Video retrieval is becoming increasingly important owing to the rapid emergence of videos on the Internet. The dominant paradigm for video retrieval learns video-text representations by pushing the distance between the similarity of positive pairs and that of negative pairs apart from a fixed margin. However, negative pairs used for training are sampled randomly, which indicates that the semantics between negative pairs may be related or even equivalent, while most methods still enforce dissimilar representations to decrease their similarity. This phenomenon leads to inaccurate supervision and poor performance in learning video-text representations. While most video retrieval methods overlook that phenomenon, we propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue. First, we design the calculation framework of the adaptive margin, including the method of distance measurement and the function between the distance and the margin. Then, we explore a novel implementation called "Cross-Modal Generalized Self-Distillation" (CMGSD), which can be built on the top of most video retrieval models with few modifications. Notably, CMGSD adds few computational overheads at train time and adds no computational overhead at test time. Experimental results on three widely used datasets demonstrate that the proposed method can yield significantly better performance than the corresponding backbone model, and it outperforms state-of-the-art methods by a large margin.

Topic segmentation plays an important role for discourse parsing and information retrieval.Due to the absence of training data, previous work mainly adopts unsupervised methods to rank semantic coherence between paragraphs for topic segmentation.In this paper, we present an intuitive and simple idea to automatically create a "quasi" training dataset, which includes a large amount of text pairs from the same or different documents with different semantic coherence.With the training corpus, we design a symmetric CNN neural network to model text pairs and rank the semantic coherence within the learning to rank framework.Experiments show that our algorithm is able to achieve competitive performance over strong baselines on several real-world datasets.

Manually annotated corpora are indispensable resources, yet for many annotation tasks, such as the creation of treebanks, there exist multiple corpora with different and incompatible annotation guidelines. This leads to an inefficient use of human expertise, but it could be remedied by integrating knowledge across corpora with different annotation guidelines. In this article we describe the problem of annotation adaptation and the intrinsic principles of the solutions, and present a series of successively enhanced models that can automatically adapt the divergence between different annotation formats. We evaluate our algorithms on the tasks of Chinese word segmentation and dependency parsing. For word segmentation, where there are no universal segmentation guidelines because of the lack of morphology in Chinese, we perform annotation adaptation from the much larger People's Daily corpus to the smaller but more popular Penn Chinese Treebank. For dependency parsing, we perform annotation adaptation from the Penn Chinese Treebank to a semantics-oriented Dependency Treebank, which is annotated using significantly different annotation guidelines. In both experiments, automatic annotation adaptation brings significant improvement, achieving state-of-the-art performance despite the use of purely local features in training.

We present a novel translation model, which simultaneously exploits the constituency and dependency trees on the source side, to combine the advantages of two types of trees.We take head-dependents relations of dependency trees as backbone and incorporate phrasal nodes of constituency trees as the source side of our translation rules, and the target side as strings.Our rules hold the property of long distance reorderings and the compatibility with phrases.Large-scale experimental results show that our model achieves significantly improvements over the constituency-to-string (+2.45 BLEU on average) and dependencyto-string (+0.91 BLEU on average) models, which only employ single type of trees, and significantly outperforms the state-of-theart hierarchical phrase-based model (+1.12BLEU on average), on three Chinese-English NIST test sets.

Collocation translation is important for machine translation and many other NLP tasks. Unlike previous methods using bilingual parallel corpora, this paper presents a new method for acquiring collocation translations by making use of monolingual corpora and linguistic knowledge. First, dependency triples are extracted from Chinese and English corpora with dependency parsers. Then, a dependency triple translation model is estimated using the EM algorithm based on a dependency correspondence assumption. The generated triple translation model is used to extract collocation translations from two monolingual corpora. Experiments show that our approach outperforms the existing monolingual corpus based methods in dependency triple translation and achieves promising results in collocation translation extraction.