Stepwise API usage assistance using n -gram language models

We propose algorithms to train production-quality n-gram language models using federated learning. Federated learning is a distributed computation platform that can be used to train global models for portable devices such as smart phones. Federated learning is especially relevant for applications handling privacy-sensitive data, such as virtual keyboards, because training is performed without the users’ data ever leaving their devices. While the principles of federated learning are fairly generic, its methodology assumes that the underlying models are neural networks. However, virtual keyboards are typically powered by n-gram language models for latency reasons. We propose to train a recurrent neural network language model using the decentralized FederatedAveraging algorithm and to approximate this federated model server-side with an n-gram model that can be deployed to devices for fast inference. Our technical contributions include ways of handling large vocabularies, algorithms to correct capitalization errors in user data, and efficient finite state transducer algorithms to convert word language models to word-piece language models and vice versa. The n-gram language models trained with federated learning are compared to n-grams trained with traditional server-based algorithms using A/B tests on tens of millions of users of a virtual keyboard. Results are presented for two languages, American English and Brazilian Portuguese. This work demonstrates that high-quality n-gram language models can be trained directly on client mobile devices without sensitive training data ever leaving the devices.

Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies have shown that statistical language modeling techniques can improve the performance of code completion tools through learning from large-scale software repositories. However, these models suffer from two major drawbacks: a) Existing research uses static embeddings, which map a word to the same vector regardless of its context. The differences in the meaning of a token in varying contexts are lost when each token is associated with a single representation; b) Existing language model based code completion models perform poor on completing identifiers, and the type information of the identifiers is ignored in most of these models. To address these challenges, in this paper, we develop a multi-task learning based pre-trained language model for code understanding and code generation with a Transformer-based neural architecture. We pre-train it with hybrid objective functions that incorporate both code understanding and code generation tasks. Then we fine-tune the pre-trained model on code completion. During the completion, our model does not directly predict the next token. Instead, we adopt multi-task learning to predict the token and its type jointly and utilize the predicted type to assist the token prediction. Experiments results on two real-world datasets demonstrate the effectiveness of our model when compared with state-of-the-art methods.

Integrated Development Environments (IDEs) are pivotal in enhancing productivity with features like code completion in modern software development. Recent advancements in Natural Language Processing (NLP) have empowered neural language models for code completion. In this study, we present an extensive investigation of the impact of open and closed vocabulary systems on the task of code completion. Specifically, we compare open and closed vocabulary systems with various vocabulary sizes to observe their impact on code completion performance. We experiment with three different open vocabulary systems: byte pair encoding (BPE), WordPiece and Unigram to compare them with closed-vocabulary systems to analyze their modeling performance. We also conduct experiments with different context sizes to study their impact on code completion performance. We have experimented using various prominent language models, including one from recurrent neural networks and five from transformers. Our results indicate that vocabulary size significantly impacts modeling performance and can artificially boost the accuracy of code completion models, especially in the case of a closed-vocabulary system. Moreover, we find that different vocabulary systems have varying impacts on token coverage, whereas open-vocabulary systems exhibit better token coverage. Our findings offer valuable insights for building effective code completion models, aiding researchers and practitioners in this field.

Traditional program slicing techniques are crucial for early bug detection and manual/automated debugging of online code snippets. Nevertheless, their inability to handle incomplete code hinders their real-world applicability in such scenarios. To overcome these challenges, we present NS-Slicer, a novel learning-based approach that predicts static program slices for both complete and partial code Our tool leverages a pre-trained language model to exploit its understanding of fine-grained variable-statement dependencies within source code. With this knowledge, given a variable at a specific location and a statement in a code snippet, NS-Slicer determines whether the statement belongs to the backward slice or forward slice, respectively. We conducted a series of experiments to evaluate NS-Slicer's performance. On complete code, it predicts the backward and forward slices with an F1-score of 97.41% and 95.82%, respectively, while achieving an overall F1-score of 96.77%. Notably, in 85.20% of the cases, the static program slices predicted by NS-Slicer exactly match entire slices from the oracle. For partial programs, it achieved an F1-score of 96.77%–97.49% for backward slicing, 92.14%–95.40% for forward slicing, and an overall F1-score of 94.66%–96.62%. Furthermore, we demonstrate NS-Slicer's utility in vulnerability detection (VD), integrating its predicted slices into an automated VD tool. In this setup, the tool detected vulnerabilities in Java code with a high F1-score of 73.38%. We also include the analyses studying NS-Slicer’s promising performance and limitations, providing insights into its understanding of intrinsic code properties such as variable aliasing, leading to better slicing.

