Discourse Representation Theory (DRT) distinguishes itself from other
semantic representation frameworks by its ability to model complex semantic and
discourse phenomena through structural nesting and variable binding. While
seq2seq models hold the state of the art on DRT parsing, their accuracy
degrades with the complexity of the sentence, and they sometimes struggle to
produce well-formed DRT representations. We introduce the AMS parser, a
compositional, neurosymbolic semantic parser for DRT. It rests on a novel
mechanism for predicting quantifier scope. We show that the AMS parser reliably
produces well-formed outputs and performs well on DRT parsing, especially on
complex sentences.

用于预测量化器范围的一种新颖机制的 AMS 解析器，在 Discourse Representation Theory（DRT）解析方面表现良好，尤其是对于复杂句子。

扩展范围的组合语义解析：面向 DRT

Scope-enhanced Compositional Semantic Parsing for DRT

Semantic parsing offers many opportunities to improve natural language
understanding. We present a semantically annotated parallel corpus for English,
German, Italian, and Dutch where sentences are aligned with scoped meaning
representations in order to capture the semantics of negation, modals,
quantification, and presupposition triggers. The semantic formalism is based on
Discourse Representation Theory, but concepts are represented by WordNet
synsets and thematic roles by VerbNet relations. Translating scoped meaning
representations to sets of clauses enables us to compare them for the purpose
of semantic parser evaluation and checking translations. This is done by
computing precision and recall on matching clauses, in a similar way as is done
for Abstract Meaning Representations. We show that our matching tool for
evaluating scoped meaning representations is both accurate and efficient.
Applying this matching tool to three baseline semantic parsers yields F-scores
between 43% and 54%. A pilot study is performed to automatically find changes
in meaning by comparing meaning representations of translations. This
comparison turns out to be an additional way of (i) finding annotation mistakes
and (ii) finding instances where our semantic analysis needs to be improved.

本文介绍了针对英语，德语，意大利语和荷兰语的语义注释平行语料库，旨在捕获否定，情态动词，量化和假设触发器的语义。将平行语料中句子与范围内的义结构对齐，可以将概念表示为 WordNet 同义词集，并通过 VerbNet 关系表示语义角色。通过将范围内的意义表示翻译为一组从句，可以比较它们以进行语义解析器的评估和翻译检查。我们证明了用于评估范围内的含义表示的匹配工具既准确又高效。将此匹配工具应用于三个基线语义解析器，得到的 F 得分介于 43％至 54％之间。通过比较翻译的意义表示来自动查找意义变化的尝试研究表明，这种比较是发现注释错误和需要改进语义分析的实例的另一种方法。

评估 Scoped Meaning Representations

Evaluating Scoped Meaning Representations

The Parallel Meaning Bank is a corpus of translations annotated with shared,
formal meaning representations comprising over 11 million words divided over
four languages (English, German, Italian, and Dutch). Our approach is based on
cross-lingual projection: automatically produced (and manually corrected)
semantic annotations for English sentences are mapped onto their word-aligned
translations, assuming that the translations are meaning-preserving. The
semantic annotation consists of five main steps: (i) segmentation of the text
in sentences and lexical items; (ii) syntactic parsing with Combinatory
Categorial Grammar; (iii) universal semantic tagging; (iv) symbolization; and
(v) compositional semantic analysis based on Discourse Representation Theory.
These steps are performed using statistical models trained in a semi-supervised
manner. The employed annotation models are all language-neutral. Our first
results are promising.

Parallel Meaning Bank 是一个包含四种语言 (英语、德语、意大利语和荷兰语) 的 11 百万单词的翻译语料库，词汇对齐的翻译文本上的语义注释基于跨语言映射，采用统计模型进行。语义注释由五个主要步骤组成，包括：句子和词汇项的分割；组合范畴语法的句法分析；通用语义标签；符号化；基于话语表征理论的组成语义分析。这些步骤都是使用半监督训练的统计模型执行的。使用的注释模型都是语言无关的。我们的初步结果很有前途。