An official website of the United States government
Entity typing aims at predicting one or more words that describe the type(s) of a specific mention in a sentence. Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations. To comprehensively investigate the faithfulness and reliability of entity typing methods, we first systematically define distinct kinds of model biases that are reflected mainly from spurious correlations. Particularly, we identify six types of existing model biases, including mention-context bias, lexical overlapping bias, named entity bias, pronoun bias, dependency bias, and overgeneralization bias. To mitigate model biases, we then introduce a counterfactual data augmentation method. By augmenting the original training set with their debiasedcounterparts, models are forced to fully comprehend sentences and discover the fundamental cues for entity typing, rather than relying on spurious correlations for shortcuts. Experimental results on the UFET dataset show our counterfactual data augmentation approach helps improve generalization of different entity typing models with consistently better performance on both the original and debiased test sets.
more »
« less
Learning type annotation: is big data enough?
TypeScript is a widely used optionally-typed language where developers can adopt “pay as you go” typing: they can add types as desired, and benefit from static typing. The “type annotation tax” or manual effort required to annotate new or existing TypeScript can be reduced by a variety of automatic methods. Probabilistic machine-learning (ML) approaches work quite well. ML approaches use different inductive biases, ranging from simple token sequences to complex graphical neural network (GNN) models capturing syntax and semantic relations. More sophisticated inductive biases are hand-engineered to exploit the formal nature of software. Rather than deploying fancy inductive biases for code, can we just use “big data” to learn natural patterns relevant to typing? We find evidence suggesting that this is the case. We present TypeBert, demonstrating that even with simple token-sequence inductive bias used in BERT-style models and enough data, type-annotation performance of the most sophisticated models can be surpassed.
more »
« less
- Award ID(s):
- 1934568
- PAR ID:
- 10349460
- Date Published:
- Journal Name:
- Proceedings of ESEC/FSE Conference
- Page Range / eLocation ID:
- 1483 to 1486
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Type migration is the process of adding types to untyped code to gain assurance at compile time. TypeScript and other gradual type systems facilitate type migration by allowing programmers to start with imprecise types and gradually strengthen them. However, adding types is a manual effort and several migrations on large, industry codebases have been reported to have taken years. In the research community, there has been significant interest in using machine learning to automate TypeScript type migration. Existing machine learning models report a high degree of accuracy in predicting individual TypeScript type annotations. However, in this paper we argue that accuracy can be misleading, and we should address a different question: can an automatic type migration tool produce code that passes the TypeScript type checker? We present TypeWeaver, a TypeScript type migration tool into which one can plug in an arbitrary type prediction model. We evaluate TypeWeaver with three models from the literature: DeepTyper (a recurrent neural network), LambdaNet (a graph neural network), and InCoder (a general-purpose, multi-language transformer that supports fill-in-the-middle tasks). Our tool automates several steps that are necessary to use a type prediction model, including (1) importing types for a project’s dependencies; (2) migrating JavaScript modules to TypeScript notation; (3) inserting predicted type annotations into the program to produce TypeScript when needed; and (4) rejecting non-type predictions when needed. We evaluate TypeWeaver on a dataset of 513 JavaScript packages, including packages that have never been typed before. With the best type prediction model, we find that only 21% of packages type check, but more encouragingly, 69% of files type check successfully.more » « less
-
Large language models (LLMs) have reshaped the landscape of program synthesis. However, contemporary LLM-based code completion systems often hallucinate broken code because they lack appropriate code context, particularly when working with definitions that are neither in the training data nor near the cursor. This paper demonstrates that tighter integration with the type and binding structure of the programming language in use, as exposed by its language server, can help address this contextualization problem in a token-efficient manner. In short, we contend that AIs need IDEs, too! In particular, we integrate LLM code generation into the Hazel live program sketching environment. The Hazel Language Server is able to identify the type and typing context of the hole that the programmer is filling, with Hazel's total syntax and type error correction ensuring that a meaningful program sketch is available whenever the developer requests a completion. This allows the system to prompt the LLM with codebase-wide contextual information that is not lexically local to the cursor, nor necessarily in the same file, but that is likely to be semantically local to the developer's goal. Completions synthesized by the LLM are then iteratively refined via further dialog with the language server, which provides error localization and error messages. To evaluate these techniques, we introduce MVUBench, a dataset of model-view-update (MVU) web applications with accompanying unit tests that have been written from scratch to avoid data contamination, and that can easily be ported to new languages because they do not have large external library dependencies. These applications serve as challenge problems due to their extensive reliance on application-specific data structures. Through an ablation study, we examine the impact of contextualization with type definitions, function headers, and errors messages, individually and in combination. We find that contextualization with type definitions is particularly impactful. After introducing our ideas in the context of Hazel, a low-resource language, we duplicate our techniques and port MVUBench to TypeScript in order to validate the applicability of these methods to higher-resource mainstream languages. Finally, we outline ChatLSP, a conservative extension to the Language Server Protocol (LSP) that language servers can implement to expose capabilities that AI code completion systems of various designs can use to incorporate static context when generating prompts for an LLM.more » « less
-
Gradual typing allows programmers to use both static and dynamic typing in a single program. However, a well-known problem with sound gradual typing is that the interactions between static and dynamic code can cause significant performance degradation. These performance pitfalls are hard to predict and resolve, and discourage users from using gradual typing features. For example, when migrating to a more statically typed program, often adding a type annotation will trigger a slowdown that can be resolved by adding more annotations elsewhere, but since it is not clear where the additional annotations must be added, the easier solution is to simply remove the annotation. To address these problems, we develop: (1) a static cost semantics that accurately predicts the overhead of static-dynamic interactions in a gradually typed program, (2) a technique for efficiently inferring such costs for all combinations of inferrable type assignments in a program, and (3) a method for translating the results of this analysis into specific recommendations and explanations that can help programmers understand, debug, and optimize the performance of gradually typed programs. We have implemented our approach in Herder, a tool for statically analyzing the performance of different typing configurations for Reticulated Python programs. An evaluation on 15 Python programs shows that Herder can use this analysis to accurately and efficiently recommend type assignments that optimize the performance of these programs without sacrificing the safety guarantees provided by static typing.more » « less
-
The growing adoption of hardware accelerators driven by their intelligent compiler and runtime system counterparts has democratized ML services and precipitously reduced their execution times. This motivates us to shift our attention to efficiently serve these ML services under distributed settings and characterize the overheads imposed by the RPC mechanism ('RPC tax') when serving them on accelerators. The RPC implementations designed over the years implicitly assume the host CPU services the requests, and we focus on expanding such works towards accelerator-based services. While recent proposals calling for SmartNICs to take on this task are reasonable for simple kernels, serving complex ML models requires a more nuanced view to optimize both the data-path and the control/orchestration of these accelerators. We program today's commodity network interface cards (NICs) to split the control and data paths for effective transfer of control while efficiently transferring the payload to the accelerator. As opposed to unified approaches that bundle these paths together, limiting the flexibility in each of these paths, we design and implement SplitRPC - a control + data path optimizing RPC mechanism for ML inference serving. SplitRPC allows us to optimize the datapath to the accelerator while simultaneously allowing the CPU to maintain full orchestration capabilities. We implement SplitRPC on both commodity NICs and SmartNICs and demonstrate how GPU-based ML services running different compiler/runtime systems can benefit. For a variety of ML models served using different inference runtimes, we demonstrate that SplitRPC is effective in minimizing the RPC tax while providing significant gains in throughput and latency over existing kernel by-pass approaches, without requiring expensive SmartNIC devices.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3468264.3473135
