首页/论文/2012.04575

arXiv 2012.045752020-12-08cs.CL

The Role of Interpretable Patterns in Deep Learning for Morphology

Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Institute for Computer Science and Control（计算机科学与控制研究所）

Judit Acs, Andras Kornai

备注：: Best paper at the Hungarian NLP conference (MSZNY2020)
发表信息：: XVI. Magyar Számítógépes Nyelvészeti Konferencia, 2020, page 171-179 (MSZNY2020)

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We examine the role of character patterns in three tasks: morphological analysis, lemmatization and copy. We use a modified version of the standard sequence-to-sequence model, where the encoder is a pattern matching network. Each pattern scores all possible N character long subwords (substrings) on the source side, and the highest scoring subword's score is used to initialize the decoder as well as the input to the attention mechanism. This method allows learning which subwords of the input are important for generating the output. By training the models on the same source but different target, we can compare what subwords are important for different tasks and how they relate to each other. We define a similarity metric, a generalized form of the Jaccard similarity, and assign a similarity score to each pair of the three tasks that work on the same source but may differ in target. We examine how these three tasks are related to each other in 12 languages. Our code is publicly available.

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。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

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。

继续探索

相关论文

词形和根的屈折形态：阿拉伯语的破碎复数

Pattern-and-root inflectional morphology: the Arabic broken plural

LIGM, Université Paris-Est（LIGM，巴黎-est大学）；DLL, Universidade Federal do Espírito Santo（DLL，弗拉门杜斯皮里霍萨联邦大学）

本文提出了一种对阿拉伯语名词屈折形态的描述模型，重点在于阿拉伯语学者在管理词典和其他语言资源时的处理方式。其突破在于将传统的根-词形塞语模型反转为词形-根模型，优先考虑词形。该模型包括破碎复数（BPs），即通过修改词干形成的复数。它基于传统的塞语形态学中的根和词形概念。与传统阿拉伯语形态学相比，它将屈折的正式描述与派生和语义分开。如同传统阿拉伯语词典，可更新的词典以词形的词典条目结构进行组织，并且参考拼写完全带变音符号。在我们的模型中，阿拉伯语文本的形态分析直接使用词典进行，而无需形态音律规则。我们对名词屈折的分类是简单、有序且详细的。我们通过指定元音数量为v或vv，并忽略元音质量来简化单数词形的分类。根交替和正字法变化是独立于词形并以事实方式编码的，而不涉及深根或形态音律或正字法规则。具有三重词干BPs的名词根据22个词形细分到90个类别中进行分类，而具有四重词干BPs的名词根据3个词形细分到70个类别中进行分类。这些160个类别在考虑只影响单数的屈折变化时，变为300个屈折类别。我们提供了一种直接的编码方案，该方案应用于3200个BPs名词条目。

2026-05-21cs.CL

A Formal Description of Sorani Kurdish Morphology

Insight Centre for Data Analytics（数据分析洞察中心）；National University of Ireland Galway（爱尔兰国立大学戈尔韦分校）

Sorani Kurdish, also known as Central Kurdish, has a complex morphology, particularly due to the patterns in which morphemes appear. Although several aspects of Kurdish morphology have been studied, such as pronominal endoclitics and Izafa constructions, Sorani Kurdish morphology has received trivial attention in computational linguistics. Moreover, some morphemes, such as the emphasis endoclitic =îş, and derivational morphemes have not been previously studied. To tackle the complex morphology of Sorani, we provide a thorough description of Sorani Kurdish morphological and morphophonological c…

2021-09-08cs.CL

Fixing the Infix: Unsupervised Discovery of Root-and-Pattern Morphology

University of Illinois（伊利诺伊大学）

We present an unsupervised and language-agnostic method for learning root-and-pattern morphology in Semitic languages. This form of morphology, abundant in Semitic languages, has not been handled in prior unsupervised approaches. We harness the syntactico-semantic information in distributed word representations to solve the long standing problem of root-and-pattern discovery in Semitic languages. Moreover, we construct an unsupervised root extractor based on the learned rules. We prove the validity of learned rules across Arabic, Hebrew, and Amharic, alongside showing that our root extractor c…

2017-02-11cs.CL

Argumentative Explanations for Pattern-Based Text Classifiers

Imperial College London（伦敦帝国理工学院）

Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely underexplored. In this paper, we fill this gap by focusing on explanations for a specific interpretable model, namely pattern-based logistic regression (PLR) for binary text classification. We do so because, albeit interpretable, PLR is challenging when it comes to explanations. In particular, we found that a standard way to extract explanations from this model does not …

2022-05-22cs.AIcs.CLcs.LG

Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation

University of British Columbia（不列颠哥伦比亚大学）；Tianjin University（天津大学）；University of Fraser Valley（弗雷泽谷大学）

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers propose new attention augmentation methods to make transformers more accurate, efficient and interpretable. In this paper, we combine these two lines of research in a human-in-the-loop pipeline to first discover important task-specific attention patterns. Then those patterns are injected, not only to smaller models, but also to the original model. The benefits of …

