Learning Shared Semantic Space for Speech-to-Text Translation

Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its sibling - text machine translation (MT). With text and audio inputs represented differently, the modality gap has rendered MT data and its end-to-end models incompatible with their ST counterparts. In observation of this obstacle, we propose to bridge this representation gap with Chimera. By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art. Specifically, Chimera obtains 27.1 BLEU on MuST-C EN-DE, improving the SOTA by a +1.9 BLEU margin. Further experimental analyses demonstrate that the shared semantic space indeed conveys common knowledge between these two tasks and thus paves a new way for augmenting training resources across modalities. Code, data, and resources are available at https://github.com/Glaciohound/Chimera-ST.

Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge

Knowledge facts are typically represented by relational triples, while we observe that some commonsense facts are represented by the triples whose forms are inconsistent with the expression of language. This inconsistency puts forward a challenge for pre-trained language models to deal with these commonsense knowledge facts. In this paper, we term such knowledge as deep commonsense knowledge and conduct extensive exploratory experiments on it. We show that deep commonsense knowledge occupies a significant part of commonsense knowledge while conventional methods fail to capture it effectively. We further propose a novel method to mine the deep commonsense knowledge distributed in sentences, alleviating the reliance of conventional methods on the triple representation form of knowledge. Experiments demonstrate that the proposal significantly improves the performance in mining deep commonsense knowledge.

Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker

Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task: a) the target event arguments are scattered across sentences; b) the correlation among events in a document is non-trivial to model. In this paper, we propose Heterogeneous Graph-based Interaction Model with a Tracker (GIT) to solve the aforementioned two challenges. For the first challenge, GIT constructs a heterogeneous graph interaction network to capture global interactions among different sentences and entity mentions. For the second, GIT introduces a Tracker module to track the extracted events and hence capture the interdependency among the events. Experiments on a large-scale dataset (Zheng et al., 2019) show GIT outperforms the previous methods by 2.8 F1. Further analysis reveals GIT is effective in extracting multiple correlated events and event arguments that scatter across the document. Our code is available at https://github.com/RunxinXu/GIT.

Personalized Transformer for Explainable Recommendation

Personalization of natural language generation plays a vital role in a large spectrum of tasks, such as explainable recommendation, review summarization and dialog systems. In these tasks, user and item IDs are important identifiers for personalization. Transformer, which is demonstrated with strong language modeling capability, however, is not personalized and fails to make use of the user and item IDs since the ID tokens are not even in the same semantic space as the words. To address this problem, we present a PErsonalized Transformer for Explainable Recommendation (PETER), on which we design a simple and effective learning objective that utilizes the IDs to predict the words in the target explanation, so as to endow the IDs with linguistic meanings and to achieve personalized Transformer. Besides generating explanations, PETER can also make recommendations, which makes it a unified model for the whole recommendation-explanation pipeline. Extensive experiments show that our small unpretrained model outperforms fine-tuned BERT on the generation task, in terms of both effectiveness and efficiency, which highlights the importance and the nice utility of our design.

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. Our intuition is based on the hypothesis that a universal cross-language representation leads to better multilingual translation performance. To this end, we propose \method, a training method to obtain a single unified multilingual translation model. mCOLT is empowered by two techniques: (i) a contrastive learning scheme to close the gap among representations of different languages, and (ii) data augmentation on both multiple parallel and monolingual data to further align token representations. For English-centric directions, mCOLT achieves competitive or even better performance than a strong pre-trained model mBART on tens of WMT benchmarks. For non-English directions, mCOLT achieves an improvement of average 10+ BLEU compared with the multilingual baseline.

Learning Language Specific Sub-network for Multilingual Machine Translation

Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradation on rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS to jointly train a single unified multilingual MT model. LaSS learns Language Specific Sub-network (LaSS) for each language pair to counter parameter interference. Comprehensive experiments on IWSLT and WMT datasets with various Transformer architectures show that LaSS obtains gains on 36 language pairs by up to 1.2 BLEU. Besides, LaSS shows its strong generalization performance at easy extension to new language pairs and zero-shot translation.LaSS boosts zero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codes and trained models are available at https://github.com/NLP-Playground/LaSS.

Unsupervised MMRegNet based on Spatially Encoded Gradient Information

Multi-modality medical images can provide relevant and complementary anatomical information for a target (organ, tumor or tissue). Registering the multi-modality images to a common space can fuse these comprehensive information, and bring convenience for clinical application. Recently, neural networks have been widely investigated to boost registration methods. However, it is still challenging to develop a multi-modality registration network due to the lack of robust criteria for network training. Besides, most existing registration networks mainly focus on pairwise registration, and can hardly be applicable for multiple image scenarios. In this work, we propose a multi-modality registration network (MMRegNet), which can jointly register multiple images with different modalities to a target image. Meanwhile, we present spatially encoded gradient information to train the MMRegNet in an unsupervised manner. The proposed network was evaluated on two datasets, i.e, MM-WHS 2017 and CHAOS 2019. The results show that the proposed network can achieve promising performance for cardiac left ventricle and liver registration tasks. Source code is released publicly on github.

The Volctrans Neural Speech Translation System for IWSLT 2021

This paper describes the systems submitted to IWSLT 2021 by the Volctrans team. We participate in the offline speech translation and text-to-text simultaneous translation tracks. For offline speech translation, our best end-to-end model achieves 8.1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution. For text-to-text simultaneous translation, we explore the best practice to optimize the wait-k model. As a result, our final submitted systems exceed the benchmark at around 7 BLEU on the same latency regime. We will publish our code and model to facilitate both future research works and industrial applications.

Duplex Sequence-to-Sequence Learning for Reversible Machine Translation

Sequence-to-sequence (seq2seq) problems such as machine translation are bidirectional, which naturally derive a pair of directional tasks and two directional learning signals. However, typical seq2seq neural networks are {\em simplex} that only model one unidirectional task, which cannot fully exploit the potential of bidirectional learning signals from parallel data. To address this issue, we propose a {\em duplex} seq2seq neural network, REDER (Reversible Duplex Transformer), and apply it to machine translation. The architecture of REDER has two ends, each of which specializes in a language so as to read and yield sequences in that language. As a result, REDER can simultaneously learn from the bidirectional signals, and enables {\em reversible machine translation} by simply flipping the input and output ends, Experiments on widely-used machine translation benchmarks verify that REDER achieves the first success of reversible machine translation, which helps obtain considerable gains over several strong baselines.