Extrapolating Multilingual Understanding Models as Multilingual Generators

Multilingual understanding models (or encoder-based), pre-trained via masked language modeling, have achieved promising results on many language understanding tasks (e.g., mBERT). However, these non-autoregressive (NAR) models still struggle to generate high-quality texts compared with autoregressive (AR) models. Considering that encoder-based models have the advantage of efficient generation and self-correction abilities, this paper explores methods to empower multilingual understanding models the generation abilities to get a unified model. Specifically, we start from a multilingual encoder (XLM-R) and propose a \textbf{S}emantic-\textbf{G}uided \textbf{A}lignment-then-Denoising (SGA) approach to adapt an encoder to a multilingual generator with a small number of new parameters. Experiments show that the proposed approach is an effective adaption method, outperforming widely-used initialization-based methods with gains of 9.4 BLEU on machine translation, 8.1 Rouge-L on question generation, and 5.5 METEOR on story generation on XLM-R$_{large}$. On the other hand, we observe that XLM-R is still inferior to mBART in supervised settings despite better results on zero-shot settings, indicating that more exploration is required to make understanding models strong generators.

Continuous sign language recognition based on cross-resolution knowledge distillation

The goal of continuous sign language recognition(CSLR) research is to apply CSLR models as a communication tool in real life, and the real-time requirement of the models is important. In this paper, we address the model real-time problem through cross-resolution knowledge distillation. In our study, we found that keeping the frame-level feature scales consistent between the output of the student network and the teacher network is better than recovering the frame-level feature sizes for feature distillation. Based on this finding, we propose a new frame-level feature extractor that keeps the output frame-level features at the same scale as the output of by the teacher network. We further combined with the TSCM+2D hybrid convolution proposed in our previous study to form a new lightweight end-to-end CSLR network-Low resolution input net(LRINet). It is then used to combine cross-resolution knowledge distillation and traditional knowledge distillation methods to form a CSLR model based on cross-resolution knowledge distillation (CRKD). The CRKD uses high-resolution frames as input to the teacher network for training, locks the weights after training, and then uses low-resolution frames as input to the student network LRINet to perform knowledge distillation on frame-level features and classification features respectively. Experiments on two large-scale continuous sign language datasets have proved the effectiveness of CRKD. Compared with the model with high-resolution data as input, the calculation amount, parameter amount and inference time of the model have been significantly reduced under the same experimental conditions, while ensuring the accuracy of the model, and has achieved very competitive results in comparison with other advanced methods.

Lego-MT: Towards Detachable Models in Massively Multilingual Machine Translation

Traditional multilingual neural machine translation (MNMT) uses a single model to translate all directions. However, with the increasing scale of language pairs, simply using a single model for massive MNMT brings new challenges: parameter tension and large computations. In this paper, we revisit multi-way structures by assigning an individual branch for each language (group). Despite being a simple architecture, it is challenging to train de-centralized models due to the lack of constraints to align representations from all languages. We propose a localized training recipe to map different branches into a unified space, resulting in an efficient detachable model, Lego-MT. For a fair comparison, we collect data from OPUS and build the first large-scale open-source translation benchmark covering 7 language-centric data, each containing 445 language pairs. Experiments show that Lego-MT (1.2B) brings gains of more than 4 BLEU while outperforming M2M-100 (12B) (We will public all training data, models, and checkpoints)

Temporal superimposed crossover module for effective continuous sign language

The ultimate goal of continuous sign language recognition(CSLR) is to facilitate the communication between special people and normal people, which requires a certain degree of real-time and deploy-ability of the model. However, in the previous research on CSLR, little attention has been paid to the real-time and deploy-ability. In order to improve the real-time and deploy-ability of the model, this paper proposes a zero parameter, zero computation temporal superposition crossover module(TSCM), and combines it with 2D convolution to form a "TSCM+2D convolution" hybrid convolution, which enables 2D convolution to have strong spatial-temporal modelling capability with zero parameter increase and lower deployment cost compared with other spatial-temporal convolutions. The overall CSLR model based on TSCM is built on the improved ResBlockT network in this paper. The hybrid convolution of "TSCM+2D convolution" is applied to the ResBlock of the ResNet network to form the new ResBlockT, and random gradient stop and multi-level CTC loss are introduced to train the model, which reduces the final recognition WER while reducing the training memory usage, and extends the ResNet network from image classification task to video recognition task. In addition, this study is the first in CSLR to use only 2D convolution extraction of sign language video temporal-spatial features for end-to-end learning for recognition. Experiments on two large-scale continuous sign language datasets demonstrate the effectiveness of the proposed method and achieve highly competitive results.

