Related papers: Confidence-Calibrated Ensemble Dense Phrase Retrie…

We propose a new algorithm to learn a dictionary for reconstructing and sparsely encoding signals from measurements without phase. Specifically, we consider the task of estimating a two-dimensional image from squared-magnitude measurements…

The long-standing goal of dense retrievers in abtractive open-domain question answering (ODQA) tasks is to learn to capture evidence passages among relevant passages for any given query, such that the reader produce factually correct…

Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech from a corpus of acoustic speech data. One potential approach to this problem is to use dynamic time warping (DTW) to find well-aligning patterns from the…

Image captioning creates informative text from an input image by creating a relationship between the words and the actual content of an image. Recently, deep learning models that utilize transformers have been the most successful in…

Deep Neural Networks (DNNs), despite their tremendous success in recent years, could still cast doubts on their predictions due to the intrinsic uncertainty associated with their learning process. Ensemble techniques and post-hoc…

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.…

Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large…

While pre-trained language models (PLMs) have become a de-facto standard promoting the accuracy of text classification tasks, recent studies find that PLMs often predict over-confidently. Although various calibration methods have been…

Large Language Model-based Dense Retrieval (LLM-DR) optimizes over numerous heterogeneous fine-tuning collections from different domains. However, the discussion about its training data distribution is still minimal. Previous studies rely…

Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of…

IR models using a pretrained language model significantly outperform lexical approaches like BM25. In particular, SPLADE, which encodes texts to sparse vectors, is an effective model for practical use because it shows robustness to…

Ensemble learning is a mainstay in modern data science practice. Conventional ensemble algorithms assigns to base models a set of deterministic, constant model weights that (1) do not fully account for variations in base model accuracy…

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the…

Improving the reliability of large language models (LLMs) is critical for deploying them in real-world scenarios. In this paper, we propose \textbf{Deliberative Searcher}, the first framework to integrate certainty calibration with…

This paper presents ConvRerank, a conversational passage re-ranker that employs a newly developed pseudo-labeling approach. Our proposed view-ensemble method enhances the quality of pseudo-labeled data, thus improving the fine-tuning of…

Paraphrasing exists at different granularity levels, such as lexical level, phrasal level and sentential level. This paper presents Decomposable Neural Paraphrase Generator (DNPG), a Transformer-based model that can learn and generate…

Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to model. To overcome this, recent learning-based methods have…

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…

Speech dereverberation aims to alleviate the negative impact of late reverberant reflections. The weighted prediction error (WPE) method is a well-established technique known for its superior performance in dereverberation. However, in…

Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search,…