Page: 1... 3 4 5 6 7 8 9 10 11... 1.020
| 121 |
Analysis of Language Change in Collaborative Instruction Following
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
|
| 122 |
SCiL 2022 Editors' Note
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
|
| 123 |
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 468-483 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 124 |
PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 414-433 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 125 |
VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 376-392 (2022) (2022)
|
|
Abstract:
AbstractAccurately extracting structured content from PDFs is a critical first step for NLP over scientific papers. Recent work has improved extraction accuracy by incorporating elementary layout information, for example, each token’s 2D position on the page, into language model pretraining. We introduce new methods that explicitly model VIsual LAyout (VILA) groups, that is, text lines or text blocks, to further improve performance. In our I-VILA approach, we show that simply inserting special tokens denoting layout group boundaries into model inputs can lead to a 1.9% Macro F1 improvement in token classification. In the H-VILA approach, we show that hierarchical encoding of layout-groups can result in up to 47% inference time reduction with less than 0.8% Macro F1 loss. Unlike prior layout-aware approaches, our methods do not require expensive additional pretraining, only fine-tuning, which we show can reduce training cost by up to 95%. Experiments are conducted on a newly curated evaluation suite, S2-VLUE, that unifies existing automatically labeled datasets and includes a new dataset of manual annotations covering diverse papers from 19 scientific disciplines. Pre-trained weights, benchmark datasets, and source code are available at https://github.com/allenai/VILA.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doi.org/10.1162/tacl_a_00466
https://doaj.org/article/8391c75e305f49999ff12c1d2cd19316
|
|
BASE
|
|
Hide details
|
|
|
| 126 |
LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 434-451 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 127 |
Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 393-413 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 128 |
Time-Aware Language Models as Temporal Knowledge Bases
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 257-273 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 129 |
Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 240-256 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 130 |
Phylogenetic trees: Grammar versus vocabulary
|
|
|
|
In: Russian Journal of Linguistics, Vol 26, Iss 1, Pp 31-50 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 131 |
Les débuts de la phraséologie et les premières « phraséologies historiques » italo-françaises
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 132 |
Formen und Funktionen des Konjunktivs II in historischen ostoberdeutschen Predigten.
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 133 |
Zur Sprachdynamik des Konjunktivs im Bairischen in Österreich
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 134 |
Die Konjunktiv-II-Bildung im Kontext von Partikelverben in den Basisdialekten Salzburgs
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 135 |
Evaluating Explanations: How Much Do Explanations from the Teacher Aid Students?
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 359-375 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 136 |
Informationen zu den Beitragenden/Information about the authors
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 137 |
A Coordenação na Gramática Discursivo-Funcional
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 138 |
Der Konjunktiv II in den ruralen Basisdialekten Österreichs.
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 139 |
Konjunktiv II-Variation im urbanen Sprachgebrauch in Österreich
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 140 |
Der Konjunktiv II in Salzburger Varietäten: Grammatik, Gebrauch, soziale Faktoren
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
Page: 1... 3 4 5 6 7 8 9 10 11... 1.020 |
|
