arXiv subjects

Zhaopeng Tu

Publications and source records attributed to Zhaopeng Tu.

At least 127 records · Page 7Linked to original sources

arXiv2020

On the Sub-Layer Functionalities of Transformer Decoder

There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains largely unexamined despite its critical role. During translation, the decoder must predict output tokens by considering both the source-language text from the encoder and the target-language prefix produced in previous steps. In this work, we study how Transformer-based decoders leverage information from the source and target languages -- developing a universal probe task to assess how information is propagated through each module of each decoder layer. We perform extensive experiments on three major translation datasets (WMT En-De, En-Fr, and En-Zh). Our analysis provides insight on when and where decoders leverage different sources. Based on these insights, we demonstrate that the residual feed-forward module in each Transformer decoder layer can be dropped with minimal loss of performance -- a significant reduction in computation and number of parameters, and consequently a significant boost to both training and inference speed.

cs.CL↗

arXiv2020

On the Inference Calibration of Neural Machine Translation

Confidence calibration, which aims to make model predictions equal to the true correctness measures, is important for neural machine translation (NMT) because it is able to offer useful indicators of translation errors in the generated output. While prior studies have shown that NMT models trained with label smoothing are well-calibrated on the ground-truth training data, we find that miscalibration still remains a severe challenge for NMT during inference due to the discrepancy between training and inference. By carefully designing experiments on three language pairs, our work provides in-depth analyses of the correlation between calibration and translation performance as well as linguistic properties of miscalibration and reports a number of interesting findings that might help humans better analyze, understand and improve NMT models. Based on these observations, we further propose a new graduated label smoothing method that can improve both inference calibration and translation performance.

cs.CL↗

arXiv2020

How Does Selective Mechanism Improve Self-Attention Networks?

Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words. However, the underlying reasons for their strong performance have not been well explained. In this paper, we bridge the gap by assessing the strengths of selective SANs (SSANs), which are implemented with a flexible and universal Gumbel-Softmax. Experimental results on several representative NLP tasks, including natural language inference, semantic role labelling, and machine translation, show that SSANs consistently outperform the standard SANs. Through well-designed probing experiments, we empirically validate that the improvement of SSANs can be attributed in part to mitigating two commonly-cited weaknesses of SANs: word order encoding and structure modeling. Specifically, the selective mechanism improves SANs by paying more attention to content words that contribute to the meaning of the sentence. The code and data are released at https://github.com/xwgeng/SSAN.

cs.CL↗

arXiv2020

Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models

Machine translation (MT) systems translate text between different languages by automatically learning in-depth knowledge of bilingual lexicons, grammar and semantics from the training examples. Although neural machine translation (NMT) has led the field of MT, we have a poor understanding on how and why it works. In this paper, we bridge the gap by assessing the bilingual knowledge learned by NMT models with phrase table -- an interpretable table of bilingual lexicons. We extract the phrase table from the training examples that an NMT model correctly predicts. Extensive experiments on widely-used datasets show that the phrase table is reasonable and consistent against language pairs and random seeds. Equipped with the interpretable phrase table, we find that NMT models learn patterns from simple to complex and distill essential bilingual knowledge from the training examples. We also revisit some advances that potentially affect the learning of bilingual knowledge (e.g., back-translation), and report some interesting findings. We believe this work opens a new angle to interpret NMT with statistic models, and provides empirical supports for recent advances in improving NMT models.

cs.CL↗

arXiv2020

Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory

For dialogue response generation, traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways. Consequentially, those models tend to output generic and dull responses, impeding the generation of informative utterances. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. When generating a response for a current query, similar dialogues retrieved from the entire training data are considered as an additional knowledge source. While this may harvest massive information, the generative models could be overwhelmed, leading to undesirable performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-then-response paradigm. At first, a skeleton is generated by revising the retrieved responses. Then, a novel generative model uses both the generated skeleton and the original query for response generation. Experimental results show that our approaches significantly improve the diversity and informativeness of the generated responses.

cs.CL↗

arXiv2019

Neuron Interaction Based Representation Composition for Neural Machine Translation

Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better capture complex information by composing the linguistic properties embedded in individual neurons. Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e.g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors. Specifically, we leverage bilinear pooling to model pairwise multiplicative interactions among individual neurons, and a low-rank approximation to make the model computationally feasible. We further propose extended bilinear pooling to incorporate first-order representations. Experiments on WMT14 English-German and English-French translation tasks show that our model consistently improves performances over the SOTA Transformer baseline. Further analyses demonstrate that our approach indeed captures more syntactic and semantic information as expected.

