Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work proposes to capture the variability of dialogue responses with a recurrent neural network (RNN)-based conditional variational autoencoder (CVAE). However, the autoregressive computation of the RNN limits the training efficiency. Therefore, we propose the Variational Transformer (VT), a variational self-attentive feed-forward sequence model. The VT combines the parallelizability and global receptive field of the Transformer with the variational nature of the CVAE by incorporating stochastic latent variables into Transformers. We explore two types of the VT: 1) modeling the discourse-level diversity with a global latent variable; and 2) augmenting the Transformer decoder with a sequence of fine-grained latent variables. Then, the proposed models are evaluated on three conversational datasets with both automatic metric and human evaluation. The experimental results show that our models improve standard Transformers and other baselines in terms of diversity, semantic relevance, and human judgment.
We detect out-of-training-distribution sentences in Neural Machine Translation using the Bayesian Deep Learning equivalent of Transformer models. For this we develop a new measure of uncertainty designed specifically for long sequences of discrete random variables -- i.e. words in the output sentence. Our new measure of uncertainty solves a major intractability in the naive application of existing approaches on long sentences. We use our new measure on a Transformer model trained with dropout approximate inference. On the task of German-English translation using WMT13 and Europarl, we show tha…
Posterior collapse plagues VAEs for text, especially for conditional text generation with strong autoregressive decoders. In this work, we address this problem in variational neural machine translation by explicitly promoting mutual information between the latent variables and the data. Our model extends the conditional variational autoencoder (CVAE) with two new ingredients: first, we propose a modified evidence lower bound (ELBO) objective which explicitly promotes mutual information; second, we regularize the probabilities of the decoder by mixing an auxiliary factorized distribution which …
Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are dense, assigning a non-zero weight to all context words. In this work, we introduce the adaptively sparse Transformer, wherein attention heads have flexible, context-dependent sparsity patterns. This sparsity is accomplished by replacing softmax with $α$-entmax: a differentiable ge…
Transformer has become ubiquitous due to its dominant performance in various NLP and image processing tasks. However, it lacks understanding of how to generate mathematically grounded uncertainty estimates for transformer architectures. Models equipped with such uncertainty estimates can typically improve predictive performance, make networks robust, avoid over-fitting and used as acquisition function in active learning. In this paper, we introduce BayesFormer, a Transformer model with dropouts designed by Bayesian theory. We proposed a new theoretical framework to extend the approximate varia…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inferenc…
We propose a VAE for Transformers by developing a variational information bottleneck regulariser for Transformer embeddings. We formalise the embedding space of Transformer encoders as mixture probability distributions, and use Bayesian nonparametrics to derive a nonparametric variational information bottleneck (NVIB) for such attention-based embeddings. The variable number of mixture components supported by nonparametric methods captures the variable number of vectors supported by attention, and the exchangeability of our nonparametric distributions captures the permutation invariance of atte…
Despite the recent advances in applying pre-trained language models to generate high-quality texts, generating long passages that maintain long-range coherence is yet challenging for these models. In this paper, we propose DiscoDVT, a discourse-aware discrete variational Transformer to tackle the incoherence issue. DiscoDVT learns a discrete variable sequence that summarizes the global structure of the text and then applies it to guide the generation process at each decoding step. To further embed discourse-aware information into the discrete latent representations, we introduce an auxiliary o…
Aspect-term sentiment analysis (ATSA) is a longstanding challenge in natural language understanding. It requires fine-grained semantical reasoning about a target entity appeared in the text. As manual annotation over the aspects is laborious and time-consuming, the amount of labeled data is limited for supervised learning. This paper proposes a semi-supervised method for the ATSA problem by using the Variational Autoencoder based on Transformer (VAET), which models the latent distribution via variational inference. By disentangling the latent representation into the aspect-specific sentiment a…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Microsoft Research Asia（微软亚洲研究院）
The past several years have witnessed Variational Auto-Encoder's superiority in various text generation tasks. However, due to the sequential nature of the text, auto-regressive decoders tend to ignore latent variables and then reduce to simple language models, known as the KL vanishing problem, which would further deteriorate when VAE is combined with Transformer-based structures. To ameliorate this problem, we propose DELLA, a novel variational Transformer framework. DELLA learns a series of layer-wise latent variables with each inferred from those of lower layers and tightly coupled with th…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京国家信息科学与技术研究中心）；Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院）；Microsoft Research Asia（微软亚洲研究院）；Jiangsu Normal University（江苏师范大学）；Jiangsu Collaborative Innovation Center for Language Ability（江苏省语言能力协同创新中心）
