Related papers: Dynamic Programming Encoding for Subword Segmentat…

Byte Pair Encoding (BPE) serves as a foundation method for text tokenization in the Natural Language Processing (NLP) field. Despite its wide adoption, the original BPE algorithm harbors an inherent flaw: it inadvertently introduces a…

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

This work presents a fine-grained, text-chunking algorithm designed for the task of multiword expressions (MWEs) segmentation. As a lexical class, MWEs include a wide variety of idioms, whose automatic identification are a necessity for the…

We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Such generation probability can be factorized into the…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient…

Most machine vision tasks (e.g., semantic segmentation) are based on images encoded and decoded by image compression algorithms (e.g., JPEG). However, these decoded images in the pixel domain introduce distortion, and they are optimized for…

Subgraph matching is a NP-complete problem that extracts isomorphic embeddings of a query graph $q$ in a data graph $G$. In this paper, we present a framework with three components: Preprocessing, Reordering and Enumeration. While pruning…

Keyphrase extraction (KPE) is an important task in Natural Language Processing for many scenarios, which aims to extract keyphrases that are present in a given document. Many existing supervised methods treat KPE as sequential labeling,…

In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly…

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the…

Programming by Example (PBE) targets at automatically inferring a computer program for accomplishing a certain task from sample input and output. In this paper, we propose a deep neural networks (DNN) based PBE model called Neural…

We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation.…

We revisit the idea of using deep neural networks for one-shot decoding of random and structured codes, such as polar codes. Although it is possible to achieve maximum a posteriori (MAP) bit error rate (BER) performance for both code…

Conventional neural machine translation (NMT) models typically use subwords and words as the basic units for model input and comprehension. However, complete words and phrases composed of several tokens are often the fundamental units for…

Estimating noise information exactly is crucial for noise aware training in speech applications including speech enhancement (SE) which is our focus in this paper. To estimate noise-only frames, we employ voice activity detection (VAD) to…

In recent years, neural machine translation (NMT) has become the dominant approach in automated translation. However, like many other deep learning approaches, NMT suffers from overfitting when the amount of training data is limited. This…

Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence…

Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially ambiguous and…

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…