Multilingual topic models enable document analysis across languages through coherent multilingual summaries of the data. However, there is no standard and effective metric to evaluate the quality of multilingual topics. We introduce a new intrinsic evaluation of multilingual topic models that correlates well with human judgments of multilingual topic coherence as well as performance in downstream applications. Importantly, we also study evaluation for lowresource languages. Because standard metrics fail to accurately measure topic quality when robust external resources are unavailable, we propose an adaptation model that improves the accuracy and reliability of these metrics in low-resource settings.

Finding out an effective way to score Chinese written essays automatically remains challenging for researchers. Several methods have been proposed and developed but limited in the character and word usage levels. As one of the scoring standards, however, content or topic perspective is also an important and necessary indicator to assess an essay. Therefore, in this paper, we propose a novel perspective -topic, and a new method integrating topic modeling strategy called Regularized Latent Semantic Indexing to recognize the latent topics and Support Vector Machines to train the scoring model. Experimental results show that automated Chinese essay scoring from topic perspective is effective which can improve the rating agreement to 89%.

Chinese text error detection and correction is widely applicable, but the methods so far are not robust enough for industrial use. In this paper, a new method is proposed based on Tri-gram modeled-Weighted Finite-State Transducer (WFST). By integrating confusing-character table, beam search and A* search, we evaluate the performance on real test essays. Various experiments have been conducted to prove that the proposed method is effective with the recall rate of 85.68%, the detection accuracy of 91.22% and the correction accuracy of 87.30%.

No abstract

Writing has been increasingly regarded by the testers of language tests as an important indicator to assess the language skill of testees. As such tests become more and more popular and the number of testees becomes larger, it is a huge task to score so many essays by raters. So far, many methods have been used to solve this problem and the traditional method is Latent Semantic Analysis (LSA). In this paper, we introduce a new incremental method of LSA to score essays effectively when the dataset is massive. By comparison of the traditional method and our new incremental method, concerning the running time and memory usage, experimental results make it obvious that the incremental method has a huge advantage over the traditional method. Furthermore, we use real corpora of test essays submitted to the MHK test (Chinese Proficiency Test for Minorities), to demonstrate that the incremental method is not only efficient but also effective in performing LSA. The experimental results also show that when using incremental LSA, the scoring accuracy can reach 88.8%.