arXiv subjects

Long Zhou

Publications and source records attributed to Long Zhou.

64 records · Page 4Linked to original sources

arXiv2019

Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential benefits of lower latency, smaller model size, and less error propagation. However, it is notoriously difficult to implement such a model without transcriptions as intermediate. Existing works generally apply multi-task learning to improve translation quality by jointly training end-to-end ST along with automatic speech recognition (ASR). However, different tasks in this method cannot utilize information from each other, which limits the improvement. Other works propose a two-stage model where the second model can use the hidden state from the first one, but its cascade manner greatly affects the efficiency of training and inference process. In this paper, we propose a novel interactive attention mechanism which enables ASR and ST to perform synchronously and interactively in a single model. Specifically, the generation of transcriptions and translations not only relies on its previous outputs but also the outputs predicted in the other task. Experiments on TED speech translation corpora have shown that our proposed model can outperform strong baselines on the quality of speech translation and achieve better speech recognition performances as well.

cs.CL↗

arXiv2019

Sequence Generation: From Both Sides to the Middle

The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually generates a sequence token by token from left to right, hence (1) this autoregressive decoding procedure is time-consuming when the output sentence becomes longer, and (2) it lacks the guidance of future context which is crucial to avoid under translation. To alleviate these issues, we propose a synchronous bidirectional sequence generation (SBSG) model which predicts its outputs from both sides to the middle simultaneously. In the SBSG model, we enable the left-to-right (L2R) and right-to-left (R2L) generation to help and interact with each other by leveraging interactive bidirectional attention network. Experiments on neural machine translation (En-De, Ch-En, and En-Ro) and text summarization tasks show that the proposed model significantly speeds up decoding while improving the generation quality compared to the autoregressive Transformer.

cs.CL↗

arXiv2019

Synchronous Bidirectional Neural Machine Translation

Existing approaches to neural machine translation (NMT) generate the target language sequence token by token from left to right. However, this kind of unidirectional decoding framework cannot make full use of the target-side future contexts which can be produced in a right-to-left decoding direction, and thus suffers from the issue of unbalanced outputs. In this paper, we introduce a synchronous bidirectional neural machine translation (SB-NMT) that predicts its outputs using left-to-right and right-to-left decoding simultaneously and interactively, in order to leverage both of the history and future information at the same time. Specifically, we first propose a new algorithm that enables synchronous bidirectional decoding in a single model. Then, we present an interactive decoding model in which left-to-right (right-to-left) generation does not only depend on its previously generated outputs, but also relies on future contexts predicted by right-to-left (left-to-right) decoding. We extensively evaluate the proposed SB-NMT model on large-scale NIST Chinese-English, WMT14 English-German, and WMT18 Russian-English translation tasks. Experimental results demonstrate that our model achieves significant improvements over the strong Transformer model by 3.92, 1.49 and 1.04 BLEU points respectively, and obtains the state-of-the-art performance on Chinese-English and English-German translation tasks.

cs.CL↗

arXiv2019

Synchronous Bidirectional Inference for Neural Sequence Generation

In sequence to sequence generation tasks (e.g. machine translation and abstractive summarization), inference is generally performed in a left-to-right manner to produce the result token by token. The neural approaches, such as LSTM and self-attention networks, are now able to make full use of all the predicted history hypotheses from left side during inference, but cannot meanwhile access any future (right side) information and usually generate unbalanced outputs in which left parts are much more accurate than right ones. In this work, we propose a synchronous bidirectional inference model to generate outputs using both left-to-right and right-to-left decoding simultaneously and interactively. First, we introduce a novel beam search algorithm that facilitates synchronous bidirectional decoding. Then, we present the core approach which enables left-to-right and right-to-left decoding to interact with each other, so as to utilize both the history and future predictions simultaneously during inference. We apply the proposed model to both LSTM and self-attention networks. In addition, we propose two strategies for parameter optimization. The extensive experiments on machine translation and abstractive summarization demonstrate that our synchronous bidirectional inference model can achieve remarkable improvements over the strong baselines.

cs.CL↗

arXiv2018

Language-Independent Representor for Neural Machine Translation

Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation. This language-dependent design leads to large-scale network parameters and makes the duality of the parallel data underutilized. To address the problem, we propose in this paper a language-independent representor to replace the encoder and decoder by using weight sharing. This shared representor can not only reduce large portion of network parameters, but also facilitate us to fully explore the language duality by jointly training source-to-target, target-to-source, left-to-right and right-to-left translations within a multi-task learning framework. Experiments show that our proposed framework can obtain significant improvements over conventional NMT models on resource-rich and low-resource translation tasks with only a quarter of parameters.

