Search Results for author:
Found 7 papers, 1 papers with code
TST$^\mathrm{R}$: Target Similarity Tuning Meets the Real World
Target similarity tuning (TST) is a method of selecting relevant examples in natural language (NL) to code generation through large language models (LLMs) to improve performance.
Augmented Embeddings for Custom Retrievals
The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and corpus elements are both natural language (NL) utterances (homogeneous) and the goal is to pick most relevant elements from the corpus in the Top-K, where K is large, such as 10, 25, 50 or even 100 (relaxed).
GrACE: Generation using Associated Code Edits
In our experiments with two datasets, the knowledge of prior edits boosts the performance of the LLMs significantly and enables them to generate 29% and 54% more correctly edited code in top-1 suggestions relative to the current state-of-the-art symbolic and neural approaches, respectively.
Overwatch: Learning Patterns in Code Edit Sequences
Our experiments show that Overwatch has 78% precision and that Overwatch not only completed edits when developers missed the opportunity to use the IDE tool support but also predicted new edits that have no tool support in the IDE.
A Probabilistic Framework for Knowledge Graph Data Augmentation
We present NNMFAug, a probabilistic framework to perform data augmentation for the task of knowledge graph completion to counter the problem of data scarcity, which can enhance the learning process of neural link predictors.
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes
To tackle this issue of availability of annotated data, a lot of research has been done on unsupervised domain adaptation that tries to generate systems for an unlabelled target domain data, given labeled source domain data.
Unbiased Loss Functions for Extreme Classification With Missing Labels
In addition to the computational burden arising from large number of training instances, features and labels, problems in XMC are faced with two statistical challenges, (i) large number of 'tail-labels' -- those which occur very infrequently, and (ii) missing labels as it is virtually impossible to manually assign every relevant label to an instance.
