Related papers: Design of Negative Sampling Strategies for Distant…
The availability of large amounts of user-provided data has been key to the success of machine learning for many real-world tasks. Recently, an increasing awareness has emerged that users should be given more control about how their data is…
Recently, the self-supervised pre-training paradigm has shown great potential in leveraging large-scale unlabeled data to improve downstream task performance. However, increasing the scale of unlabeled pre-training data in real-world…
Missing data is a fundamental challenge in data science, significantly hindering analysis and decision-making across a wide range of disciplines, including healthcare, bioinformatics, social science, e-commerce, and industrial monitoring.…
We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy.…
In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…
Selecting an appropriate task is challenging for contributors to Open Source Software (OSS), mainly for those who are contributing for the first time. Therefore, researchers and OSS projects have proposed various strategies to aid…
Recent work shows that post-training datasets for LLMs can be substantially downsampled without noticeably deteriorating performance. However, data selection often incurs high computational costs or is limited to narrow domains. In this…
Offline evaluation plays a central role in benchmarking recommender systems when online testing is impractical or risky. However, it is susceptible to two key sources of bias: exposure bias, where users only interact with items they are…
This paper addresses the problem of extracting keyphrases from scientific articles and categorizing them as corresponding to a task, process, or material. We cast the problem as sequence tagging and introduce semi-supervised methods to a…
While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a…
We propose and analyze a family of information processing systems, where a finite set of experts or servers are employed to extract information about a stream of incoming jobs. Each job is associated with a hidden label drawn from some…
It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target domain. Recently, Deep Neural Network (DNN) has become a…
The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues, which are out of the scope of APIs/DB. By leveraging external knowledge resources, relevant information can be retrieved and encoded…
Several methods have been explored for automating parts of Systematic Mapping (SM) and Systematic Review (SR) methodologies. Challenges typically evolve around the gaps in semantic understanding of text, as well as lack of domain and…
Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…
How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward…
Matching model is essential for Image-Text Retrieval framework. Existing research usually train the model with a triplet loss and explore various strategy to retrieve hard negative sentences in the dataset. We argue that current…
Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data structure or context by solving a pretext task.…
The design and complexity analysis of randomized coordinate descent methods, and in particular of variants which update a random subset (sampling) of coordinates in each iteration, depends on the notion of expected separable…
An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task. However, these models sample a large number of negative entities and negative relations during the model training,…