2022-10-26cs.AIcs.CL

Constructing large scale biomedical knowledge bases from scratch with rapid annotation of interpretable patterns

BenevolentAI（benevolent人工智能公司）

Knowledge base construction is crucial for summarising, understanding and inferring relationships between biomedical entities. However, for many practical applications such as drug discovery, the scarcity of relevant facts (e.g. gene X is therapeutic target for disease Y) severely limits a domain expert's ability to create a usable knowledge base, either directly or by training a relation extraction model. In this paper, we present a simple and effective method of extracting new facts with a pre-specified binary relationship type from the biomedical literature, without requiring any training d…

2019-07-03cs.CL

更多相关论文收起更多论文

无国界词素：在阿拉伯语分词器和大语言模型中评估根-模式词素学

Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs

Saudi Data & AI Authority (SDAIA)（沙特数据与人工智能局）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；Princess Nourah Bint Abdulrahman University (PNU)（普罗瑟·努拉·本·阿卜杜勒拉赫曼大学）

研究评估了阿拉伯语分词器和大语言模型在处理根-模式词素学方面的表现，发现分词器的词素对齐并非生成词素学的必要或充分条件。

2026-03-16cs.AIcs.CL

通过可解释的Token模式理解与缓解分类错误

Understanding and Mitigating Classification Errors Through Interpretable Token Patterns

Cornell University（康奈尔大学）；Harvard University（哈佛大学）；Saarland University（萨尔大学）；CISPA（CISPA亥姆霍兹信息安全中心）

提出基于最小描述长度原则的Premise方法，通过发现区分正确与错误预测的token模式，为NLP分类器提供全局可解释的系统性错误描述，并在高度不平衡数据上有效恢复真实情况。

2023-11-18cs.AIcs.CL

一种基于规则的盖尔语形态学计算模型

A Rule-based Computational Model for Gaidhlig Morphology

1 School of Computing, Engineering, \& the Built Environment Edinburgh Napier University, Scotland

本文提出了一种基于规则的盖尔语形态学模型，利用维基词典数据构建规则库，以提升低资源语言处理的可解释性和应用价值。

2026-02-12cs.CL

Lightly-supervised Representation Learning with Global Interpretability

University of Arizona（亚利桑那大学）

We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction patterns, with the robust learning approaches proposed in representation learning. Our algorithm iteratively learns custom embeddings for both the multi-word entities to be extracted and the patterns that match them from a few example entities per category. We demonstrate that this representation-based approach outperforms three other state-of-the-art bootstra…

2018-05-29cs.CL

GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns

Imperial College London（伦敦帝国学院）；IBM Research（IBM研究院）

Data exploration is an important step of every data science and machine learning project, including those involving textual data. We provide a novel language tool, in the form of a publicly available Python library for extracting patterns from textual data. The library integrates a first public implementation of the existing GrASP algorithm. It allows users to extract patterns using a number of general-purpose built-in linguistic attributes (such as hypernyms, part-of-speech tags, and syntactic dependency tags), as envisaged for the original algorithm, as well as domain-specific custom attribu…

2022-06-16cs.AIcs.CLcs.LG

Interpretable Low-Rank Document Representations with Label-Dependent Sparsity Patterns

Rudjer Boskovic Institute（鲁杰尔·博什科维奇研究所）

In context of document classification, where in a corpus of documents their label tags are readily known, an opportunity lies in utilizing label information to learn document representation spaces with better discriminative properties. To this end, in this paper application of a Variational Bayesian Supervised Nonnegative Matrix Factorization (supervised vbNMF) with label-driven sparsity structure of coefficients is proposed for learning of discriminative nonsubtractive latent semantic components occuring in TF-IDF document representations. Constraints are such that the components pursued are …

2014-07-25cs.CLcs.IRcs.LG

Explaining Patterns in Data with Language Models via Interpretable Autoprompting

Microsoft Research（微软研究院）；Cornell University（康奈尔大学）

Large language models (LLMs) have displayed an impressive ability to harness natural language to perform complex tasks. In this work, we explore whether we can leverage this learned ability to find and explain patterns in data. Specifically, given a pre-trained LLM and data examples, we introduce interpretable autoprompting (iPrompt), an algorithm that generates a natural-language string explaining the data. iPrompt iteratively alternates between generating explanations with an LLM and reranking them based on their performance when used as a prompt. Experiments on a wide range of datasets, fro…

2023-01-26cs.AIcs.CLcs.LG

社交媒体中焦虑的早期语言模式：基于可解释语言特征的多维验证研究与作者不相交评估

Early Linguistic Pattern of Anxiety from Social Media Using Interpretable Linguistic Features: A Multi-Faceted Validation Study with Author-Disjoint Evaluation

本文提出了一种基于可解释语言特征的社交媒体焦虑检测方法，通过多维度验证和作者不相交评估，实现了高准确率和鲁棒性。

2026-01-16cs.AIcs.CLcs.LG