Search Results for author: David R Mortensen

Found 4 papers, 2 papers with code

Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typing

1 code implementation1 Nov 2023 Yanlin Feng, Adithya Pratapa, David R Mortensen

In this paper, we present CASENT, a seq2seq model designed for ultra-fine entity typing that predicts ultra-fine types with calibrated confidence scores.

Entity Typing

ASR2K: Speech Recognition for Around 2000 Languages without Audio

1 code implementation6 Sep 2022 Xinjian Li, Florian Metze, David R Mortensen, Alan W Black, Shinji Watanabe

We achieve 50% CER and 74% WER on the Wilderness dataset with Crubadan statistics only and improve them to 45% CER and 69% WER when using 10000 raw text utterances.

Language Modelling Speech Recognition

AUTOLEX: An Automatic Framework for Linguistic Exploration

no code implementations25 Mar 2022 Aditi Chaudhary, Zaid Sheikh, David R Mortensen, Antonios Anastasopoulos, Graham Neubig

Each language has its own complex systems of word, phrase, and sentence construction, the guiding principles of which are often summarized in grammar descriptions for the consumption of linguists or language learners.

Sentence

Shaped Rewards Bias Emergent Language

no code implementations29 Sep 2021 Brendon Boldt, Yonatan Bisk, David R Mortensen

The second is shaped rewards which are designed specifically to make the task easier to learn by introducing biases in the learning process.

Inductive Bias

Cannot find the paper you are looking for? You can Submit a new open access paper.