Page: 1 2 3 4 5 6 7 8 9 10... 41
101 |
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them ...
|
|
|
|
Abstract:
Open-domain Question Answering models which directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared to conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models lack the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate improved QA-pair models, we introduce Probably Asked Questions (PAQ), a very large resource of 65M automatically-generated QA-pairs. We introduce a new QA-pair retriever, RePAQ, to complement PAQ. We find that PAQ preempts and caches test questions, enabling RePAQ to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. Using PAQ, we train CBQA models which outperform comparable ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Question-Answering Systems
|
|
URL: https://underline.io/lecture/38209-paq-65-million-probably-asked-questions-and-what-you-can-do-with-them https://dx.doi.org/10.48448/s0hq-cn08
|
|
BASE
|
|
Hide details
|
|
103 |
To what extent do human explanations of model behavior align with actual model behavior? ...
|
|
|
|
BASE
|
|
Show details
|
|
104 |
Sequence Length is a Domain: Length-based Overfitting in Transformer Models ...
|
|
|
|
BASE
|
|
Show details
|
|
105 |
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations ...
|
|
|
|
BASE
|
|
Show details
|
|
106 |
Effective Sequence-to-Sequence Dialogue State Tracking ...
|
|
|
|
BASE
|
|
Show details
|
|
107 |
An Investigation into the Contribution of Locally Aggregated Descriptors to Figurative Language Identification ...
|
|
|
|
BASE
|
|
Show details
|
|
108 |
Solving Aspect Category Sentiment Analysis as a Text Generation Task ...
|
|
|
|
BASE
|
|
Show details
|
|
109 |
Discourse-Driven Integrated Dialogue Development Environment for Open-Domain Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
110 |
Context or No Context? A preliminary exploration of human-in-the-loop approach for Incremental Temporal Summarization in meetings ...
|
|
|
|
BASE
|
|
Show details
|
|
111 |
Learning Data Augmentation Schedules for Natural Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
114 |
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification ...
|
|
|
|
BASE
|
|
Show details
|
|
115 |
Improving Synonym Recommendation Using Sentence Context ...
|
|
|
|
BASE
|
|
Show details
|
|
116 |
Debiasing Methods in Natural Language Understanding Make Bias More Accessible ...
|
|
|
|
BASE
|
|
Show details
|
|
117 |
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9 10... 41
|
|