Continuous Sign Language Recognition via Temporal Super-Resolution Network

Aiming at the problem that the spatial-temporal hierarchical continuous sign language recognition model based on deep learning has a large amount of computation, which limits the real-time application of the model, this paper proposes a temporal super-resolution network(TSRNet). The data is reconstructed into a dense feature sequence to reduce the overall model computation while keeping the final recognition accuracy loss to a minimum. The continuous sign language recognition model(CSLR) via TSRNet mainly consists of three parts: frame-level feature extraction, time series feature extraction and TSRNet, where TSRNet is located between frame-level feature extraction and time-series feature extraction, which mainly includes two branches: detail descriptor and rough descriptor. The sparse frame-level features are fused through the features obtained by the two designed branches as the reconstructed dense frame-level feature sequence, and the connectionist temporal classification(CTC) loss is used for training and optimization after the time-series feature extraction part. To better recover semantic-level information, the overall model is trained with the self-generating adversarial training method proposed in this paper to reduce the model error rate. The training method regards the TSRNet as the generator, and the frame-level processing part and the temporal processing part as the discriminator. In addition, in order to unify the evaluation criteria of model accuracy loss under different benchmarks, this paper proposes word error rate deviation(WERD), which takes the error rate between the estimated word error rate (WER) and the reference WER obtained by the reconstructed frame-level feature sequence and the complete original frame-level feature sequence as the WERD. Experiments on two large-scale sign language datasets demonstrate the effectiveness of the proposed model.

Multi-scale temporal network for continuous sign language recognition

Continuous Sign Language Recognition (CSLR) is a challenging research task due to the lack of accurate annotation on the temporal sequence of sign language data. The recent popular usage is a hybrid model based on "CNN + RNN" for CSLR. However, when extracting temporal features in these works, most of the methods using a fixed temporal receptive field and cannot extract the temporal features well for each sign language word. In order to obtain more accurate temporal features, this paper proposes a multi-scale temporal network (MSTNet). The network mainly consists of three parts. The Resnet and two fully connected (FC) layers constitute the frame-wise feature extraction part. The time-wise feature extraction part performs temporal feature learning by first extracting temporal receptive field features of different scales using the proposed multi-scale temporal block (MST-block) to improve the temporal modeling capability, and then further encoding the temporal features of different scales by the transformers module to obtain more accurate temporal features. Finally, the proposed multi-level Connectionist Temporal Classification (CTC) loss part is used for training to obtain recognition results. The multi-level CTC loss enables better learning and updating of the shallow network parameters in CNN, and the method has no parameter increase and can be flexibly embedded in other models. Experimental results on two publicly available datasets demonstrate that our method can effectively extract sign language features in an end-to-end manner without any prior knowledge, improving the accuracy of CSLR and reaching the state-of-the-art.

Simpson's Bias in NLP Training

In most machine learning tasks, we evaluate a model $M$ on a given data population $S$ by measuring a population-level metric $F(S;M)$. Examples of such evaluation metric $F$ include precision/recall for (binary) recognition, the F1 score for multi-class classification, and the BLEU metric for language generation. On the other hand, the model $M$ is trained by optimizing a sample-level loss $G(S_t;M)$ at each learning step $t$, where $S_t$ is a subset of $S$ (a.k.a. the mini-batch). Popular choices of $G$ include cross-entropy loss, the Dice loss, and sentence-level BLEU scores. A fundamental assumption behind this paradigm is that the mean value of the sample-level loss $G$, if averaged over all possible samples, should effectively represent the population-level metric $F$ of the task, such as, that $\mathbb{E}[ G(S_t;M) ] \approx F(S;M)$. In this paper, we systematically investigate the above assumption in several NLP tasks. We show, both theoretically and experimentally, that some popular designs of the sample-level loss $G$ may be inconsistent with the true population-level metric $F$ of the task, so that models trained to optimize the former can be substantially sub-optimal to the latter, a phenomenon we call it, Simpson's bias, due to its deep connections with the classic paradox known as Simpson's reversal paradox in statistics and social sciences.

Reinforced Multi-Teacher Selection for Knowledge Distillation

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation transfers knowledge from one or multiple large (teacher) models to a small (student) model. When multiple teacher models are available in distillation, the state-of-the-art methods assign a fixed weight to a teacher model in the whole distillation. Furthermore, most of the existing methods allocate an equal weight to every teacher model. In this paper, we observe that, due to the complexity of training examples and the differences in student model capability, learning differentially from teacher models can lead to better performance of student models distilled. We systematically develop a reinforced method to dynamically assign weights to teacher models for different training instances and optimize the performance of student model. Our extensive experimental results on several NLP tasks clearly verify the feasibility and effectiveness of our approach.

Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension

Multilingual pre-trained models could leverage the training data from a rich source language (such as English) to improve performance on low resource languages. However, the transfer quality for multilingual Machine Reading Comprehension (MRC) is significantly worse than sentence classification tasks mainly due to the requirement of MRC to detect the word level answer boundary. In this paper, we propose two auxiliary tasks in the fine-tuning stage to create additional phrase boundary supervision: (1) A mixed MRC task, which translates the question or passage to other languages and builds cross-lingual question-passage pairs; (2) A language-agnostic knowledge masking task by leveraging knowledge phrases mined from web. Besides, extensive experiments on two cross-lingual MRC datasets show the effectiveness of our proposed approach.