Byte Pair Encoding

NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, …...

For efficiency considerations, state-of-the- art neural machine translation (NMT) re- quires the vocabulary to be restricted to a limited-size set of several thousand sym- bols. This is highly problematic when …...

AbstractIn this paper, we describe GTCOM’s neural machine translation(NMT) systems for the International Workshop on Spoken Language Translation(IWSLT) 2017. We participated in the English-to-Chinese and Chinese-to-English tracks in the small …...

We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, …...

This paper investigates the robustness of NLP against perturbed word forms. While neural approaches can achieve (almost) human-like accuracy for certain tasks and conditions, they often are sensitive to small …...

AbstractThis paper presents Prompsit Language Engineering’s submission to the IWSLT 2018 Low Resource Machine Translation task. Our submission is based on cross-lingual learning: a multilingual neural machine translation system was …...

AbstractFor unsegmented languages such as Japanese and Chinese, tokenization of a sentence has a significant impact on the performance of text classification. Sentences are usually segmented with words or subwords …...

AbstractMost pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split …...

AbstractA large number of significant assets are available online in English, which is frequently translated into native languages to ease the information sharing among local people who are not much …...

AbstractWe introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method …...

Lifelong topic models mainly focus on in- domain text streams in which each chunk only contains documents from a single domain. To overcome data diversity of the in-domain cor- pus, …...

AbstractDeciphering historical substitution ciphers is a challenging problem. Example problems that have been previously studied include detecting cipher type, detecting plaintext language, and acquiring the substitution key for segmented ciphers. …...

AbstractNeural machine translation (NMT) has achieved state-of-art performance in high-resource language pairs, but the performance of NMT drops in low-resource conditions. Morphologically rich languages are yet another challenge in NMT. …...

AbstractNeural machine translation has been shown to outperform all other machine translation paradigms when trained in a high-resource setting. However, it still performs poorly when dealing with low-resource languages, for …...