cs.CL↗

arXiv2019

Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks

The key challenge of multi-domain translation lies in simultaneously encoding both the general knowledge shared across domains and the particular knowledge distinctive to each domain in a unified model. Previous work shows that the standard neural machine translation (NMT) model, trained on mixed-domain data, generally captures the general knowledge, but misses the domain-specific knowledge. In response to this problem, we augment NMT model with additional domain transformation networks to transform the general representations to domain-specific representations, which are subsequently fed to the NMT decoder. To guarantee the knowledge transformation, we also propose two complementary supervision signals by leveraging the power of knowledge distillation and adversarial learning. Experimental results on several language pairs, covering both balanced and unbalanced multi-domain translation, demonstrate the effectiveness and universality of the proposed approach. Encouragingly, the proposed unified model achieves comparable results with the fine-tuning approach that requires multiple models to preserve the particular knowledge. Further analyses reveal that the domain transformation networks successfully capture the domain-specific knowledge as expected.

cs.CL↗

arXiv2019

Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons

Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work. With the belief that modeling hierarchical structure is an essential complementary between SANs and RNNs, we propose to further enhance the strength of hybrid models with an advanced variant of RNNs - Ordered Neurons LSTM (ON-LSTM), which introduces a syntax-oriented inductive bias to perform tree-like composition. Experimental results on the benchmark machine translation task show that the proposed approach outperforms both individual architectures and a standard hybrid model. Further analyses on targeted linguistic evaluation and logical inference tasks demonstrate that the proposed approach indeed benefits from a better modeling of hierarchical structure.

cs.CL↗

arXiv2019

Dynamic Past and Future for Neural Machine Translation

Previous studies have shown that neural machine translation (NMT) models can benefit from explicitly modeling translated (Past) and untranslated (Future) to groups of translated and untranslated contents through parts-to-wholes assignment. The assignment is learned through a novel variant of routing-by-agreement mechanism (Sabour et al., 2017), namely {\em Guided Dynamic Routing}, where the translating status at each decoding step {\em guides} the routing process to assign each source word to its associated group (i.e., translated or untranslated content) represented by a capsule, enabling translation to be made from holistic context. Experiments show that our approach achieves substantial improvements over both RNMT and Transformer by producing more adequate translations. Extensive analysis demonstrates that our method is highly interpretable, which is able to recognize the translated and untranslated contents as expected.

cs.CL↗

arXiv2019

Towards Understanding Neural Machine Translation with Word Importance

Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory. In this work, we propose to address this gap by focusing on understanding the input-output behavior of NMT models. Specifically, we measure the word importance by attributing the NMT output to every input word through a gradient-based method. We validate the approach on a couple of perturbation operations, language pairs, and model architectures, demonstrating its superiority on identifying input words with higher influence on translation performance. Encouragingly, the calculated importance can serve as indicators of input words that are under-translated by NMT models. Furthermore, our analysis reveals that words of certain syntactic categories have higher importance while the categories vary across language pairs, which can inspire better design principles of NMT architectures for multi-lingual translation.

cs.CL↗

arXiv2019

Multi-Granularity Self-Attention for Neural Machine Translation

Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information. However, prior work on statistical machine translation has shown that extending the basic translation unit from words to phrases has produced substantial improvements, suggesting the possibility of improving NMT performance from explicit modeling of phrases. In this work, we present multi-granularity self-attention (Mg-Sa): a neural network that combines multi-head self-attention and phrase modeling. Specifically, we train several attention heads to attend to phrases in either n-gram or syntactic formalism. Moreover, we exploit interactions among phrases to enhance the strength of structure modeling - a commonly-cited weakness of self-attention. Experimental results on WMT14 English-to-German and NIST Chinese-to-English translation tasks show the proposed approach consistently improves performance. Targeted linguistic analysis reveals that Mg-Sa indeed captures useful phrase information at various levels of granularities.

cs.CL↗

arXiv2019

One Model to Learn Both: Zero Pronoun Prediction and Translation

Zero pronouns (ZPs) are frequently omitted in pro-drop languages, but should be recalled in non-pro-drop languages. This discourse phenomenon poses a significant challenge for machine translation (MT) when translating texts from pro-drop to non-pro-drop languages. In this paper, we propose a unified and discourse-aware ZP translation approach for neural MT models. Specifically, we jointly learn to predict and translate ZPs in an end-to-end manner, allowing both components to interact with each other. In addition, we employ hierarchical neural networks to exploit discourse-level context, which is beneficial for ZP prediction and thus translation. Experimental results on both Chinese-English and Japanese-English data show that our approach significantly and accumulatively improves both translation performance and ZP prediction accuracy over not only baseline but also previous works using external ZP prediction models. Extensive analyses confirm that the performance improvement comes from the alleviation of different kinds of errors especially caused by subjective ZPs.

