相关论文: Fast, Flexible, and Declarative Construction of Ab…

Syntactic parsing is essential in natural-language processing, with constituent structure being one widely used description of syntax. Traditional views of constituency demand that constituents consist of adjacent words, but this poses…

When applying the Transformer architecture to source code, designing a good self-attention mechanism is critical as it affects how node relationship is extracted from the Abstract Syntax Trees (ASTs) of the source code. We present Code…

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and…

Predictive models are fundamental to engineering reliable software systems. However, designing conservative, computable approximations for the behavior of programs (static analyses) remains a difficult and error-prone process for modern…

Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this paper, we…

Error recovery is an essential feature for a parser that should be plugged in Integrated Development Environments (IDEs), which must build Abstract Syntax Trees (ASTs) even for syntactically invalid programs in order to offer features such…

Autoregressive language models demonstrate excellent performance in various scenarios. However, the inference efficiency is limited by its one-step-one-word generation mode, which has become a pressing problem recently as the models become…

The application of machine learning algorithms to source code has grown in the past years. Since these algorithms are quite sensitive to input data, it is not surprising that researchers experiment with input representations. Nowadays, a…

Model structure and complexity selection remains a challenging problem in system identification, especially for parametric non-linear models. Many Evolutionary Algorithm (EA) based methods have been proposed in the literature for estimating…

This paper describes an approach to creating textual syntax for Do- main-Specific Languages (DSL). We consider target meta-model to be the main artifact and hence to be developed first. The key idea is to represent analysis of textual…

Syntactic natural language parsers have shown themselves to be inadequate for processing highly-ambiguous large-vocabulary text, as is evidenced by their poor performance on domains like the Wall Street Journal, and by the movement away…

Understanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent computational studies show that artificial neural language models spontaneously develop differentiated…

Automatic code review (ACR), which can relieve the costs of manual inspection, is an indispensable and essential task in software engineering. To deal with ACR, existing work is to serialize the abstract syntax tree (AST). However, making…

PEGs are a formal grammar foundation for describing syntax, and are not hard to generate parsers with a plain recursive decent parsing. However, the large amount of C-stack consumption in the recursive parsing is not acceptable especially…

We consider symbolic tree automata (sta) and symbolic tree transducers (stt). We characterize s-recognizable tree languages (which are the tree languages recognizable by sta) in terms of (classical) recognizable tree languages and…

Abstracting Gradual Typing (AGT) is a systematic approach to designing gradually-typed languages. Languages developed using AGT automatically satisfy the formal semantic criteria for gradual languages identified by Siek et al. [2015].…

Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical…

Text generation is a fundamental building block in natural language processing tasks. Existing sequential models performs autoregression directly over the text sequence and have difficulty generating long sentences of complex structures.…

Effective Service Function Chain (SFC) provisioning requires precise orchestration in dynamic and latency-sensitive networks. Reinforcement Learning (RL) improves adaptability but often ignores structured domain knowledge, which limits…

Decision tree models, including random forests and gradient-boosted decision trees, are widely used in machine learning due to their high predictive performance. However, their complex structures often make them difficult to interpret,…