Related papers: How Does Beam Search improve Span-Level Confidence…

Second-order semantic parsing with end-to-end mean-field inference has been shown good performance. In this work we aim to improve this method by modeling label correlations between adjacent arcs. However, direct modeling leads to memory…

Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance. Such techniques, however, are not directly applicable to more…

This paper introduces PAG-a novel optimization and decoding approach that guides autoregressive generation of document identifiers in generative retrieval models through simultaneous decoding. To this aim, PAG constructs a set-based and…

Generative retrieval seeks to replace traditional search index data structures with a single large-scale neural network, offering the potential for improved efficiency and seamless integration with generative large language models. As an…

The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model framework for multi-label text classification. Instead of…

Quantifying uncertainty in automatically generated text is important for letting humans check potential hallucinations and making systems more reliable. Conformal prediction is an attractive framework to provide predictions imbued with…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to…

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often…

Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising, it crucially relies on accurate descriptions of the label…

Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…

The CL-SciSumm 2016 shared task introduced an interesting problem: given a document D and a piece of text that cites D, how do we identify the text spans of D being referenced by the piece of text? The shared task provided the first…

A reliable representation of uncertainty is essential for the application of modern machine learning methods in safety-critical settings. In this regard, the use of credal sets (i.e., convex sets of probability distributions) has recently…

Within the scope of natural language processing, the domain of multi-label text classification is uniquely challenging due to its expansive and uneven label distribution. The complexity deepens due to the demand for an extensive set of…

Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation…

This project aims to investigate a novel sequence generation method inspired by the AlphaGo paradigm, adapting it for use with large language models (LLMs). The proposed approach involves creating search trees of different possible…

Structured prediction is often approached by training a locally normalized model with maximum likelihood and decoding approximately with beam search. This approach leads to mismatches as, during training, the model is not exposed to its…

Sentence encoders map sentences to real valued vectors for use in downstream applications. To peek into these representations - e.g., to increase interpretability of their results - probing tasks have been designed which query them for…

Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small label spaces and…