Zijian Yang

Yingbo Gao, Christian Herold, Zijian Yang et al.

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost comes for free, makes it widely adopted in neural machine translation research. Despite the popularity, the method itself simply takes the mean of the model parameters from several checkpoints, the selection of which is mostly based on empirical recipes without many justifications. In this work, we revisit the concept of checkpoint averaging and consider several extensions. Specifically, we experiment with ideas such as using different checkpoint selection strategies, calculating weighted average instead of simple mean, making use of gradient information and fine-tuning the interpolation weights on development data. Our results confirm the necessity of applying checkpoint averaging for optimal performance, but also suggest that the landscape between the converged checkpoints is rather flat and not much further improvement compared to simple averaging is to be obtained.

Yingbo Gao, Christian Herold, Zijian Yang et al.

Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Transformer networks, plus the introduction and development of attention mechanism, encoder-decoder is still the de facto neural network architecture for state-of-the-art models. While the motivation for decoding information from some hidden space is straightforward, the strict separation of the encoding and decoding steps into an encoder and a decoder in the model architecture is not necessarily a must. Compared to the task of autoregressive language modeling in the target language, machine translation simply has an additional source sentence as context. Given the fact that neural language models nowadays can already handle rather long contexts in the target language, it is natural to ask whether simply concatenating the source and target sentences and training a language model to do translation would work. In this work, we investigate the aforementioned concept for machine translation. Specifically, we experiment with bilingual translation, translation with additional target monolingual data, and multilingual translation. In all cases, this alternative approach performs on par with the baseline encoder-decoder Transformer, suggesting that an encoder-decoder architecture might be redundant for neural machine translation.

Zijian Yang, Wei Zhou, Ralf Schlüter et al.

Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obtain superior performance in hybrid models, are rarely investigated in RNN-Transducers. In this work, we propose three lattice-free training objectives, namely lattice-free maximum mutual information, lattice-free segment-level minimum Bayes risk, and lattice-free minimum Bayes risk, which are used for the final posterior output of the phoneme-based neural transducer with a limited context dependency. Compared to criteria using N-best lists, lattice-free methods eliminate the decoding step for hypotheses generation during training, which leads to more efficient training. Experimental results show that lattice-free methods gain up to 6.5% relative improvement in word error rate compared to a sequence-level cross-entropy trained model. Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance.

Zijian Yang, Wei Zhou, Ralf Schlüter et al.

Internal language model (ILM) subtraction has been widely applied to improve the performance of the RNN-Transducer with external language model (LM) fusion for speech recognition. In this work, we show that sequence discriminative training has a strong correlation with ILM subtraction from both theoretical and empirical points of view. Theoretically, we derive that the global optimum of maximum mutual information (MMI) training shares a similar formula as ILM subtraction. Empirically, we show that ILM subtraction and sequence discriminative training achieve similar effects across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context. The benefit of ILM subtraction also becomes much smaller after sequence discriminative training. We also provide an in-depth study to show that sequence discriminative training has a minimal effect on the commonly used zero-encoder ILM estimation, but a joint effect on both encoder and prediction + joint network for posterior probability reshaping including both ILM and blank suppression.

Christoph Lüscher, Mohammad Zeineldeen, Zijian Yang et al.

Language barriers present a great challenge in our increasingly connected and global world. Especially within the medical domain, e.g. hospital or emergency room, communication difficulties and delays may lead to malpractice and non-optimal patient care. In the HYKIST project, we consider patient-physician communication, more specifically between a German-speaking physician and an Arabic- or Vietnamese-speaking patient. Currently, a doctor can call the Triaphon service to get assistance from an interpreter in order to help facilitate communication. The HYKIST goal is to support the usually non-professional bilingual interpreter with an automatic speech translation system to improve patient care and help overcome language barriers. In this work, we present our ASR system development efforts for this conversational telephone speech translation task in the medical domain for two languages pairs, data collection, various acoustic model architectures and dialect-induced difficulties.

Qi Zhang, Zijian Yang, Yilun Huang et al.

In this paper, we present our solution to the Multilingual Information Retrieval Across a Continuum of Languages (MIRACL) challenge of WSDM CUP 2023\footnote{https://project-miracl.github.io/}. Our solution focuses on enhancing the ranking stage, where we fine-tune pre-trained multilingual transformer-based models with MIRACL dataset. Our model improvement is mainly achieved through diverse data engineering techniques, including the collection of additional relevant training data, data augmentation, and negative sampling. Our fine-tuned model effectively determines the semantic relevance between queries and documents, resulting in a significant improvement in the efficiency of the multilingual information retrieval process. Finally, Our team is pleased to achieve remarkable results in this challenging competition, securing 2nd place in the Surprise-Languages track with a score of 0.835 and 3rd place in the Known-Languages track with an average nDCG@10 score of 0.716 across the 16 known languages on the final leaderboard.

Jingjing Xu, Wei Zhou, Zijian Yang et al.

Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency. To avoid redundant training and optimization efforts for individual models of different sizes, we present the dynamic encoder size approach, which jointly trains multiple performant models within one supernet from scratch. These subnets of various sizes are layer-wise pruned from the supernet, and thus, enjoy full parameter sharing. By combining score-based pruning with supernet training, we propose two novel methods, Simple-Top-k and Iterative-Zero-Out, to automatically select the best-performing subnets in a data-driven manner, avoiding resource-intensive search efforts. Our experiments using CTC on both Librispeech and TED-LIUM-v2 corpora show that our methods can achieve on-par performance as individually trained models of each size category. Also, our approach consistently brings small performance improvements for the full-size supernet.

Zijian Yang, Wei Zhou, Ralf Schlüter et al.

In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers. Both lattice-free and N-best-list approaches are examined. For lattice-free methods with phoneme-level LMs, we propose a method to approximate the context history to employ LMs with full-context dependency. This approximation can be extended to arbitrary context length and enables the usage of word-level LMs in lattice-free methods. Moreover, a systematic comparison is conducted across lattice-free and N-best-list-based methods. Experimental results on Librispeech show that using the word-level LM in training outperforms the phoneme-level LM. Besides, we find that the context size of the LM used for probability computation has a limited effect on performance. Moreover, our results reveal the pivotal importance of the hypothesis space quality in sequence discriminative training.

Zijian Yang, Yingbo Gao, Alexander Gerstenberger et al.

To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based neural language models. These training criteria typically enjoy the benefit of faster training and testing, at a cost of slightly degraded performance in terms of perplexity and almost no visible drop in word error rate. While noise contrastive estimation is one of the most popular choices, recently we show that other sampling-based criteria can also perform well, as long as an extra correction step is done, where the intended class posterior probability is recovered from the raw model outputs. In this work, we propose self-normalized importance sampling. Compared to our previous work, the criteria considered in this work are self-normalized and there is no need to further conduct a correction step. Through self-normalized language model training as well as lattice rescoring experiments, we show that our proposed self-normalized importance sampling is competitive in both research-oriented and production-oriented automatic speech recognition tasks.