A study of n-gram and decision tree letter language modeling methods

This paper proposes a method of combining two n-gram language models, one constructed from a very small corpus of the right domain of interest, the other constructed from a large but less adequate corpus, resulting in a significantly enhanced language model. This method is based on the observation that a small corpus from the right domain has high quality n-grams but has serious sparseness problem, while a large corpus from a different domain has more n-gram statistics but inadequately biased. Two n-gram models are combined by extending the idea of Katz’s backoff. We ran experiments with 3-gram language models constructed from newspaper corpora of several million to tens of million words together with models from smaller broadcast news corpora. The target domain was broadcast news. We obtained significant improvement (30%) by incorporating a small corpus around one thirtieth size of the newspaper corpus.

Code completion, one of the most useful features in the Integrated Development Environments (IDEs), can accelerate software development by suggesting the libraries, APIs, and method names in real-time. Recent studies have shown that statistical language models can improve the performance of code completion tools through learning from large-scale software repositories. However, these models suffer from three major drawbacks: a) The hierarchical structural information of the programs is not fully utilized in the program's representation; b) In programs, the semantic relationships can be very long. Existing recurrent neural networks based language models are not sufficient to model the long-term dependency. c) Existing approaches perform a specific task in one model, which leads to the underuse of the information from related tasks. To address these challenges, in this paper, we propose a self-attentional neural architecture for code completion with multi-task learning. To utilize the hierarchical structural information of the programs, we present a novel method that considers the path from the predicting node to the root node. To capture the long-term dependency in the input programs, we adopt a self-attentional architecture based network as the base language model. To enable the knowledge sharing between related tasks, we creatively propose a Multi-Task Learning (MTL) framework to learn two related tasks in code completion jointly. Experiments on three real-world datasets demonstrate the effectiveness of our model when compared with state-of-the-art methods.

N-gram language models are frequently used by the speech recognition systems to constrain and guide the search. N-gram models use only the last N-1 words to predict the next word. Typical values of N that are used range from 2-4. N-gram language models thus lack the long-term context information. We show that the predictive power of the N-gram language models can be improved by using long-term context information about the topic of discussion. We use information retrieval techniques to generalize the available context information for topic-dependent language modeling. We demonstrate the effectiveness of this technique by performing experiments on the Wall Street Journal text corpus, which is a relatively difficult task for topic-dependent language modeling since the text is relatively homogeneous. The proposed method can reduce the perplexity of the baseline language model by 37%, indicating the predictive power of the topic-dependent language model.

This paper presents a language model adaptation technique to build a single static language model from a set of language models each trained on a separate text corpus while aiming to maximize the likelihood of an adaptation data set given as a development set of sentences. The proposed model can be considered as a mixture of mixture language models. The mixture model at the top level is a sentence-level mixture model where each sentence is assumed to be drawn from one of a discrete set of topic or task clusters. After selecting a cluster, each n-gram is assumed to be drawn from one of the given n-gram language models. We estimate cluster mixture weights and n-gram language model mixture weights for each cluster using the expectation-maximization (EM) algorithm to seek the parameter estimates maximizing the likelihood of the development sentences. This mixture of mixture models can be represented efficiently as a static n-gram language model using the previously proposed Bayesian language model interpolation technique. We show a significant improvement with this technique (both perplexity and WER) compared to the standard one level interpolation scheme.

Biases in language and their reflection in language models have attracted researchers' attention, particularly with the growth of large language models (LLMs). However, many questions on the links between language models and people’s biased attitudes remain unanswered. In the current study we focus on gender–career bias to examine the extent to which language models can be used to model behavioural responses in the Gender–Career Implicit Association Test (IAT). We provide a systematic evaluation of a range of language models, including n-gram, count vector, predict (word2vec), and Large Language Models (LLMs), to determine how well they capture people’s behaviour in the IAT. We compared response time data from over 800,000 participants against 25 language models, with a total of 675 model variants. We find that many language models, including large language models (LLMs), correlated well with human behavior. While results support previous findings for both predict and count model families, we observed that performance of LLMs was consistently different from that of simpler predict models, particularly in terms of the direction and strength of correlations with reaction time and bias. This divergence may indicate successful attempts to mitigate bias in LLMs while preserving other aspects of linguistic information. Our findings reinforce the idea that societal biases are generally encoded in language, but that large language models can exhibit behaviors different to classical language models.

