2016 ADecomposableAttentionModelforN: Difference between revisions
Jump to navigation
Jump to search
(ContinuousReplacement) Tag: continuous replacement |
|||
Line 18: | Line 18: | ||
On the [[Stanford Natural Language Inference (SNLI) dataset]], [[2016_ADecomposableAttentionModelforN|we]] obtain [[state-of-the-art results]] with almost an [[order of magnitude]] [[fewer parameter]]s than [[previous work]] and without relying on any [[word-order information]]. </s> | On the [[Stanford Natural Language Inference (SNLI) dataset]], [[2016_ADecomposableAttentionModelforN|we]] obtain [[state-of-the-art results]] with almost an [[order of magnitude]] [[fewer parameter]]s than [[previous work]] and without relying on any [[word-order information]]. </s> | ||
Adding [[intra-sentence attention]] that takes a [[minimum amount]] of order into account yields further improvements. </s> | Adding [[intra-sentence attention]] that takes a [[minimum amount]] of order into account yields further improvements. </s> | ||
=== 1 Introduction === | === 1 Introduction === | ||
=== 2 Related Work === | === 2 Related Work === | ||
=== 3 Approach === | === 3 Approach === | ||
==== 3.1 Attend ==== | ==== 3.1 Attend ==== | ||
==== 3.2 Compare ==== | ==== 3.2 Compare ==== | ||
==== 3.3 Aggregate ==== | ==== 3.3 Aggregate ==== | ||
==== 3.4 Intra-Sentence Attention (Optional) ==== | ==== 3.4 Intra-Sentence Attention (Optional) ==== | ||
=== 4 Computational Complexity === | === 4 Computational Complexity === | ||
=== 5 Experiments === | === 5 Experiments === | ||
==== 5.1 Implementation Details ==== | ==== 5.1 Implementation Details ==== | ||
==== 5.2 Results ==== | ==== 5.2 Results ==== | ||
=== 6 Conclusion === | === 6 Conclusion === | ||
=== Acknowledgements === | === Acknowledgements === | ||
Revision as of 00:37, 13 September 2019
- (Parikh et al., 2016) ⇒ Ankur P. Parikh, Oscar Tackstrom, Dipanjan Das, and Jakob Uszkoreit. (2016). “A Decomposable Attention Model for Natural Language Inference.” In: Proceedings of 2016_Conference on Empirical Methods in Natural Language Processing (EMNLP 2016). arXiv:1606.01933
Subject Headings: Attention Mechanism, Textual Entailment Recognition.
Notes
Cited By
- Google Scholar: ~ 401 Citations
- Semantic Scholar: ~ 397 Citations
Quotes
Abstract
We propose a simple neural architecture for natural language inference. Our approach uses attention to decompose the problem into subproblems that can be solved separately, thus making it trivially parallelizable. On the Stanford Natural Language Inference (SNLI) dataset, we obtain state-of-the-art results with almost an order of magnitude fewer parameters than previous work and without relying on any word-order information. Adding intra-sentence attention that takes a minimum amount of order into account yields further improvements.
1 Introduction
2 Related Work
3 Approach
3.1 Attend
3.2 Compare
3.3 Aggregate
3.4 Intra-Sentence Attention (Optional)
4 Computational Complexity
5 Experiments
5.1 Implementation Details
5.2 Results
6 Conclusion
Acknowledgements
References
;
Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
---|---|---|---|---|---|---|---|---|---|---|
2016 ADecomposableAttentionModelforN | Dipanjan Das Jakob Uszkoreit Ankur P. Parikh Oscar Tackstrom | A Decomposable Attention Model for Natural Language Inference | 2016 |