Variational Auto-Encoder (VAE) has been widely adopted in text generation. Among many variants, recurrent VAE learns token-wise latent variables with each conditioned on the preceding ones, which captures sequential variability better in the era of RNN. However, it is unclear how to incorporate such recurrent dynamics into the recently dominant Transformer due to its parallelism. In this work, we propose TRACE, a Transformer-based recurrent VAE structure. TRACE imposes recurrence on segment-wise latent variables with arbitrarily separated text segments and constructs the posterior distribution…
Text variational autoencoders (VAEs) are notorious for posterior collapse, a phenomenon where the model's decoder learns to ignore signals from the encoder. Because posterior collapse is known to be exacerbated by expressive decoders, Transformers have seen limited adoption as components of text VAEs. Existing studies that incorporate Transformers into text VAEs (Li et al., 2020; Fang et al., 2021) mitigate posterior collapse using massive pretraining, a technique unavailable to most of the research community without extensive computing resources. We present a simple two-phase training scheme …
In human dialogue, a single query may elicit numerous appropriate responses. The Transformer-based dialogue model produces frequently occurring sentences in the corpus since it is a one-to-one mapping function. CVAE is a technique for reducing generic replies. In this paper, we create a new dialogue model (CVAE-T) based on the Transformer with CVAE structure. We use a pre-trained MLM model to rewrite some key n-grams in responses to obtain a series of negative examples, and introduce a regularization term during training to explicitly guide the latent variable in learning the semantic differen…
University at Buffalo（布法罗大学）；JD Finance America Corporation（京东金融美国公司）
We investigate large-scale latent variable models (LVMs) for neural story generation -- an under-explored application for open-domain long text -- with objectives in two threads: generation effectiveness and controllability. LVMs, especially the variational autoencoder (VAE), have achieved both effective and controllable generation through exploiting flexible distributional latent representations. Recently, Transformers and its variants have achieved remarkable effectiveness without explicit latent representation learning, thus lack satisfying controllability in generation. In this paper, we a…
Poetry generation has long been a challenge for artificial intelligence. In the scope of Japanese poetry generation, many researchers have paid attention to Haiku generation, but few have focused on Waka generation. To further explore the creative potential of natural language generation systems in Japanese poetry creation, we propose a novel Waka generation model, WakaVT, which automatically produces Waka poems given user-specified keywords. Firstly, an additive mask-based approach is presented to satisfy the form constraint. Secondly, the structures of Transformer and variational autoencoder…
Data augmentation methods for Natural Language Processing tasks are explored in recent years, however they are limited and it is hard to capture the diversity on sentence level. Besides, it is not always possible to perform data augmentation on supervised tasks. To address those problems, we propose a neural data augmentation method, which is a combination of Conditional Variational Autoencoder and encoder-decoder Transformer model. While encoding and decoding the input sentence, our model captures the syntactic and semantic representation of the input language with its class condition. Follow…
CMATH: Cross-Modality Augmented Transformer with Hierarchical Variational Distillation for Multimodal Emotion Recognition in Conversation
Chongqing University of Technology（重庆理工大学）；Fuzhou University（福州大学）；China Automotive Engineering Research Institute Co., Ltd.（中国汽车工程研究院股份有限公司）；Chongqing Changan Automobile Co., Ltd.（重庆长安汽车股份有限公司）
Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder
Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系）；Idiap Research Institute（Idiap研究机构）；National Biomarker Centre, CRUK-MI, Univ. of Manchester（国家生物标记中心，CRUK-MI，曼彻斯特大学）
PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism
Northeastern University（东北大学）；Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning (MCML), LMU Munich（慕尼黑大学慕尼黑机器学习中心（MCML））
University of Virginia（弗吉尼亚大学）；The Chinese University of Hong Kong（香港中文大学）
Generating high quality texts with high diversity is important for many NLG applications, but current methods mostly focus on building deterministic models to generate higher quality texts and do not provide many options for promoting diversity. In this work, we present a novel latent structured variable model to generate high quality texts by enriching contextual representation learning of encoder-decoder models. Specifically, we introduce a stochastic function to map deterministic encoder hidden states into random context variables. The proposed stochastic function is sampled from a Gaussian…
Institute for Artificial Intelligence（人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Baozun（宝尊）
Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence, or to generate diversified expressions. To address these issues, we propose a Planning-based Hierarchical Variational Model (PHVM). Our model first plans a sequence of groups (each group is a subset of input items to be covered by a sentence) and then realizes each sentence conditioned on the planning result and the previously generated context, thereby decomposing long text gene…
