Search Results for author:
Found 17 papers, 8 papers with code
Iterative Feature Mining for Constraint-Based Data Collection to Increase Data Diversity and Model Robustness
Diverse data is crucial for training robust models, but crowdsourced text often lacks diversity as workers tend to write simple variations from prompts.
Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification
Intent classifiers must be able to distinguish when a user's utterance does not belong to any supported intent to avoid producing incorrect and unrelated system responses.
Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization
Furthermore, alignment between model and human foci in this setting does not seem to dictate the quality of the LLM-generated summaries.
EyeTrans: Merging Human and Machine Attention for Neural Code Summarization
Neural code summarization leverages deep learning models to automatically generate brief natural language summaries of code snippets.
On Evaluation of Document Classification using RVL-CDIP
The RVL-CDIP benchmark is widely used for measuring performance on the task of document classification.
Revisiting Lightweight Compiler Provenance Recovery on ARM Binaries
In this paper, we extend previous work with a shallow-learning model that efficiently and accurately recovers compiler configuration properties for ARM binaries.
Revisiting Deep Learning for Variable Type Recovery
Unfortunately, the lack of semantic information like variable types makes comprehending binaries difficult.
Augmenting Task-Oriented Dialogue Systems with Relation Extraction
The standard task-oriented dialogue pipeline uses intent classification and slot-filling to interpret user utterances.
Evaluating Out-of-Distribution Performance on Document Image Classifiers
Our new out-of-distribution benchmark consists of two types of documents: those that are not part of any of the 16 in-domain RVL-CDIP categories (RVL-CDIP-O), and those that are one of the 16 in-domain categories yet are drawn from a distribution different from that of the original RVL-CDIP dataset (RVL-CDIP-N).
Pre-Training Representations of Binary Code Using Contrastive Learning
To the best of our knowledge, COMBO is the first language representation model that incorporates source code, binary code, and comments into contrastive code representation learning and unifies multiple tasks for binary code analysis.
A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog
By extension, so too has interest in developing and improving intent classification and slot-filling models, which are two components that are commonly used in task-oriented dialog systems.
Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset
Similarly, developers of such ML-driven systems need to be able to add new training data to an already-existing dataset to support these new skills.
One Agent To Rule Them All: Towards Multi-agent Conversational AI
To address these problems, we introduce a new task BBAI: Black-Box Agent Integration, focusing on combining the capabilities of multiple black-box CAs at scale.
Ranked #1 on
Multi-agent Integration
on BBAI Dataset
Conversational Response Selection
Multi-agent Integration
+1
Inconsistencies in Crowdsourced Slot-Filling Annotations: A Typology and Identification Methods
Using three new noisy crowd-annotated datasets, we show that a wide range of inconsistencies occur and can impact system performance if not addressed.
Data Query Language and Corpus Tools for Slot-Filling and Intent Classification Data
Typical machine learning approaches to developing task-oriented dialog systems require the collection and management of large amounts of training data, especially for the tasks of intent classification and slot-filling.
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
We find that while the classifiers perform well on in-scope intent classification, they struggle to identify out-of-scope queries.
The State and Future of Genetic Improvement
We report the discussion session at the sixth international Genetic Improvement workshop, GI-2019 @ ICSE, which was held as part of the 41st ACM/IEEE International Conference on Software Engineering on Tuesday 28th May 2019.
