Raphael Shu


2021

pdf
GraphPlan: Story Generation by Planning with Event Graph
Hong Chen | Raphael Shu | Hiroya Takamura | Hideki Nakayama
Proceedings of the 14th International Conference on Natural Language Generation

Story generation is a task that aims to automatically generate a meaningful story. This task is challenging because it requires high-level understanding of the semantic meaning of sentences and causality of story events. Naivesequence-to-sequence models generally fail to acquire such knowledge, as it is difficult to guarantee logical correctness in a text generation model without strategic planning. In this study, we focus on planning a sequence of events assisted by event graphs and use the events to guide the generator. Rather than using a sequence-to-sequence model to output a sequence, as in some existing works, we propose to generate an event sequence by walking on an event graph. The event graphs are built automatically based on the corpus. To evaluate the proposed approach, we incorporate human participation, both in event planning and story generation. Based on the largescale human annotation results, our proposed approach has been shown to provide more logically correct event sequences and stories compared with previous approaches.

2020

pdf
Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
Jason Lee | Raphael Shu | Kyunghyun Cho
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et al., 2020), we train an inference network to approximate the gradient of the marginal log probability of the target sentence, using the latent variable instead. This allows us to use gradient-based optimization to find the target sentence at inference time that approximately maximizes its marginal probability. As each refinement step only involves computation in the latent space of low dimensionality (we use 8 in our experiments), we avoid computational overhead incurred by existing non-autoregressive inference procedures that often refine in token space. We compare our approach to a recently proposed EM-like inference procedure (Shu et al., 2020) that optimizes in a hybrid space, consisting of both discrete and continuous variables. We evaluate our approach on WMT’14 En→De, WMT’16 Ro→En and IWSLT’16 De→En, and observe two advantages over the EM-like inference: (1) it is computationally efficient, i.e. each refinement step is twice as fast, and (2) it is more effective, resulting in higher marginal probabilities and BLEU scores with the same number of refinement steps. On WMT’14 En→De, for instance, our approach is able to decode 6.2 times faster than the autoregressive model with minimal degradation to translation quality (0.9 BLEU).

2019

pdf bib
Enabling Real-time Neural IME with Incremental Vocabulary Selection
Jiali Yao | Raphael Shu | Xinjian Li | Katsutoshi Ohtsuki | Hideki Nakayama
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)

Input method editor (IME) converts sequential alphabet key inputs to words in a target language. It is an indispensable service for billions of Asian users. Although the neural-based language model is extensively studied and shows promising results in sequence-to-sequence tasks, applying a neural-based language model to IME was not considered feasible due to high latency when converting words on user devices. In this work, we articulate the bottleneck of neural IME decoding to be the heavy softmax computation over a large vocabulary. We propose an approach that incrementally builds a subset vocabulary from the word lattice. Our approach always computes the probability with a selected subset vocabulary. When the selected vocabulary is updated, the stale probabilities in previous steps are fixed by recomputing the missing logits. The experiments on Japanese IME benchmark shows an over 50x speedup for the softmax computations comparing to the baseline, reaching real-time speed even on commodity CPU without losing conversion accuracy. The approach is potentially applicable to other incremental sequence-to-sequence decoding tasks such as real-time continuous speech recognition.

pdf
Generating Diverse Translations with Sentence Codes
Raphael Shu | Hideki Nakayama | Kyunghyun Cho
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Users of machine translation systems may desire to obtain multiple candidates translated in different ways. In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation. We describe two methods to extract the codes, either with or without the help of syntax information. For diverse generation, we sample multiple candidates, each of which conditioned on a unique code. Experiments show that the sampled translations have much higher diversity scores when using reasonable sentence codes, where the translation quality is still on par with the baselines even under strong constraint imposed by the codes. In qualitative analysis, we show that our method is able to generate paraphrase translations with drastically different structures. The proposed approach can be easily adopted to existing translation systems as no modification to the model is required.

2018

pdf
Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation
Raphael Shu | Hideki Nakayama
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

To achieve high translation performance, neural machine translation models usually rely on the beam search algorithm for decoding sentences. The beam search finds good candidate translations by considering multiple hypotheses of translations simultaneously. However, as the algorithm produces hypotheses in a monotonic left-to-right order, a hypothesis can not be revisited once it is discarded. We found such monotonicity forces the algorithm to sacrifice some good decoding paths. To mitigate this problem, we relax the monotonic constraint of the beam search by maintaining all found hypotheses in a single priority queue and using a universal score function for hypothesis selection. The proposed algorithm allows discarded hypotheses to be recovered in a later step. Despite its simplicity, we show that the proposed decoding algorithm enhances the quality of selected hypotheses and improve the translations even for high-performance models in English-Japanese translation task.

2017

pdf bib
An Empirical Study of Adequate Vision Span for Attention-Based Neural Machine Translation
Raphael Shu | Hideki Nakayama
Proceedings of the First Workshop on Neural Machine Translation

Recently, the attention mechanism plays a key role to achieve high performance for Neural Machine Translation models. However, as it computes a score function for the encoder states in all positions at each decoding step, the attention model greatly increases the computational complexity. In this paper, we investigate the adequate vision span of attention models in the context of machine translation, by proposing a novel attention framework that is capable of reducing redundant score computation dynamically. The term “vision span”’ means a window of the encoder states considered by the attention model in one step. In our experiments, we found that the average window size of vision span can be reduced by over 50% with modest loss in accuracy on English-Japanese and German-English translation tasks.

2016

pdf
Residual Stacking of RNNs for Neural Machine Translation
Raphael Shu | Akiva Miura
Proceedings of the 3rd Workshop on Asian Translation (WAT2016)

To enhance Neural Machine Translation models, several obvious ways such as enlarging the hidden size of recurrent layers and stacking multiple layers of RNN can be considered. Surprisingly, we observe that using naively stacked RNNs in the decoder slows down the training and leads to degradation in performance. In this paper, We demonstrate that applying residual connections in the depth of stacked RNNs can help the optimization, which is referred to as residual stacking. In empirical evaluation, residual stacking of decoder RNNs gives superior results compared to other methods of enhancing the model with a fixed parameter budget. Our submitted systems in WAT2016 are based on a NMT model ensemble with residual stacking in the decoder. To further improve the performance, we also attempt various methods of system combination in our experiments.

pdf
Generating Video Description using Sequence-to-sequence Model with Temporal Attention
Natsuda Laokulrat | Sang Phan | Noriki Nishida | Raphael Shu | Yo Ehara | Naoaki Okazaki | Yusuke Miyao | Hideki Nakayama
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Automatic video description generation has recently been getting attention after rapid advancement in image caption generation. Automatically generating description for a video is more challenging than for an image due to its temporal dynamics of frames. Most of the work relied on Recurrent Neural Network (RNN) and recently attentional mechanisms have also been applied to make the model learn to focus on some frames of the video while generating each word in a describing sentence. In this paper, we focus on a sequence-to-sequence approach with temporal attention mechanism. We analyze and compare the results from different attention model configuration. By applying the temporal attention mechanism to the system, we can achieve a METEOR score of 0.310 on Microsoft Video Description dataset, which outperformed the state-of-the-art system so far.