Search Results for author:
Found 110 papers, 16 papers with code
A Text Editing Approach to Joint Japanese Word Segmentation, POS Tagging, and Lexical Normalization
Lexical normalization, in addition to word segmentation and part-of-speech tagging, is a fundamental task for Japanese user-generated text processing.
Synchronous Refinement for Neural Machine Translation
Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner.
SJTU-NICT’s Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
In this paper, we introduced our joint team SJTU-NICT ‘s participation in the WMT 2020 machine translation shared task.
Unsupervised Neural Machine Translation with Universal Grammar
Machine translation usually relies on parallel corpora to provide parallel signals for training.
Restricted or Not: A General Training Framework for Neural Machine Translation
Although this can satisfy the requirements overall, it usually requires a larger beam size and far longer decoding time than unrestricted translation, which limits the concurrent processing ability of the translation model in deployment, and thus its practicality.
What Works and Doesn’t Work, A Deep Decoder for Neural Machine Translation
Inspired by this discovery, we then propose approaches to improving it, with respect to model structure and model training, to make the deep decoder practical in NMT.
NICT’s Neural Machine Translation Systems for the WAT21 Restricted Translation Task
This paper describes our system (Team ID: nictrb) for participating in the WAT’21 restricted machine translation task.
A Multimodal Simultaneous Interpretation Prototype: Who Said What
“Who said what” is essential for users to understand video streams that have more than one speaker, but conventional simultaneous interpretation systems merely present “what was said” in the form of subtitles.
Multi-Source Cross-Lingual Constituency Parsing
Pretrained multilingual language models have become a key part of cross-lingual transfer for many natural language processing tasks, even those without bilingual information.
FeatureBART: Feature Based Sequence-to-Sequence Pre-Training for Low-Resource NMT
In this paper we present FeatureBART, a linguistically motivated sequence-to-sequence monolingual pre-training strategy in which syntactic features such as lemma, part-of-speech and dependency labels are incorporated into the span prediction based pre-training framework (BART).
MiSS@WMT21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation
In this paper, we describe our MiSS system that participated in the WMT21 news translation task.
MiSS: An Assistant for Multi-Style Simultaneous Translation
With this system, we aim to provide a complete translation experience for machine translation users.
TikZero: Zero-Shot Text-Guided Graphics Program Synthesis
Meanwhile, large amounts of unaligned graphics programs and captioned raster images are more readily available.
IteRABRe: Iterative Recovery-Aided Block Reduction
Large Language Models (LLMs) have grown increasingly expensive to deploy, driving the need for effective model compression techniques.
Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation
We further scale up and collect 9. 3 billion sentence pairs across 24 languages from public datasets to pre-train two models, namely MITRE (multilingual translation with registers).
Improving Language Transfer Capability of Decoder-only Architecture in Multilingual Neural Machine Translation
We propose dividing the decoding process into two stages so that target tokens are explicitly excluded in the first stage to implicitly boost the transfer capability across languages.
On Eliciting Syntax from Language Models via Hashing
Unsupervised parsing, also known as grammar induction, aims to infer syntactic structure from raw text.
To be Continuous, or to be Discrete, Those are Bits of Questions
In this paper, we investigate the feasibility of further introducing it to the output side, aiming to allow models to output binary labels instead.
Ranked #1 on
Constituency Parsing
on Penn Treebank
Centroid-Based Efficient Minimum Bayes Risk Decoding
Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.
Universal Multimodal Representation for Language Understanding
Representation learning is the foundation of natural language processing (NLP).
Language Model Pre-training on True Negatives
Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones.
Smoothing Dialogue States for Open Conversational Machine Reading
In this work, we propose an effective gating strategy by smoothing the two dialogue states in only one decoder and bridge decision making and question generation to provide a richer dialogue state reference.
Cross-lingual Transferring of Pre-trained Contextualized Language Models
Though the pre-trained contextualized language model (PrLM) has made a significant impact on NLP, training PrLMs in languages other than English can be impractical for two reasons: other languages often lack corpora sufficient for training powerful PrLMs, and because of the commonalities among human languages, computationally expensive PrLM training for different languages is somewhat redundant.
User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization
Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT).
Text Compression-aided Transformer Encoding
In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily.
Prior Knowledge Representation for Self-Attention Networks
Self-attention networks (SANs) have shown promising empirical results in various natural language processing tasks.