cs.CL↗

arXiv2019

Self-Attention with Structural Position Representations

Although self-attention networks (SANs) have advanced the state-of-the-art on various NLP tasks, one criticism of SANs is their ability of encoding positions of input words (Shaw et al., 2018). In this work, we propose to augment SANs with structural position representations to model the latent structure of the input sentence, which is complementary to the standard sequential positional representations. Specifically, we use dependency tree to represent the grammatical structure of a sentence, and propose two strategies to encode the positional relationships among words in the dependency tree. Experimental results on NIST Chinese-to-English and WMT14 English-to-German translation tasks show that the proposed approach consistently boosts performance over both the absolute and relative sequential position representations.

cs.CL↗

arXiv2019

Exploiting Sentential Context for Neural Machine Translation

In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT). Specifically, we first show that a shallow sentential context extracted from the top encoder layer only, can improve translation performance via contextualizing the encoding representations of individual words. Next, we introduce a deep sentential context, which aggregates the sentential context representations from all the internal layers of the encoder to form a more comprehensive context representation. Experimental results on the WMT14 English-to-German and English-to-French benchmarks show that our model consistently improves performance over the strong TRANSFORMER model (Vaswani et al., 2017), demonstrating the necessity and effectiveness of exploiting sentential context for NMT.

cs.CL↗

arXiv2019

Assessing the Ability of Self-Attention Networks to Learn Word Order

Self-attention networks (SAN) have attracted a lot of interests due to their high parallelization and strong performance on a variety of NLP tasks, e.g. machine translation. Due to the lack of recurrence structure such as recurrent neural networks (RNN), SAN is ascribed to be weak at learning positional information of words for sequence modeling. However, neither this speculation has been empirically confirmed, nor explanations for their strong performances on machine translation tasks when "lacking positional information" have been explored. To this end, we propose a novel word reordering detection task to quantify how well the word order information learned by SAN and RNN. Specifically, we randomly move one word to another position, and examine whether a trained model can detect both the original and inserted positions. Experimental results reveal that: 1) SAN trained on word reordering detection indeed has difficulty learning the positional information even with the position embedding; and 2) SAN trained on machine translation learns better positional information than its RNN counterpart, in which position embedding plays a critical role. Although recurrence structure make the model more universally-effective on learning word order, learning objectives matter more in the downstream tasks such as machine translation.

cs.CL↗

arXiv2019

Convolutional Self-Attention Network

Self-attention network (SAN) has recently attracted increasing interest due to its fully parallelized computation and flexibility in modeling dependencies. It can be further enhanced with multi-headed attention mechanism by allowing the model to jointly attend to information from different representation subspaces at different positions (Vaswani et al., 2017). In this work, we propose a novel convolutional self-attention network (CSAN), which offers SAN the abilities to 1) capture neighboring dependencies, and 2) model the interaction between multiple attention heads. Experimental results on WMT14 English-to-German translation task demonstrate that the proposed approach outperforms both the strong Transformer baseline and other existing works on enhancing the locality of SAN. Comparing with previous work, our model does not introduce any new parameters.

cs.CL↗

arXiv2019

Modeling Recurrence for Transformer

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement of translation capacity. In response to this problem, we propose to directly model recurrence for Transformer with an additional recurrence encoder. In addition to the standard recurrent neural network, we introduce a novel attentive recurrent network to leverage the strengths of both attention and recurrent networks. Experimental results on the widely-used WMT14 English-German and WMT17 Chinese-English translation tasks demonstrate the effectiveness of the proposed approach. Our studies also reveal that the proposed model benefits from a short-cut that bridges the source and target sequences with a single recurrent layer, which outperforms its deep counterpart.

cs.CL↗

arXiv2019

Information Aggregation for Multi-Head Attention with Routing-by-Agreement

Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a linear transformation, which may not fully exploit the expressiveness of multi-head attention. In this work, we propose to improve the information aggregation for multi-head attention with a more powerful routing-by-agreement algorithm. Specifically, the routing algorithm iteratively updates the proportion of how much a part (i.e. the distinct information learned from a specific subspace) should be assigned to a whole (i.e. the final output representation), based on the agreement between parts and wholes. Experimental results on linguistic probing tasks and machine translation tasks prove the superiority of the advanced information aggregation over the standard linear transformation.

cs.CL↗