In the real-world scenario, a longstanding goal of multilingual neural machine translation (MNMT) is that a single model can incrementally adapt to new language pairs without accessing previous training data.In this scenario, previous studies concentrate on overcoming catastrophic forgetting while lacking encouragement to learn new knowledge from incremental language pairs, especially when the incremental language is not related to the set of original languages.To better acquire new knowledge, we propose a knowledge transfer method that can efficiently adapt original MNMT models to diverse incremental language pairs.The method flexibly introduces the knowledge from an external model into original models, which encourages the models to learn new language pairs, completing the procedure of knowledge transfer.Moreover, all original parameters are frozen to ensure that translation qualities on original language pairs are not degraded.Experimental results show that our method can learn new knowledge from diverse language pairs incrementally meanwhile maintaining performance on original language pairs, outperforming various strong baselines in incremental learning for MNMT.

Passage ranking involves two stages: passage retrieval and passage re-ranking, which are important and challenging topics for both academics and industries in the area of Information Retrieval (IR). However, the commonly-used datasets for passage ranking usually focus on the English language. For non-English scenarios, such as Chinese, the existing datasets are limited in terms of data scale, fine-grained relevance annotation and false negative issues. To address this problem, we introduce T2Ranking, a large-scale Chinese benchmark for passage ranking. T2Ranking comprises more than 300K queries and over 2M unique passages from real-world search engines. Expert annotators are recruited to provide 4-level graded relevance scores (fine-grained) for query-passage pairs instead of binary relevance judgments (coarse-grained). To ease the false negative issues, more passages with higher diversities are considered when performing relevance annotations, especially in the test set, to ensure a more accurate evaluation. Apart from the textual query and passage data, other auxiliary resources are also provided, such as query types and XML files of documents which passages are generated from, to facilitate further studies. To evaluate the dataset, commonly used ranking models are implemented and tested on T2Ranking as baselines. The experimental results show that T2Ranking is challenging and there is still scope for improvement. The full data and all codes are available at https://github.com/THUIR/T2Ranking/.

Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the given image, such as 'What color are her eyes?'. The human generated crowdsourcing questions are relatively simple and sometimes have the bias toward certain entities or attributes [1, 55].

User behavior analysis has played an important role in Web information retrieval. Rare queries, whose frequencies are rather low, are usually ignored in existing studies due to the data sparseness. Little has been known about the mass of rare queries on either the information need or the user behavior. In this paper, we make an empirical study of users' behavior on rare queries using a large scale search log. Features concerning query, resource and post-query actions are analyzed, based on which we propose a practical categorization framework and obtain an overview of rare query composition. Further, we study the characteristics of several most commonly occurring types of rare queries, and suggest improving the search performance of them separately. This work gives more insights into understanding the long tail of queries and will be helpful for Web search in terms of rare queries.