Players of online games generate rich behavioral data during gaming. Based on these data, game developers can build a range of data science applications, such as bot detection and social recommendation, to improve the gaming experience. However, the development of such applications requires data cleansing, training sample labeling, feature engineering, and model development, which makes the use of such applications in small and medium-sized game studios still uncommon. While acquiring supervised learning data is costly, unlabeled behavioral logs are often continuously and automatically generated in games. Thus we resort to unsupervised representation learning of player behavioral data to optimize intelligent services in games. Behavioral data has many unique properties, including semantic complexity, excessive length, etc. A worth noting property within raw player behavioral data is that a lot of it is task-irrelevant. For these data characteristics, we introduce a BPE-enhanced compression method and propose a novel adaptive masking strategy called Masking by Token Confidence (MTC) for the Masked Language Modeling (MLM) pre-training task. MTC is designed to increase the masking probabilities of task-relevant tokens. Experiments on four downstream tasks and successful deployment in a world-renowned Massively Multiplayer Online Role-Playing Game (MMORPG) prove the effectiveness of the MTC strategy1.

Abstract Standard multi-task benchmarks are essential for developing pretraining models that can generalize to various downstream tasks. Existing benchmarks for natural language processing (NLP) usually focus only on understanding or generating short texts. However, long text modeling requires many distinct abilities in contrast to short texts, such as the modeling of long-range discourse and commonsense relations, and the coherence and controllability of generation. The lack of standardized benchmarks makes it difficult to assess these abilities of a model and fairly compare different models, especially Chinese models. Therefore, we propose a story-centric benchmark named LOT for evaluating Chinese long text modeling, which aggregates two understanding tasks and two generation tasks. We construct new datasets for these tasks based on human-written Chinese stories with hundreds of words. Furthermore, we release an encoder-decoder-based Chinese long text pretraining model named LongLM with up to 1 billion parameters. We pretrain LongLM on 120G Chinese novels with two generative tasks including text infilling and conditional continuation. Extensive experiments show that LongLM outperforms similar-sized pretraining models substantially on both the understanding and generation tasks in LOT.

Generating stylized responses is essential to build intelligent and engaging dialogue systems. However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when the target style is embedded only in unpaired texts that cannot be directly used to train the dialogue model. This paper proposes a stylized dialogue generation method that can capture stylistic features embedded in unpaired texts. Specifically, our method can produce dialogue responses that are both coherent to the given context and conform to the target style. In this study, an inverse dialogue model is first introduced to predict possible posts for the input responses. Then this inverse model is used to generate stylized pseudo dialogue pairs based on these stylized unpaired texts. Further, these pseudo pairs are employed to train the stylized dialogue model with a joint training process. A style routing approach is proposed to intensify stylistic features in the decoder. Automatic and manual evaluations on two datasets demonstrate that our method outperforms competitive baselines in producing coherent and style-intensive dialogue responses.

Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, Minlie Huang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Ziyang Luo, Artur Kulmizev, Xiaoxi Mao. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Label Smoothing is a widely used technique in many areas. It can prevent the network from being over-confident. However, it hypotheses that the prior distribution of all classes is uniform. Here, we decide to abandon this hypothesis and propose a new smoothing method, called Smoothing with Fake Label. It shares a part of the prediction probability to a new fake class. Our experiment results show that the method can increase the performance of the models on most tasks and outperform the Label Smoothing on text classification and cross-lingual transfer tasks.

Grounded dialogue models generate responses that are grounded on certain concepts.Limited by the distribution of grounded dialogue data, models trained on such data face the transferability challenges in terms of the data distribution and the type of grounded concepts.To address the challenges, we propose the grounded minimal editing framework, which minimally edits existing responses to be grounded on the given concept.Focusing on personas, we propose Grounded Minimal Editor (GME), which learns to edit by disentangling and recombining persona-related and persona-agnostic parts of the response.To evaluate persona-grounded minimal editing, we present the PERSONAMI-NEDIT dataset, and experimental results show that GME outperforms competitive baselines by a large margin.To evaluate the transferability, we experiment on the test set of BLEND-EDSKILLTALK and show that GME can edit dialogue models' responses to largely improve their persona consistency while preserving the use of knowledge and empathy. 1

Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the persona sparsity issue observed in most dialogue corpora. This paper proposes a pre-training based personalized dialogue model that can generate coherent responses using persona-sparse dialogue data. In this method, a pre-trained language model is used to initialize an encoder and decoder, and personal attribute embeddings are devised to model richer dialogue contexts by encoding speakers' personas together with dialogue histories. Further, to incorporate the target persona in the decoding process and to balance its contribution, an attention routing structure is devised in the decoder to merge features extracted from the target persona and dialogue contexts using dynamically predicted weights. Our model can utilize persona-sparse dialogues in a unified manner during the training process, and can also control the amount of persona-related features to exhibit during the inference process. Both automatic and manual evaluation demonstrates that the proposed model outperforms state-of-the-art methods for generating more coherent and persona consistent responses with persona-sparse data.

Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data.However, collecting large-scale dialogue data is usually time-consuming and labor-intensive.To address this data dilemma, we propose a novel data augmentation method for training opendomain dialogue models by utilizing unpaired data.Specifically, a data-level distillation process is first proposed to construct augmented dialogues where both post and response are retrieved from the unpaired data.A ranking module is employed to filter out low-quality dialogues.Further, a model-level distillation process is employed to distill a teacher model trained on high-quality paired data to augmented dialogue pairs, thereby preventing dialogue models from being affected by the noise in the augmented data.Automatic and manual evaluation indicates that our method can produce high-quality dialogue pairs with diverse contents, and the proposed data-level and model-level dialogue distillation can improve the performance of competitive baselines.