Petroni, F;
Piktus, A;
Fan, A;
Lewis, PSH;
Yazdani, M;
Cao, ND;
Thorne, J;
... Riedel, S; + view all
(2021)
KILT: a Benchmark for Knowledge Intensive Language Tasks.
In: Toutanova, K and Rumshisky, A and Zettlemoyer, L and Hakkani-Tür, D and Beltagy, I and Bethard, S and Cotterell, R and Chakraborty, T and Zhou, Y, (eds.)
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
(pp. pp. 2523-2544).
Association for Computational Linguistics
Preview |
Text
Rocktäschel_2021.naacl-main.200.pdf - Published Version Download (850kB) | Preview |
Abstract
Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well on individual tasks, developing general models is difficult as each task might require computationally expensive indexing of custom knowledge sources, in addition to dedicated infrastructure. To catalyze research on models that condition on specific information in large textual resources, we present a benchmark for knowledge-intensive language tasks (KILT). All tasks in KILT are grounded in the same snapshot of Wikipedia, reducing engineering turnaround through the re-use of components, as well as accelerating research into task-agnostic memory architectures. We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance. We find that a shared dense vector index coupled with a seq2seq model is a strong baseline, outperforming more tailor-made approaches for fact checking, open-domain question answering and dialogue, and yielding competitive results on entity linking and slot filling, by generating disambiguated text. KILT data and code are available at https://github.com/facebookresearch
| Type: | Proceedings paper |
|---|---|
| Title: | KILT: a Benchmark for Knowledge Intensive Language Tasks. |
| Event: | 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| ISBN-13: | 978-1-954085-46-6 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://www.aclweb.org/anthology/volumes/2021.naac... |
| Language: | English |
| Additional information: | © 1963–2021 ACL. The Creative Commons Attribution 4.0 International (CC BY 4.0) - PB 22/06/2021 |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10129948 |
Loading...
Loading...Loading...| 1. |  China | 5 |
| 2. |  Russian Federation | 2 |
| 3. |  United States | 1 |
| 4. |  France | 1 |
| 5. |  Lithuania | 1 |
| 6. |  Germany | 1 |
Archive Staff Only
 |
View Item |
