相关论文: Can inferred provenance and its visualisation be u…
The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is…
Given a knowledge base (KB) with a non-entailed fact, the ABox abduction problem asks for possible extensions of the KB that would entail this fact. This problem has many applications, ranging from diagnosis to explainability and repair.…
Recognition errors are common in human communication. Similar errors often lead to unwanted behaviour in dialogue systems or virtual assistants. In human communication, we can recover from them by repeating misrecognized words or phrases;…
Natural Language Inference (NLI) datasets contain annotation artefacts resulting in spurious correlations between the natural language utterances and their respective entailment classes. These artefacts are exploited by neural networks even…
Public repositories for genome and proteome annotations, such as the Gene Ontology (GO), rarely stores negative annotations, i.e. proteins not possessing a given function. This leaves undefined or ill defined the set of negative examples,…
A crucial aspect of a knowledge base population system that extracts new facts from text corpora, is the generation of training data for its relation extractors. In this paper, we present a method that maximizes the effectiveness of newly…
We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…
Data analytics often involves hypothetical reasoning: repeatedly modifying the data and observing the induced effect on the computation result of a data-centric application. Previous work has shown that fine-grained data provenance can help…
Many studies focus on data annotation techniques for training effective PRMs. However, current methods encounter a significant issue when applied to long CoT reasoning processes: they tend to focus solely on the first incorrect step and all…
Gene studies are crucial for fields such as protein structure prediction, drug discovery, and cancer genomics, yet they face challenges in fully utilizing the vast and diverse information available. Gene studies require clean, factual…
Increasingly modern data science platforms today have non-intrusive and extensible provenance ingestion mechanisms to collect rich provenance and context information, handle modifications to the same file using distinguishable versions, and…
The ongoing functional annotation of proteins relies upon the work of curators to capture experimental findings from scientific literature and apply them to protein sequence and structure data. However, with the increasing use of…
The code base of software projects evolves essentially through inserting and removing information to and from the source code. We can measure this evolution via the elements of information - tokens, words, nodes - of the respective…
Auditing language-model outputs often requires more than judging correctness: an auditor may need to identify which source document most likely supports the knowledge expressed in a response. We study this as pinpoint provenance: given a…
The ubiquity of computation in modern scientific research inflicts new challenges for reproducibility. While most journals now require code and data be made available, the standards for organization, annotation, and validation remain lax,…
Multi-class classification annotations have significantly advanced AI applications, with truth inference serving as a critical technique for aggregating noisy and biased annotations. Existing state-of-the-art methods typically model each…
Knowledge graphs (KGs) have increasingly become the backbone of many critical knowledge-centric applications. Most large-scale KGs used in practice are automatically constructed based on an ensemble of extraction techniques applied over…
Predicting which words are considered hard to understand for a given target population is a vital step in many NLP applications such as text simplification. This task is commonly referred to as Complex Word Identification (CWI). With a few…
While the use of machine learning for the detection of propaganda techniques in text has garnered considerable attention, most approaches focus on "black-box" solutions with opaque inner workings. Interpretable approaches provide a…
While the Semantic Web currently can exhibit provenance information by using the W3C PROV standards, there is a "missing link" in connecting PROV to storing and querying for dynamic changes to RDF graphs using SPARQL. Solving this problem…