Related papers: Reference-based Weak Supervision for Answer Senten…

Answer Sentence Selection (AS2) is an efficient approach for the design of open-domain Question Answering (QA) systems. In order to achieve low latency, traditional AS2 models score question-answer pairs individually, ignoring any…

State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such…

Recent advancements in transformer-based models have greatly improved the ability of Question Answering (QA) systems to provide correct answers; in particular, answer sentence selection (AS2) models, core components of retrieval-based…

Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led…

We study Label Smoothing (LS), a widely used regularization technique, in the context of neural learning to rank (L2R) models. LS combines the ground-truth labels with a uniform distribution, encouraging the model to be less confident in…

This research studies graph-based approaches for Answer Sentence Selection (AS2), an essential component for retrieval-based Question Answering (QA) systems. During offline learning, our model constructs a small-scale relevant training…

Question Answering (QA) has shown great success thanks to the availability of large-scale datasets and the effectiveness of neural models. Recent research works have attempted to extend these successes to the settings with few or no labeled…

The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…

This paper contributes a new large-scale dataset for weakly supervised cross-media retrieval, named Twitter100k. Current datasets, such as Wikipedia, NUS Wide and Flickr30k, have two major limitations. First, these datasets are lacking in…

Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the…

The limited availability of ground truth relevance labels has been a major impediment to the application of supervised methods to ad-hoc retrieval. As a result, unsupervised scoring methods, such as BM25, remain strong competitors to deep…

There have been a few recent methods proposed in text to video moment retrieval using natural language queries, but requiring full supervision during training. However, acquiring a large number of training videos with temporal boundary…

Respondent-Driven Sampling (RDS) employs a variant of a link-tracing network sampling strategy to collect data from hard-to-reach populations. By tracing the links in the underlying social network, the process exploits the social structure…

Recent years have seen rapid development in Information Extraction, as well as its subtask, Relation Extraction. Relation Extraction is able to detect semantic relations between entities in sentences. Currently, many efficient approaches…

With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supervising and enhancing these powerful models using smaller,…

Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample…

Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly…

Weak supervision combines the advantages of training on real data with the ability to exploit signal properties. However, training a neural network using weak supervision often requires an excessive amount of signal data, which severely…

Existing weak supervision approaches use all the data covered by weak signals to train a classifier. We show both theoretically and empirically that this is not always optimal. Intuitively, there is a tradeoff between the amount of…

Labeling training data has become one of the major roadblocks to using machine learning. Among various weak supervision paradigms, programmatic weak supervision (PWS) has achieved remarkable success in easing the manual labeling bottleneck…