Monash University（莫纳什大学）；The University of Melbourne（墨尔本大学）
In this paper, we propose a variational autoencoder with disentanglement priors, VAE-DPRIOR, for task-specific natural language generation with none or a handful of task-specific labeled examples. In order to tackle compositional generalization across tasks, our model performs disentangled representation learning by introducing a conditional prior for the latent content space and another conditional prior for the latent label space. Both types of priors satisfy a novel property called $ε$-disentangled. We show both empirically and theoretically that the novel priors can disentangle representat…
We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different pretraining approaches for generating these signals, (2) the quantity of parallel data for which document context is available, and (3) conditioning on source, target, or source and target contexts. Experiments on the NIST Chinese-English, and IWSLT and WMT English-German tasks support four general conclusions: that using pretrained context representations markedly improves sa…
P-Transformer: A Prompt-based Multimodal Transformer Architecture For Medical Tabular Data
Saw Swee Hock School of Public Health, National University of Singapore（新加坡国立大学苏瑞福公共卫生学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院）；Singapore General Hospital（新加坡综合医院）
Wuhan University（武汉大学）；Huazhong University of Science and Technology（华中科技大学）；Wuhan University of Technology（武汉理工大学）；Deakin University（迪肯大学）；City University of Hong Kong（香港城市大学）
Stack Overflow is one of the most popular programming communities where developers can seek help for their encountered problems. Nevertheless, if inexperienced developers fail to describe their problems clearly, it is hard for them to attract sufficient attention and get the anticipated answers. We propose M$_3$NSCT5, a novel approach to automatically generate multiple post titles from the given code snippets. Developers may use the generated titles to find closely related posts and complete their problem descriptions. M$_3$NSCT5 employs the CodeT5 backbone, which is a pre-trained Transformer …
While describing Spatio-temporal events in natural language, video captioning models mostly rely on the encoder's latent visual representation. Recent progress on the encoder-decoder model attends encoder features mainly in linear interaction with the decoder. However, growing model complexity for visual data encourages more explicit feature interaction for fine-grained information, which is currently absent in the video captioning domain. Moreover, feature aggregations methods have been used to unveil richer visual representation, either by the concatenation or using a linear layer. Though fe…
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey desired information. Traditional template-based generators can produce sentences with all necessary information, but these sentences are not sufficiently diverse. With RNN-based models, the diversity of the generated sentences can be high, however, in the process some information is lost. In this work, we improve an RNN-based generator by considering latent inform…
Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；Swiss Data Science Institute (ETHZ/EPFL)（瑞士数据科学研究所（苏黎世联邦理工学院/洛桑联邦理工学院））
Language models (LM) have grown with non-stop in the last decade, from sequence-to-sequence architectures to the state-of-the-art and utter attention-based Transformers. In this work, we demonstrate how the inclusion of deep generative models within BERT can bring more versatile models, able to impute missing/noisy words with richer text or even improve BLEU score. More precisely, we use a Gaussian Mixture Variational Autoencoder (GMVAE) as a regularizer layer and prove its effectiveness not only in Transformers but also in the most relevant encoder-decoder based LM, seq2seq with and without a…
Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Previous works mitigated such problem by heuristic methods such as strengthening the encoder or weakening the decoder while optimizing the CVAE objective function. Nevertheless, the optimizing direction of these methods are implicit and it is hard to find an appropriate degree to which these methods should be applied. In this paper, we propose an explici…
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel varia…
Beijing Institute of Technology（北京理工大学）；Huawei Technologies Ltd.（华为技术有限公司）
Conditional variational models, using either continuous or discrete latent variables, are powerful for open-domain dialogue response generation. However, previous works show that continuous latent variables tend to reduce the coherence of generated responses. In this paper, we also found that discrete latent variables have difficulty capturing more diverse expressions. To tackle these problems, we combine the merits of both continuous and discrete latent variables and propose a Hybrid Latent Variable (HLV) method. Specifically, HLV constrains the global semantics of responses through discrete …
University of California, Berkeley（加州大学伯克利分校）；Tsinghua University（清华大学）
The predominant approach for language modeling is to process sequences from left to right, but this eliminates a source of information: the order by which the sequence was generated. One strategy to recover this information is to decode both the content and ordering of tokens. Existing approaches supervise content and ordering by designing problem-specific loss functions and pre-training with an ordering pre-selected. Other recent works use iterative search to discover problem-specific orderings for training, but suffer from high time complexity and cannot be efficiently parallelized. We addre…
