Related papers: Gram-CTC: Automatic Unit Selection and Target Deco…

Recently, Zhang et al. (2022) propose a syntax-aware grammatical error correction (GEC) approach, named SynGEC, showing that incorporating tailored dependency-based syntax of the input sentence is quite beneficial to GEC. This work…

Connectionist temporal classification (CTC) and attention-based encoder decoder (AED) joint training has been widely applied in automatic speech recognition (ASR). Unlike most hybrid models that separately calculate the CTC and AED losses,…

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to…

Semi-Markov CRF has been proposed as an alternative to the traditional Linear Chain CRF for text segmentation tasks such as Named Entity Recognition (NER). Unlike CRF, which treats text segmentation as token-level prediction, Semi-CRF…

Sequence labeling models often benefit from incorporating external knowledge. However, this practice introduces data heterogeneity and complicates the model with additional modules, leading to increased expenses for training a…

Current continuous sign language recognition (CSLR) methods struggle with handling diverse samples. Although dynamic convolutions are ideal for this task, they mainly focus on spatial modeling and fail to capture the temporal dynamics and…

The time-series forecasting (TSF) problem is a traditional problem in the field of artificial intelligence. Models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and GRU (Gate Recurrent Units) have contributed to…

The performance of algorithms for decentralized optimization is affected by both the optimization error and the consensus error, the latter of which arises from the variation between agents' local models. Classically, algorithms employ…

Randomized controlled trials (RCTs) represent the paramount evidence of clinical medicine. Using machines to interpret the massive amount of RCTs has the potential of aiding clinical decision-making. We propose a RCT conclusion generation…

This report describes the parsing problem for Combinatory Categorial Grammar (CCG), showing how a combination of Transformer-based neural models and a symbolic CCG grammar can lead to substantial gains over existing approaches. The report…

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…

Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long…

We propose a new method for training iterative collective classifiers for labeling nodes in network data. The iterative classification algorithm (ICA) is a canonical method for incorporating relational information into classification. Yet,…

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units.…

Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central challenge in this setting lies in determining the optimal…

In Automatic Speech Recognition (ASR) systems, a recurring obstacle is the generation of narrowly focused output distributions. This phenomenon emerges as a side effect of Connectionist Temporal Classification (CTC), a robust sequence…

Deep neural acoustic models benefit from context-dependent (CD) modeling of output symbols. We consider direct training of CTC networks with CD outputs, and identify two issues. The first one is frame-level normalization of probabilities in…

This paper describes our submission (named clac) to the 2016 Discriminating Similar Languages (DSL) shared task. We participated in the closed Sub-task 1 (Set A) with two separate machine learning techniques. The first approach is a…