1 |
Neural Token Segmentation for High Token-Internal Complexity ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Morphological Reinflection with Multiple Arguments: An Extended Annotation schema and a Georgian Case Study ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Applying the Transformer to Character-level Transduction
|
|
|
|
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume (2021)
|
|
BASE
|
|
Show details
|
|
11 |
Telling BERT's Full Story: from Local Attention to Global Aggregation
|
|
|
|
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume (2021)
|
|
Abstract:
We take a deep look into the behaviour of self-attention heads in the transformer architecture. In light of recent work discouraging the use of attention distributions for explaining a model’s behaviour, we show that attention distributions can nevertheless provide insights into the local behaviour of attention heads. This way, we propose a distinction between local patterns revealed by attention and global patterns that refer back to the input, and analyze BERT from both angles. We use gradient attribution to analyze how the output of an attention head depends on the input tokens, effectively extending the local attention-based analysis to account for the mixing of information throughout the transformer layers. We find that there is a significant mismatch between attention and attribution distributions, caused by the mixing of context inside the model. We quantify this discrepancy and observe that interestingly, there are some patterns that persist across all layers despite the mixing.
|
|
URL: https://doi.org/10.3929/ethz-b-000496002 https://hdl.handle.net/20.500.11850/496002
|
|
BASE
|
|
Hide details
|
|
12 |
Disambiguatory Signals are Stronger in Word-initial Positions
|
|
|
|
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume (2021)
|
|
BASE
|
|
Show details
|
|
14 |
Asking It All: Generating Contextualized Questions for any Semantic Role ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Formae reformandae: for a reorganisation of verb form annotation in Universal Dependencies illustrated by the specific case of Latin
|
|
Cecchini, Flavio Massimiliano (orcid:0000-0001-9029-1822). - : Association for Computational Linguistics, 2021. : country:BGR, 2021. : place:Sofia, 2021
|
|
BASE
|
|
Show details
|
|
18 |
RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding.
|
|
|
|
BASE
|
|
Show details
|
|
|
|