Cross-lingual Transfer Learning for Pre-trained Contextualized Language Models
Though the pre-trained contextualized language model (PrLM) has made a significant impact on NLP, training PrLMs in languages other than English can be impractical for two reasons: other languages often lack corpora sufficient for training powerful PrLMs, and because of the commonalities among human languages, computationally expensive PrLM training for different languages is somewhat redundant.
Accurate Word Representations with Universal Visual Guidance
Word representation is a fundamental component in neural language understanding models.
Bilingual Subword Segmentation for Neural Machine Translation
This paper proposed a new subword segmentation method for neural machine translation, {``}Bilingual Subword Segmentation,{''} which tokenizes sentences to minimize the difference between the number of subword units in a sentence and that of its translation.
Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation
In this study, linguistic knowledge at different levels are incorporated into the neural machine translation (NMT) framework to improve translation quality for language pairs with extremely limited data.
SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
In this paper, we introduced our joint team SJTU-NICT 's participation in the WMT 2020 machine translation shared task.
A System for Worldwide COVID-19 Information Aggregation
The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education.
A Three-Parameter Rank-Frequency Relation in Natural Languages
We present that, the rank-frequency relation in textual data follows $f \propto r^{-\alpha}(r+\gamma)^{-\beta}$, where $f$ is the token frequency and $r$ is the rank by frequency, with ($\alpha$, $\beta$, $\gamma$) as parameters.
Content Word Aware Neural Machine Translation
Neural machine translation (NMT) encodes the source sentence in a universal way to generate the target sentence word-by-word.
A Myanmar (Burmese)-English Named Entity Transliteration Dictionary
For the Myanmar (Burmese) language, robust automatic transliteration for borrowed English words is a challenging task because of the complex Myanmar writing system and the lack of data.
Neural Machine Translation with Universal Visual Representation
Though visual information has been introduced for enhancing neural machine translation (NMT), its effectiveness strongly relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations.
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs.
Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks.
Explicit Reordering for Neural Machine Translation
Thus, we propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT.
Reference Language based Unsupervised Neural Machine Translation
Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism.
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training
Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community.
Modeling Future Cost for Neural Machine Translation
Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as consistent as possible.
Explicit Sentence Compression for Neural Machine Translation
In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT.
Probing Contextualized Sentence Representations with Visual Awareness
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations.
Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English
This paper presents the NICT{'}s supervised and unsupervised machine translation systems for the WAT2019 Myanmar-English and Khmer-English translation tasks.
SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing
This paper describes our SJTU-NICT{'}s system for participating in the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL).
MY-AKKHARA: A Romanization-based Burmese (Myanmar) Input Method
MY-AKKHARA is a method used to input Burmese texts encoded in the Unicode standard, based on commonly accepted Latin transcription.
Recurrent Positional Embedding for Neural Machine Translation
To address this issue, this work proposes a recurrent positional embedding approach based on word vector.
English-Myanmar Supervised and Unsupervised NMT: NICT's Machine Translation Systems at WAT-2019
This paper presents the NICT{'}s participation (team ID: NICT) in the 6th Workshop on Asian Translation (WAT-2019) shared translation task, specifically Myanmar (Burmese) - English task in both translation directions.
Document-level Neural Machine Translation with Associated Memory Network
Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network.
Hybrid Data-Model Parallel Training for Sequence-to-Sequence Recurrent Neural Network Machine Translation
We apply a model parallel approach to the RNN encoder-decoder part of the Seq2Seq model and a data parallel approach to the attention-softmax part of the model.
Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation
However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs.
NICT's Supervised Neural Machine Translation Systems for the WMT19 News Translation Task
In this paper, we describe our supervised neural machine translation (NMT) systems that we developed for the news translation task for Kazakh↔English, Gujarati↔English, Chinese↔English, and English→Finnish translation directions.
NICT's Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task
This paper presents the NICT{'}s participation in the WMT19 unsupervised news translation task.
Neural Machine Translation with Reordering Embeddings
The reordering model plays an important role in phrase-based statistical machine translation.
Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation
In previous methods, UBWE is first trained using non-parallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT.
Sentence-Level Agreement for Neural Machine Translation
The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references.
Incorporating Word Attention into Character-Based Word Segmentation
Neural network models have been actively applied to word segmentation, especially Chinese, because of the ability to minimize the effort in feature engineering.
Ranked #2 on
Japanese Word Segmentation
on BCCWJ
Improving Neural Machine Translation with Neural Syntactic Distance
The explicit use of syntactic information has been proved useful for neural machine translation (NMT).
NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task
Our systems are ranked first for the Estonian-English and Finnish-English language pairs (constraint) according to BLEU-cased.
NICT's Corpus Filtering Systems for the WMT18 Parallel Corpus Filtering Task
Using the clean data of the WMT18 shared news translation task, we designed several features and trained a classifier to score each sentence pairs in the noisy data.
Exploring Recombination for Efficient Decoding of Neural Machine Translation
In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations.
Forest-Based Neural Machine Translation
Tree-based neural machine translation (NMT) approaches, although achieved impressive performance, suffer from a major drawback: they only use the 1-best parse tree to direct the translation, which potentially introduces translation mistakes due to parsing errors.
Simplified Abugidas
An abugida is a writing system where the consonant letters represent syllables with a default vowel and other vowels are denoted by diacritics.
Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation
Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch.
Guiding Neural Machine Translation with Retrieved Translation Pieces
Specifically, for an input sentence, we use a search engine to retrieve sentence pairs whose source sides are similar with the input sentence, and then collect $n$-grams that are both in the retrieved target sentences and aligned with words that match in the source sentences, which we call "translation pieces".
CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++
This paper presents an open-source neural machine translation toolkit named CytonMT (https://github. com/arthurxlw/cytonMt).
Syntax-Directed Attention for Neural Machine Translation
In this paper, we extend local attention with syntax-distance constraint, to focus on syntactically related source words with the predicted target word, thus learning a more effective context vector for word prediction.
Improving Neural Machine Translation through Phrase-based Forced Decoding
Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency.
A Simple and Strong Baseline: NAIST-NICT Neural Machine Translation System for WAT2017 English-Japanese Translation Task
This paper describes the details about the NAIST-NICT machine translation system for WAT2017 English-Japanese Scientific Paper Translation Task.
Key-value Attention Mechanism for Neural Machine Translation
In this paper, we propose a neural machine translation (NMT) with a key-value attention mechanism on the source-side encoder.
Context-Aware Smoothing for Neural Machine Translation
In Neural Machine Translation (NMT), each word is represented as a low-dimension, real-value vector for encoding its syntax and semantic information.
Instance Weighting for Neural Machine Translation Domain Adaptation
Instance weighting has been widely applied to phrase-based machine translation domain adaptation.
Neural Machine Translation with Source Dependency Representation
Source dependency information has been successfully introduced into statistical machine translation.
Sentence Embedding for Neural Machine Translation Domain Adaptation
Although new corpora are becoming increasingly available for machine translation, only those that belong to the same or similar domains are typically able to improve translation performance.
A Prototype Automatic Simultaneous Interpretation System
Simultaneous interpretation allows people to communicate spontaneously across language boundaries, but such services are prohibitively expensive for the general public.
An Efficient and Effective Online Sentence Segmenter for Simultaneous Interpretation
Simultaneous interpretation is a very challenging application of machine translation in which the input is a stream of words from a speech recognition engine.
Global Pre-ordering for Improving Sublanguage Translation
When translating formal documents, capturing the sentence structure specific to the sublanguage is extremely necessary to obtain high-quality translations.
MuTUAL: A Controlled Authoring Support System Enabling Contextual Machine Translation
The paper introduces a web-based authoring support system, MuTUAL, which aims to help writers create multilingual texts.
Similar Southeast Asian Languages: Corpus-Based Case Study on Thai-Laotian and Malay-Indonesian
This paper illustrates the similarity between Thai and Laotian, and between Malay and Indonesian, based on an investigation on raw parallel data from Asian Language Treebank.
Neural Machine Translation with Supervised Attention
The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words.
A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique
Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information.
Connecting Phrase based Statistical Machine Translation Adaptation
Although more additional corpora are now available for Statistical Machine Translation (SMT), only the ones which belong to the same or similar domains with the original corpus can indeed enhance SMT performance directly.
Introducing the Asian Language Treebank (ALT)
The project has so far created a corpus for Myanmar and will extend in scope to include other languages in the near future.
ASPEC: Asian Scientific Paper Excerpt Corpus
In this paper, we describe the details of the ASPEC (Asian Scientific Paper Excerpt Corpus), which is the first large-size parallel corpus of scientific paper domain.
Khmer Word Segmentation Using Conditional Random Fields
The trained CRF segmenter was compared empirically to a baseline approach based on maximum matching that used a dictionary extracted from the manually segmented corpus.
