In the era of large language models, Mixture-of-Experts (MoE) is a promising architecture for managing computational costs when scaling up model parameters. However, conventional MoE architectures like GShard, which activate the top-K out of N experts, face challenges in ensuring expert specialization, i.e. each expert acquires non-overlapping and focused knowledge. In response, we propose the DeepSeekMoE architecture towards ultimate expert specialization. It involves two principal strategies: (1) finely segmenting the experts into mN ones and activating mK from them, allowing for a more flexible combination of activated experts; (2) isolating K_s experts as shared ones, aiming at capturing common knowledge and mitigating redundancy in routed experts. Starting from a modest scale with 2B parameters, we demonstrate that DeepSeekMoE 2B achieves comparable performance with GShard 2.9B, which has 1.5 × expert parameters and computation. In addition, DeepSeekMoE 2B nearly approaches the performance of its dense counterpart with the same number of total parameters, which sets the upper bound of MoE models. Subsequently, we scale up DeepSeekMoE to 16B parameters and show that it achieves comparable performance with DeepSeek 7B and LLaMA2 7B, with only about 40% of computations.

Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few-shot learning performance on downstream tasks.It would be desirable if the models can acquire some prompting knowledge before adapting to specific NLP tasks. We present the Unified Prompt Tuning (UPT) framework, leading to better few-shot text classification for BERT-style models by explicitly capturing prompting semantics from non-target NLP datasets. In UPT, a novel paradigm Prompt-Options-Verbalizer is proposed for joint prompt learning across different NLP tasks, forcing PLMs to capture task-invariant prompting knowledge. We further design a self-supervised task named Knowledge-enhanced Selective Masked Language Modeling to improve the PLM’s generalization abilities for accurate adaptation to previously unseen tasks. After multi-task learning across multiple tasks, the PLM can be better prompt-tuned towards any dissimilar target tasks in low-resourced settings. Experiments over a variety of NLP tasks show that UPT consistently outperforms state-of-the-arts for prompt-based fine-tuning.

Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual pre-trained language models: settings, algorithms, and efficiency. Experiments on nine downstream tasks show several counter-intuitive phenomena: for settings, individually pruning for each language does not induce a better result; for algorithms, the simplest method performs the best; for efficiency, a fast model does not imply that it is also small. To facilitate the comparison on all sparsity levels, we present Dynamic Sparsification, a simple approach that allows training the model once and adapting to different model sizes at inference. We hope this work fills the gap in the study of structured pruning on multilingual pre-trained models and sheds light on future research.

The emergence of multilingual pre-trained language models makes it possible to adapt to target languages with only few labeled examples. However, vanilla fine-tuning tends to achieve degenerated and unstable results, owing to the Language Interference among different languages, and Parameter Overload under the few-sample transfer learning scenarios. To address two problems elegantly, we propose S⁴-Tuning, a Simple Cross-lingual Sub-network Tuning method. S⁴-Tuning first detects the most essential sub-network for each target language, and only updates it during fine-tuning.In this way, the language sub-networks lower the scale of trainable parameters, and hence better suit the low-resource scenarios.Meanwhile, the commonality and characteristics across languages are modeled by the overlapping and non-overlapping parts to ease the interference among languages.Simple but effective, S⁴-Tuning gains consistent improvements over vanilla fine-tuning on three multi-lingual tasks involving 37 different languages in total (XNLI, PAWS-X, and Tatoeba).

Existing work in multilingual pretraining has demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages. However, much of this work only relies on the shared vocabulary and bilingual contexts to encourage the correlation across languages, which is loose and implicit for aligning the contextual representations between languages. In this paper, we plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. More importantly, when fine-tuning on downstream tasks, the cross-attention module can be plugged in or out on-demand, thus naturally benefiting a wider range of cross-lingual tasks, from language understanding to generation. As a result, the proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark, covering text classification, sequence labeling, question answering, and sentence retrieval. For cross-lingual generation tasks, it also outperforms all existing cross-lingual models and state-of-the-art Transformer variants on WMT14 English-to-German and English-to-French translation datasets, with gains of up to 1 2 BLEU.

Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training. However, in real-world scenarios, Knowledge Graphs (KG) evolve fast with out-of-knowledge-graph (OOKG) entities added frequently, and we need to efficiently represent these entities. Most existing Knowledge Graph Embedding (KGE) methods cannot represent OOKG entities without costly retraining on the whole KG. To enhance efficiency, we propose a simple and effective method that inductively represents OOKG entities by their optimal estimation under translational assumptions. Moreover, given pretrained embeddings of the in-knowledge-graph (IKG) entities, our method even needs no additional learning. Experimental results on two KGC tasks with OOKG entities show that our method outperforms the previous methods by a large margin with higher efficiency.

Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise, such as masking, shuffling, or substitution, and then try to recover the original input. However, such pre-training approaches are prone to learning representations that are covariant with the noise, leading to the discrepancy between the pre-training and fine-tuning stage. To remedy this, we present ContrAstive Pre-Training (CAPT) to learn noise invariant sequence representations. The proposed CAPT encourages the consistency between representations of the original sequence and its corrupted version via unsupervised instance-wise training signals. In this way, it not only alleviates the pretrain-finetune discrepancy induced by the noise of pre-training, but also aids the pre-trained model in better capturing global semantics of the input via more effective sentence-level supervision. Different from most prior work that focuses on a particular modality, comprehensive empirical evidence on 11 natural language understanding and cross-modal tasks illustrates that CAPT is applicable for both language and vision-language tasks, and obtains surprisingly consistent improvement, including 0.6% absolute gain on GLUE benchmarks and 0.8% absolute increment on NLVR2.

Recent pretrained language models extend from millions to billions of parameters. Thus the need to fine-tune an extremely large pretrained model with a limited training corpus arises in various downstream tasks. In this paper, we propose a straightforward yet effective fine-tuning technique, Child-Tuning, which updates a subset of parameters (called child network) of large pretrained models via strategically masking out the gradients of the non-child network during the backward process. Experiments on various downstream tasks in GLUE benchmark show that Child-Tuning consistently outperforms the vanilla fine-tuning by 1.5 8.6 average score among four different pretrained models, and surpasses the prior fine-tuning techniques by 0.6 1.3 points. Furthermore, empirical results on domain transfer and task transfer show that Child-Tuning can obtain better generalization performance by large margins.

In this paper, we focus on the task of generating a pun sentence given a pair of word senses. A major challenge for pun generation is the lack of large-scale pun corpus to guide supervised learning. To remedy this, we propose an adversarial generative network for pun generation (Pun-GAN). It consists of a generator to produce pun sentences, and a discriminator to distinguish between the generated pun sentences and the real sentences with specific word senses. The output of the discriminator is then used as a reward to train the generator via reinforcement learning, encouraging it to produce pun sentences which can support two word senses simultaneously. Experiments show that the proposed Pun-GAN can generate sentences that are more ambiguous and diverse in both automatic and human evaluation.

Automatic topic-to-essay generation is a challenging task since it requires generating novel, diverse, and topic-consistent paragraph-level text with a set of topics as input. Previous work tends to perform essay generation based solely on the given topics while ignoring massive commonsense knowledge. However, this commonsense knowledge provides additional background information, which can help to generate essays that are more novel and diverse. Towards filling this gap, we propose to integrate commonsense from the external knowledge base into the generator through dynamic memory mechanism. Besides, the adversarial training based on a multi-label discriminator is employed to further improve topic-consistency. We also develop a series of automatic evaluation metrics to comprehensively assess the quality of the generated essay. Experiments show that with external commonsense knowledge and adversarial training, the generated essays are more novel, diverse, and topic-consistent than existing methods in terms of both automatic and human evaluation.

In this paper, we focus on the task of fine-grained text sentiment transfer (FGST). This task aims to revise an input sequence to satisfy a given sentiment intensity, while preserving the original semantic content. Different from the conventional sentiment transfer task that only reverses the sentiment polarity (positive/negative) of text, the FTST task requires more nuanced and fine-grained control of sentiment. To remedy this, we propose a novel Seq2SentiSeq model. Specifically, the numeric sentiment intensity value is incorporated into the decoder via a Gaussian kernel layer to finely control the sentiment intensity of the output. Moreover, to tackle the problem of lacking parallel data, we propose a cycle reinforcement learning algorithm to guide the model training. In this framework, the elaborately designed rewards can balance both sentiment transformation and content preservation, while not requiring any ground truth output. Experimental results show that our approach can outperform existing methods by a large margin in both automatic evaluation and human evaluation.

Automatic commenting of online articles can provide additional opinions and facts to the reader, which improves user experience and engagement on social media platforms. Previous work focuses on automatic commenting based solely on textual content. However, in real-scenarios, online articles usually contain multiple modal contents. For instance, graphic news contains plenty of images in addition to text. Contents other than text are also vital because they are not only more attractive to the reader but also may provide critical information. To remedy this, we propose a new task: cross-model automatic commenting (CMAC), which aims to make comments by integrating multiple modal contents. We construct a large-scale dataset for this task and explore several representative methods. Going a step further, an effective co-attention model is presented to capture the dependency between textual and visual information. Evaluation results show that our proposed model can achieve better performance than competitive baselines.

The task of unsupervised bilingual lexicon induction (UBLI) aims to induce word translations from monolingual corpora in two languages. Previous work has shown that morphological variation is an intractable challenge for the UBLI task, where the induced translation in failure case is usually morphologically related to the correct translation. To tackle this challenge, we propose a morphology-aware alignment model for the UBLI task. The proposed model aims to alleviate the adverse effect of morphological variation by introducing grammatical information learned by the pre-trained denoising language model. Results show that our approach can substantially outperform several state-of-the-art unsupervised systems, and even achieves competitive performance compared to supervised methods.

Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision. Existing seq2seq methods face three challenges: 1) the transfer is weakly interpretable, 2) generated outputs struggle in content preservation, and 3) the trade-off between content and style is intractable. To address these challenges, we propose a hierarchical reinforced sequence operation method, named Point-Then-Operate (PTO), which consists of a high-level agent that proposes operation positions and a low-level agent that alters the sentence. We provide comprehensive training objectives to control the fluency, style, and content of the outputs and a mask-based inference algorithm that allows for multi-step revision based on the single-step trained agents. Experimental results on two text style transfer datasets show that our method significantly outperforms recent methods and effectively addresses the aforementioned challenges.

Multi-label classification (MLC) aims to predict a set of labels for a given instance. Based on a pre-defined label order, the sequence-to-sequence (Seq2Seq) model trained via maximum likelihood estimation method has been successfully applied to the MLC task and shows powerful ability to capture high-order correlations between labels. However, the output labels are essentially an unordered set rather than an ordered sequence. This inconsistency tends to result in some intractable problems, e.g., sensitivity to the label order. To remedy this, we propose a simple but effective sequence-to-set model. The proposed model is trained via reinforcement learning, where reward feedback is designed to be independent of the label order. In this way, we can reduce the dependence of the model on the label order, as well as capture high-order correlations between labels. Extensive experiments show that our approach can substantially outperform competitive baselines, as well as effectively reduce the sensitivity to the label order.

The comprehensive descriptions for factual attribute-value tables, which should be accurate, informative and loyal, can be very helpful for end users to understand the structured data in this form. However previous neural generators might suffer from key attributes missing, less informative and groundless information problems, which impede the generation of high-quality comprehensive descriptions for tables. To relieve these problems, we first propose force attention (FA) method to encourage the generator to pay more attention to the uncovered attributes to avoid potential key attributes missing. Furthermore, we propose reinforcement learning for information richness to generate more informative as well as more loyal descriptions for tables. In our experiments, we utilize the widely used WIKIBIO dataset as a benchmark. Besides, we create WB-filter based on WIKIBIO to test our model in the simulated user-oriented scenarios, in which the generated descriptions should accord with particular user interests. Experimental results show that our model outperforms the state-of-the-art baselines on both automatic and human evaluation.

Automatic story ending generation is an interesting and challenging task in natural language generation. Previous studies are mainly limited to generate coherent, reasonable and diversified story endings, and few works focus on controlling the sentiment of story endings. This paper focuses on generating a story ending which meets the given fine-grained sentiment intensity. There are two major challenges to this task. First is the lack of story corpus which has fine-grained sentiment labels. Second is the difficulty of explicitly controlling sentiment intensity when generating endings. Therefore, we propose a generic and novel framework which consists of a sentiment analyzer and a sentimental generator, respectively addressing the two challenges. The sentiment analyzer adopts a series of methods to acquire sentiment intensities of the story dataset. The sentimental generator introduces the sentiment intensity into decoder via a Gaussian Kernel Layer to control the sentiment of the output. To the best of our knowledge, this is the first endeavor to control the fine-grained sentiment for story ending generation without manually annotating sentiment labels. Experiments show that our proposed framework can generate story endings which are not only more coherent and fluent but also able to meet the given sentiment intensity better.

The goal of Word Sense Disambiguation (WSD) is to identify the correct meaning of a word in the particular context. Traditional supervised methods only use labeled data (context), while missing rich lexical knowledge such as the gloss which defines the meaning of a word sense. Recent studies have shown that incorporating glosses into neural networks for WSD has made significant improvement. However, the previous models usually build the context representation and gloss representation separately. In this paper, we find that the learning for the context and gloss representation can benefit from each other. Gloss can help to highlight the important words in the context, thus building a better context representation. Context can also help to locate the key words in the gloss of the correct word sense. Therefore, we introduce a co-attention mechanism to generate co-dependent representations for the context and gloss. Furthermore, in order to capture both word-level and sentence-level information, we extend the attention mechanism in a hierarchical fashion. Experimental results show that our model achieves the state-of-the-art results on several standard English all-words WSD test datasets.

Word Sense Disambiguation (WSD) aims to identify the correct meaning of polysemous words in the particular context. Lexical resources like WordNet which are proved to be of great help for WSD in the knowledge-based methods. However, previous neural networks for WSD always rely on massive labeled data (context), ignoring lexical resources like glosses (sense definitions). In this paper, we integrate the context and glosses of the target word into a unified framework in order to make full use of both labeled data and lexical knowledge. Therefore, we propose GAS: a gloss-augmented WSD neural network which jointly encodes the context and glosses of the target word. GAS models the semantic relationship between the context and the gloss in an improved memory network framework, which breaks the barriers of the previous supervised methods and knowledge-based methods. We further extend the original gloss of word sense via its semantic relations in WordNet to enrich the gloss information. The experimental results show that our model outperforms the state-of-the-art systems on several English all-words WSD datasets.