arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.02564cs.CLcs.AIcs.LG
收藏

一种真正联合的分割与句法分析神经架构

A Truly Joint Neural Architecture for Segmentation and Parsing

Bar Ilan University(巴伊兰大学)

Danit Yshaayahu Levi, Reut Tsarfaty

AI总结:

针对形态丰富语言中分割与句法分析流水线误差传播问题,提出基于格表示和弧因子模型的真正联合LLM架构,在希伯来语UD三项任务上达到SOTA。

摘要:

当代多语言依存句法分析器能够解析多种不同语言,但对于形态丰富语言(MRLs),已证实其性能低于其他语言。关键挑战在于,由于空格分隔的输入词元具有高度形态复杂性和歧义性,作为句法树中节点的语言单位无法预先确定。面向MRLs的前神经依存句法分析器遵循联合形态句法假设,即形态分割与句法分析应联合求解,而不是采用先分割后分析的流水线方式。然而,迄今为止的神经最先进分析器都使用严格流水线。本文提出一种联合神经架构,其中保留输入全部形态歧义的基于格的表示被提供给弧因子模型,该模型随后同时求解形态分割和句法分析任务。我们在希伯来语这一丰富且高度歧义的MRL上进行的实验表明,单一模型在UD希伯来语部分的句法分析、标注和分割任务上均达到最先进性能。所提出的架构基于LLM且与语言无关,为MRLs进一步提升性能并缩小与其他语言的差距提供了坚实基础。

英文摘要:

Contemporary multilingual dependency parsers can parse a diverse set of languages, but for Morphologically Rich Languages (MRLs), performance is attested to be lower than other languages. The key challenge is that, due to high morphological complexity and ambiguity of the space-delimited input tokens, the linguistic units that act as nodes in the tree are not known in advance. Pre-neural dependency parsers for MRLs subscribed to the joint morpho-syntactic hypothesis, stating that morphological segmentation and syntactic parsing should be solved jointly, rather than as a pipeline where segmentation precedes parsing. However, neural state-of-the-art parsers to date use a strict pipeline. In this paper we introduce a joint neural architecture where a lattice-based representation preserving all morphological ambiguity of the input is provided to an arc-factored model, which then solves the morphological segmentation and syntactic parsing tasks at once. Our experiments on Hebrew, a rich and highly ambiguous MRL, demonstrate state-of-the-art performance on parsing, tagging and segmentation of the Hebrew section of UD, using a single model. This proposed architecture is LLM-based and language agnostic, providing a solid foundation for MRLs to obtain further performance improvements and bridge the gap with other languages.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