Software Defect Prediction (SDP) plays an active area in many research domain of Software Quality of Assurance (SQA). Many existing research studies are based on software traditional metric sets and defect prediction models are built in machine language to detect the bug for limited source code line. Inspired by the above existing system. In this paper, defect prediction is focused on predicting defects in source code. The objective of this thesis is to improve the software quality for accurate defect prediction is source code for file level. So, that it helps the developer to find the bug and fix the issue, to make better use of a resource which reduces the test effort, minimize the cost and improve the quality of software. A new approach is introduced to improve the prediction performance of Bidirectional RNNLM in Deep Neural Network. To build the defect prediction model a defect learner framework is proposed and first it need to build a Neural Language Model. Using this Language Model it helps to learn to deep semantic features in source code and it train & test the model. Based on language model it combined with software traditional metric sets to measure the code and find the defect. The probability of language model and metric set Cross-Entropy with Abstract Syntax Tree (CE-AST) metric is used to evaluate the defect proneness and set as a metric label. For classification the metric label K-NN classifier is used. BPTT algorithm for learning RNN will provide additional improvement, it improves the predictions performance to find the dynamic error.

The backoff hierarchical class n-gram language models (LMs) are a generalization of the common backoff word n-gram LMs. Compared to the traditional backoff word n-gram LMs that uses (n-1)-gram to estimate the likelihood of an unseen n-gram event, backoff hierarchical class n-gram LMs uses a class hierarchy to define an appropriate context. We study the impact of the hierarchy depth on the performance of the approach. Performance is evaluated on several databases such us switchboard, call-home and wall street journal (WSJ). Results show that better improvement is achieved when a shallow word (few levels) tree is used. Experiments show up to 26% improvement on the unseen events perplexity and up to 12% improvement in the word error rate (WER).

Code completion is an essential feature of IDEs, yet current autocompleters are restricted to either grammar-based or NLP-based single token completions. Both approaches have significant drawbacks: grammar-based autocompletion is restricted in dynamically-typed language environments, whereas NLP-based autocompleters struggle to understand the semantics of the programming language and the developer's code context. In this work, we present CodeFill, a language model for autocompletion that combines learned structure and naming information. Using a parallel Transformer architecture and multi-task learning, CodeFill consumes sequences of source code token names and their equivalent AST token types. Uniquely, CodeFill is trained both for single-token and multi-token (statement) prediction, which enables it to learn long-range dependencies among grammatical and naming elements. We train CodeFill on two datasets, consisting of 29M and 425M lines of code, respectively. To make the evaluation more realistic, we develop a method to automatically infer points in the source code at which completion matters. We compare CodeFill against four baselines and two state-of-the-art models, GPT-C and TravTrans+.CodeFill surpasses all baselines in single token prediction (MRR: 70.9% vs. 66.2% and 67.8%) and outperforms the state of the art for multi-token prediction (ROUGE-L: 63.7% vs. 52.4% and 59.2%, for n=4 tokens). We publicly release our source code and datasets.

Although n-gram models are still the de facto standard in language modeling for speech recognition, it has been shown that more sophisticated models achieve better accuracy by taking additional information, such as syntactic rules, semantic relations or domain knowledge into account. Unfortunately, most of the effort in developing such models goes into the implementation of handcrafted inference routines. What lacks is a generic mechanism to introduce background knowledge into a language model. We propose the use of dynamic Bayesian networks for this purpose. Dynamic Bayesian networks can be seen as a generalization of the n-gram models and hmms traditionally used in language modeling and speech recognition. Whereas those models use a single random variable to represent state, Bayesian networks can have any number of variables. As such they are particularly well-suited for the construction of models that take additional information into account. In this paper language modeling with belief networks is discussed. Examples of belief network implementations of well-known language models are given and a new model is presented that models dependencies between the content words in a sentence.KeywordsBayesian NetworkSpeech RecognitionLanguage ModelContent WordDynamic Bayesian NetworkThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A fast and memory-efficient N-gram language model lookup method for large vocabulary continuous speech recognition