Related papers: Automated Resolution of Noisy Bibliographic Refere…
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may contain information that cannot be inferred from the source text. On large news corpora, removing low quality samples has been shown to reduce…
An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of…
We discuss two techniques used to characterize bibliographic records based on their similarity to and relationship with the contents of the NASA Astrophysics Data System (ADS) databases. The first method has been used to classify input text…
Automatic speech recognition systems are part of people's daily lives, embedded in personal assistants and mobile phones, helping as a facilitator for human-machine interaction while allowing access to information in a practically intuitive…
Automatically extracted metadata from scholarly documents in PDF formats is usually noisy and heterogeneous, often containing incomplete fields and erroneous values. One common way of cleaning metadata is to use a bibliographic reference…
Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training…
Most dense retrieval models contain an implicit assumption: the training query-document pairs are exactly matched. Since it is expensive to annotate the corpus manually, training pairs in real-world applications are usually collected…
The presence of noise in acquired data invariably leads to performance degradation in cross-modal matching. Unfortunately, obtaining precise annotations in the multimodal field is expensive, which has prompted some methods to tackle the…
Automatic speech recognition (ASR) systems can suffer from poor recall for various reasons, such as noisy audio, lack of sufficient training data, etc. Previous work has shown that recall can be improved by retrieving rewrite candidates…
Named entity recognition (NER) models often struggle with noisy inputs, such as those with spelling mistakes or errors generated by Optical Character Recognition processes, and learning a robust NER model is challenging. Existing robust NER…
Bibliographic reference parsers extract machine-readable metadata such as author names, title, journal, and year from bibliographic reference strings. To extract the metadata, the parsers apply heuristics or machine learning. However, no…
This paper studies the problem of finding the exact ranking from noisy comparisons. A comparison over a set of $m$ items produces a noisy outcome about the most preferred item, and reveals some information about the ranking. By repeatedly…
A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of their decisions on specific issues. In this work, we observe…
At third-generation (3G) gravitational-wave detector networks, compact binaries coalescences produce a ``confusion noise'' due to unresolved sources and to the error in the reconstruction of resolved sources, that can degrade the…
Noise bias is a significant source of systematic error in weak gravitational lensing measurements that must be corrected to satisfy the stringent standards of modern imaging surveys in the era of precision cosmology. This paper reviews the…
Algorithmic recourse suggests actions to individuals who have been adversely affected by automated decision-making, helping them to achieve the desired outcome. Knowing the recourse, however, does not guarantee that users can implement it…
A large fraction of textual data available today contains various types of 'noise', such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as…
Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge…
Accurately finding the wrong words in the automatic speech recognition (ASR) hypothesis and recovering them well-founded is the goal of speech error correction. In this paper, we propose a non-autoregressive speech error correction method.…
Document denoising is considered one of the most challenging tasks in computer vision. There exist millions of documents that are still to be digitized, but problems like document degradation due to natural and man-made factors make this…