Previous studies employ the autoregressive translation (AT) paradigm in the document-to-document neural machine translation. These methods extend the translation unit from a single sentence to a pseudo-document and encodes the full pseudo-document, avoiding the redundant computation problem in context. However, the AT methods cannot parallelize decoding and struggle with error accumulation, especially when the length of sentences increases. In this work, we propose a context-aware non-autoregressive framework with the sentence-aligned connectionist temporal classification (SA-CTC) loss for document-level neural machine translation. In particular, the SA-CTC loss reduces the search space of the decoding path by fixing the positions of the beginning and end tokens for each sentence in the document. Meanwhile, the context-aware architecture introduces preset nodes to represent sentence-level information and utilizes a hierarchical attention structure to regulate the attention hypothesis space. Experimental results show that our proposed method can achieve competitive performance compared with several strong baselines. Our method implements non-autoregressive modeling in Doc-to-Doc translation manner, achieving an average 46X decoding speedup compared to the document-level AT baselines on three benchmarks.

A persistent goal of multilingual neural machine translation (MNMT) is to continually adapt the model to support new language pairs or improve some current language pairs without accessing the previous training data. To achieve this, the existing methods primarily focus on preventing catastrophic forgetting by making compromises between the original and new language pairs, leading to sub-optimal performance on both translation tasks. To mitigate this problem, we propose a dual importance-based model division method to divide the model parameters into two parts and separately model the translation of the original and new tasks. Specifically, we first remove the parameters that are negligible to the original tasks but essential to the new tasks to obtain a pruned model, which is responsible for the original translation tasks. Then we expand the pruned model with external parameters and fine-tune the newly added parameters with new training data. The whole fine-tuned model will be used for the new translation tasks. Experimental results show that our method can efficiently adapt the original model to various new translation tasks while retaining the performance of the original tasks. Further analyses demonstrate that our method consistently outperforms several strong baselines under different incremental translation scenarios.

Although existing multilingual neural machine translation (MNMT) models have demonstrated remarkable performance to handle multiple translation directions in a single model and achieved zero-shot translation between language pairs unseen in training, they still suffer from relatively poor translation qualities for some language pairs. A practical scenario is that how to continually update MNMT models for both supervised and zero-shot translations when limited new data arrives. To this end, we propose a two-stage approach that encourages original models to acquire language-agnostic multilingual representations from new data, and preserves the model architecture without introducing parameters. Experimental results and further analysis demonstrate that our method can efficiently improve performance of existing MNMT models in translation directions where they are initially weak, and mitigates the degeneration in the original well-performing translation directions, offering flexibility in the real-world scenario.

Multilingual neural machine translation aims to translate multiple language pairs in a single model and has shown great success thanks to the knowledge transfer across languages with the shared parameters. Despite promising, this share-all paradigm suffers from insufficient ability to capture language-specific features. Currently, the common practice is to insert or search language-specific networks to balance the shared and specific features. However, those two types of features are not sufficient enough to model the complex commonality and divergence across languages, such as the locally shared features among similar languages, which leads to sub-optimal transfer, especially in massively multilingual translation. In this paper, we propose a novel token-level feature mixing method that enables the model to capture different features and dynamically determine the feature sharing across languages. Based on the observation that the tokens in the multilingual model are usually shared by different languages, we we insert a feature mixing layer into each Transformer sublayer and model each token representation as a mix of different features, with a proportion indicating its feature preference. In this way, we can perform fine-grained feature sharing and achieve better multilingual transfer. Experimental results on multilingual datasets show that our method outperforms various strong baselines and can be extended to zero-shot translation. Further analyses reveal that our method can capture different linguistic features and bridge the representation gap across languages.

