Level Language Model Research Articles

A Simple, Efficient, Context‐sensitive Approach for Code Completion

AbstractCode completion helps developers use application programming interfaces (APIs) and frees them from remembering every detail. In this paper, we first describe a novel technique called Context‐sensitive Code Completion (CSCC) for improving the performance of API method call completion. CSCC is context sensitive in that it uses new sources of information as the context of a target method call. CSCC indexes method calls in code examples by their context. To recommend completion proposals, CSCC ranks candidate methods by the similarities between their contexts and the context of the target call. Evaluation using a set of subject systems and five popular state‐of‐the‐art techniques suggests that CSCC performs better than existing type or example‐based code completion systems. We conduct experiments to find how different contextual elements of the target call benefit CSCC. Next, we investigate the adaptability of the technique to support another form of code completion, i.e., field completion. Evaluation with eight different subject systems suggests that CSCC can easily support field completion with high accuracy. Finally, we compare CSCC with four popular statistical language models that support code completion. Results of statistical tests from our study suggest that CSCC not only outperforms those techniques that are based on token level language models, but also in most cases performs better or equally well with GraLan, the state‐of‐the‐art graph‐based language model. Copyright © 2016 John Wiley & Sons, Ltd.

Syllable language models for Mandarin speech recognition: Exploiting character language models

Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.

A procedure for the generation of a class of simulation models from databases

This paper shows the potential of using a higher level language, such as BASIC, to automatically generate syntactically correct simulation models from functional databases. The resulting models may then be executed directly by the general purpose simulation language of choice. The procedure is primarily developed for assembly line operations. However, it can be readily extended to network-based situations of the PERT/CPM type and MRP types. The proposed approach is based on the observation that although the simulation logic of network-based models is generally simple, the structure of such models is highly input-data dependent. In the context of most general purpose simulation languages, this dependence usually necessitates making changes in the simulation model itself to accommodate the new structure of the network. Such "custom" changes impede both the ease of maintenance and the portability of the model. The outgrowth of pursuing the use of higher level language to generate executable simulation models encompasses many of the goals inherent in the simulation language work, including little or no programming and ease of maintenance and verification. The power of the process comes from having to model the problem generically only once by using a suitable higher level language model generator. Specific situations are then accounted for simply by changing the input data to the model generator.