Search Results for author:
Found 7 papers, 4 papers with code
Mitigating Learnerese Effects for CEFR Classification
The role of an author’s L1 in SLA can be challenging for automated CEFR classification, in that texts from different L1 groups may be too heterogeneous to combine them as training data.
Towards a World-English Language Model for On-Device Virtual Assistants
Based on this insight and leveraging the design of our production models, we introduce a new architecture for World English NNLM that meets the accuracy, latency, and memory constraints of our single-dialect models.
ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change
To increase the accessibility of our model to non-English speakers, we propose to make use of cascaded machine translation and show that this approach can perform comparably to natively multilingual models while being easier to scale to a large number of languages.
Translating away Translationese without Parallel Data
We show how we can eliminate the need for parallel validation data by combining the self-supervised loss with an unsupervised loss.
Towards Debiasing Translation Artifacts
Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets.
Knowledge Graph Question Answering using Graph-Pattern Isomorphism
In this paper, we present a novel QA approach, dubbed TeBaQA.
I-AID: Identifying Actionable Information from Disaster-related Tweets
In this paper, we propose I-AID, a multimodel approach to automatically categorize tweets into multi-label information types and filter critical information from the enormous volume of social media data.