Abstractive dialogue summarization aims to convert a long dialogue content into its short form where the salient information is preserved while the redundant pieces are ignored. Different from the well-structured text, such as news and scientific articles, dialogues often consist of utterances coming from two or more interlocutors, where the conversations are often informal, verbose, and repetitive, sprinkled with false-starts, backchanneling, reconfirmations, hesitations, speaker interruptions and the salient information is often scattered across the whole chat. The above properties of conversations make it difficult to directly concentrate on scattered outstanding utterances and thus present new challenges of summarizing dialogues. In this work, rather than directly forcing a summarization system to merely pay more attention to the salient pieces, we propose to explicitly have the model perceive the redundant parts of an input dialogue history during the training phase. To be specific, we design two strategies to construct examples without salient pieces as negative cues. Then, the sequence-to-sequence likelihood loss is cooperated with the unlikelihood objective to drive the model to focus less on the unimportant information and also pay more attention to the salient pieces. Extensive experiments on the benchmark dataset demonstrate that our simple method significantly outperforms the baselines with regard to both semantic matching and factual consistent based metrics. The human evaluation also proves the performance gains.

This paper describes DUTNLP Lab’s submission to the WMT22 General MT Task on four translation directions: English to/from Chinese and English to/from Japanese under the constrained condition. Our primary system are built on several Transformer variants which employ wider FFN layer or deeper encoder layer. The bilingual data are filtered by detailed data pre-processing strategies and four data augmentation methods are combined to enlarge the training data with the provided monolingual data. Several common methods are also employed to further improve the model performance, such as fine-tuning, model ensemble and post-editing. As a result, our constrained systems achieve 29.01, 63.87, 41.84, and 24.82 BLEU scores on Chinese-to-English, English-to-Chinese, English-to-Japanese, and Japanese-to-English, respectively.

This paper describes DUT-NLP Lab’s submission to the WMT-21 triangular machine translation shared task. The participants are not allowed to use other data and the translation direction of this task is Russian-to-Chinese. In this task, we use the Transformer as our baseline model, and integrate several techniques to enhance the performance of the baseline, including data filtering, data selection, fine-tuning, and post-editing. Further, to make use of the English resources, such as Russian/English and Chinese/English parallel data, the relationship triangle is constructed by multilingual neural machine translation systems. As a result, our submission achieves a BLEU score of 21.9 in Russian-to-Chinese.

Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon progression and the key information for a certain topic is often scattered across multiple utterances of different speakers, which poses challenges to abstractly summarize dialogues. To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task. The proposed contrastive objectives are framed as auxiliary tasks for the primary dialogue summarization task, united via an alternative parameter updating strategy. Extensive experiments on benchmark datasets demonstrate that the proposed simple method significantly outperforms strong baselines and achieves new state-of-the-art performance. The code and trained models are publicly available via .

Precise information of word boundary can alleviate the problem of lexical ambiguity to improve the performance of natural language processing (NLP) tasks. Thus, Chinese word segmentation (CWS) is a fundamental task in NLP. Due to the development of pre-trained language models (PLM), pre-trained knowledge can help neural methods solve the main problems of the CWS in significant measure. Existing methods have already achieved high performance on several benchmarks (e.g., Bakeoff-2005). However, recent outstanding studies are limited by the small-scale annotated corpus. To further improve the performance of CWS methods based on fine-tuning the PLMs, we propose a novel neural framework, LBGCN, which incorporates a lexicon-based graph convolutional network into the Transformer encoder. Experimental results on five benchmarks and four cross-domain datasets show the lexicon-based graph convolutional network successfully captures the information of candidate words and helps to improve performance on the benchmarks (Bakeoff-2005 and CTB6) and the cross-domain datasets (SIGHAN-2010). Further experiments and analyses demonstrate that our proposed framework effectively models the lexicon to enhance the ability of basic neural frameworks and strengthens the robustness in the cross-domain scenario.

Previous neural approaches achieve significant progress for Chinese word segmentation (CWS) as a sentence-level task, but it suffers from limitations on real-world scenario. In this paper, we address this issue with a context-aware method and optimize the solution at document-level. This paper proposes a three-step strategy to improve the performance for discourse CWS. First, the method utilizes an auxiliary segmenter to remedy the limitation on pre-segmenter. Then the context-aware algorithm computes the confidence of each split. The maximum probability path is reconstructed via this algorithm. Besides, in order to evaluate the performance in discourse, we build a new benchmark consisting of the latest news and Chinese medical articles. Extensive experiments on this benchmark show that our proposed method achieves a competitive performance on a document-level real-world scenario for CWS.