cs.CL↗

arXiv2018

Multiplicity Dependence of Charged Particle, $ϕ$ Meson and Multi-strange Particle Productions in p+p Collisions at $\sqrt{\rm s}$ = 200 GeV with PYTHIA Simulation

We report the multiplicity dependence of charged particle productions for $π^{\pm}$, $K^{\pm}$, $p$, $\overline{p}$ and $ϕ$ meson at $|y| < 1.0$ in p+p collisions at $\sqrt{\rm s}$ = 200 GeV with $\rm PYTHIA$ simulation. The impact of parton multiple interactions and gluon contributions is studied and found to be possible sources of the particle yields splitting as a function of $p_T$ with respect to multiplicity. No obvious particle species dependence for the splitting is observed. The multiplicity dependence on ratios of $K^-/π^-$, $K^+/π^+$, $\overline{p}/π^-$, $p/π^+$ and $Λ/K^{0}_{s}$ in mid-rapidity in p+p collisions is found following the similar tendency as that in Au+Au collisions at $\sqrt{s_{NN}}$ = 200 GeV from RHIC, which heralds the similar underlying initial production mechanisms despite the differences in the initial colliding systems.

hep-ph↗

arXiv2017

Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT

Neural machine translation (NMT), a new approach to machine translation, has been proved to outperform conventional statistical machine translation (SMT) across a variety of language pairs. Translation is an open-vocabulary problem, but most existing NMT systems operate with a fixed vocabulary, which causes the incapability of translating rare words. This problem can be alleviated by using different translation granularities, such as character, subword and hybrid word-character. Translation involving Chinese is one of the most difficult tasks in machine translation, however, to the best of our knowledge, there has not been any other work exploring which translation granularity is most suitable for Chinese in NMT. In this paper, we conduct an extensive comparison using Chinese-English NMT as a case study. Furthermore, we discuss the advantages and disadvantages of various translation granularities in detail. Our experiments show that subword model performs best for Chinese-to-English translation with the vocabulary which is not so big while hybrid word-character model is most suitable for English-to-Chinese translation. Moreover, experiments of different granularities show that Hybrid_BPE method can achieve best result on Chinese-to-English translation task.

cs.CL↗

arXiv2017

Look-ahead Attention for Generation in Neural Machine Translation

The attention model has become a standard component in neural machine translation (NMT) and it guides translation process by selectively focusing on parts of the source sentence when predicting each target word. However, we find that the generation of a target word does not only depend on the source sentence, but also rely heavily on the previous generated target words, especially the distant words which are difficult to model by using recurrent neural networks. To solve this problem, we propose in this paper a novel look-ahead attention mechanism for generation in NMT, which aims at directly capturing the dependency relationship between target words. We further design three patterns to integrate our look-ahead attention into the conventional attention model. Experiments on NIST Chinese-to-English and WMT English-to-German translation tasks show that our proposed look-ahead attention mechanism achieves substantial improvements over state-of-the-art baselines.

cs.CL↗

arXiv2017

Neural System Combination for Machine Translation

Neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy. It is therefore a promising direction to combine the advantages of both NMT and SMT. In this paper, we propose a neural system combination framework leveraging multi-source NMT, which takes as input the outputs of NMT and SMT systems and produces the final translation. Extensive experiments on the Chinese-to-English translation task show that our model archives significant improvement by 5.3 BLEU points over the best single system output and 3.4 BLEU points over the state-of-the-art traditional system combination methods.

cs.CL↗

arXiv2017

Measurements of $Λ_c^+$ and $D_s^+$ productions in Au+Au collisions at $\sqrt{s_{NN}}$ = 200 GeV from STAR

We report the first measurement of $Λ_c^+$ (average of $Λ_c^+$ and $\barΛ_c^-$) baryon production and significantly improved measurement of $D_s^+$ (average of $D_s^+$ and $D_s^-$) meson production, within the rapidity range of $\left|y\right| < 1$ in Au+Au collisions at $\sqrt{s_{\rm NN}}$ = 200 GeV from the STAR experiment. The transverse momentum spectra of $Λ_c^+$ and $D_s^+$ as well as their yield ratios to that of $D^0$ meson are also presented and compared to theoretical calculations.Both the $Λ_c^+/D^0$ and $D_s^+/D^0$ ratios are found to be significantly enhanced in Au+Au collisions with respect to those in p+p collisions predicted by PYTHIA. A model calculation including coalescence hadronization and thermalized charm quarks is consistent with the measured $Λ_c^+/D^0$ ratio. On the other hand, the TAMU model seems to underestimate the $D_s^+/D^0$ ratio measured in Au+Au collisions in the applicable kinematic region.

nucl-ex↗