three time periods, while the previous work either used only two time periods, or different sets of target words. The paper describes the composition and annotation procedure for the dataset. In addition, it is shown how the ternary nature of RuShiftEval allows to trace specific diachronic trajectories: {
}changed at a particular time period and stable afterwards{'} or {}was changing throughout all time periods{'}. Based on the analysis of the submissions to the recent shared task on semantic change detection for Russian, we argue that correctly identifying such trajectories can be an interesting sub-task itself.", }1. What is it?
They presented an annotated dataset for diachronic semantic change.
2. What is amazing compared to previous works?
Their dataset enables us to track the three types of semantic shifts over three time periods (pre-Soviet, Soviet, post-Soviet).
3. Where is the key to technologies and techniques?
They select target words as follows:
TIme-bins:
They annotated these words as DURel format.
4. How did evaluate it?
5. Is there a discussion?
What is it different from RuSemShift?
RuSemShift is annotated the degree of change with a set of two time periods.
6. Which paper should read next?