Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection
Uppsala University（乌普萨拉大学）；The Ohio State University（俄亥俄州立大学）；University of Turku（图尔库大学）；Charles University in Prague（布拉格查理大学）；Stanford University（斯坦福大学）；Indiana University（印第安纳大学）
Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Jan Hajič, Christopher D. Manning, Sampo Pyysalo, Sebastian Schuster, Francis Tyers, Daniel Zeman
Universal Dependencies is an open community effort to create cross-linguistically consistent treebank annotation for many languages within a dependency-based lexicalist framework. The annotation consists in a linguistically motivated word segmentation; a morphological layer comprising lemmas, universal part-of-speech tags, and standardized morphological features; and a syntactic layer focusing on syntactic relations between predicates, arguments and modifiers. In this paper, we describe version 2 of the guidelines (UD v2), discuss the major changes from UD v1 to UD v2, and give an overview of the currently available treebanks for 90 languages.
A lack of large-scale human-annotated data has hampered the hierarchical discourse parsing of Chinese. In this paper, we present GCDT, the largest hierarchical discourse treebank for Mandarin Chinese in the framework of Rhetorical Structure Theory (RST). GCDT covers over 60K tokens across five genres of freely available text, using the same relation inventory as contemporary RST treebanks for English. We also report on this dataset's parsing experiments, including state-of-the-art (SOTA) scores for Chinese RST parsing and RST parsing on the English GUM dataset, using cross-lingual training in …
Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Department of Linguistics, University of Washington（华盛顿大学语言学系）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties unfamiliar to these models, whose labeled \emph{and unlabeled} data is too limited to train a monolingual model effectively. We propose the use of additional language-specific pretraining and vocabulary augmentation to adapt multilingual models to low-resource settings. Using dependency parsing of four diverse low-resource language varieties as a case study, w…
Harbin Institute of Technology（哈尔滨工业大学）；Baidu Inc.（百度公司）
Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain syntactic knowledge that is potential to benefit each other. This paper presents an universal framework for exploiting these multi-typed treebanks to improve parsing with deep multi-task learning. We consider two kinds of treebanks as source: the multilingual universal treebanks and the monolingual heterogeneous treebanks. Multiple treebanks are trained jointly and interacted with multi-level parameter sharing. Experiments on s…
Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）；Pompeu Fabra University（庞培法布拉大学）
We train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language information; and (iii) language-specific features (fine-grained POS tags). This input representation enables the parser not only to parse effectively in multiple languages, but also to generalize across languages based on linguistic universals and typological similarities, making it more effective to learn from limited annotations. Our parser's performance compares favorably to strong baselines…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language with a large treebank to a language with a small or nonexistent treebank, by sharing parameters between languages in the parser itself. We experiment with a diverse selection of languages in both simulated and truly low-resource scenarios, and show that multilingual CWRs greatly facilitate low-resource dependency parsing even without crosslingual supervision…
The University of Tokyo（东京大学）；Artificial Intelligence Research Center, AIST（产业技术综合研究所人工智能研究中心）；LeapMind Inc.（LeapMind公司）
Incorporating stronger syntactic biases into neural language models (LMs) is a long-standing goal, but research in this area often focuses on modeling English text, where constituent treebanks are readily available. Extending constituent tree-based LMs to the multilingual setting, where dependency treebanks are more common, is possible via dependency-to-constituency conversion methods. However, this raises the question of which tree formats are best for learning the model, and for which languages. We investigate this question by training recurrent neural network grammars (RNNGs) using various …
San Mateo High School（圣马特奥高中）；Georgetown University（乔治城大学）
We present the first linguistically annotated treebank of Ashokan Prakrit, an early Middle Indo-Aryan dialect continuum attested through Emperor Ashoka Maurya's 3rd century BCE rock and pillar edicts. For annotation, we used the multilingual Universal Dependencies (UD) formalism, following recent UD work on Sanskrit and other Indo-Aryan languages. We touch on some interesting linguistic features that posed issues in annotation: regnal names and other nominal compounds, "proto-ergative" participial constructions, and possible grammaticalizations evidenced by sandhi (phonological assimilation ac…
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究所）
Text discourse parsing plays an important role in understanding information flow and argumentative structure in natural language. Previous research under the Rhetorical Structure Theory (RST) has mostly focused on inducing and evaluating models from the English treebank. However, the parsing tasks for other languages such as German, Dutch, and Portuguese are still challenging due to the shortage of annotated data. In this work, we investigate two approaches to establish a neural, cross-lingual discourse parser via: (1) utilizing multilingual vector representations; and (2) adopting segment-lev…
We propose a practical scheme to train a single multilingual sequence labeling model that yields state of the art results and is small and fast enough to run on a single CPU. Starting from a public multilingual BERT checkpoint, our final model is 6x smaller and 27x faster, and has higher accuracy than a state-of-the-art multilingual baseline. We show that our model especially outperforms on low-resource languages, and works on codemixed input text without being explicitly trained on codemixed examples. We showcase the effectiveness of our method by reporting on part-of-speech tagging and morph…
We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependen…
Morphosyntactic probing of multilingual BERT models
ELKH Institute for Computer Science and Control (SZTAKI)（ELKH计算机科学与控制研究所（SZTAKI））；Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Comenius University in Bratislava（布拉迪斯拉发考门斯基大学）；Hebrew University of Jerusalem（耶路撒冷希伯来大学）；University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Lexicon-based methods using syntactic rules for polarity classification rely on parsers that are dependent on the language and on treebank guidelines. Thus, rules are also dependent and require adaptation, especially in multilingual scenarios. We tackle this challenge in the context of the Iberian Peninsula, releasing the first symbolic syntax-based Iberian system with rules shared across five official languages: Basque, Catalan, Galician, Portuguese and Spanish. The model is made available.
Charles University（查理大学）；Saarland University（萨尔兰大学）
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages. By leveraging a multilingual BERT self-attention model pretrained on 104 languages, we found that fine-tuning it on all datasets concatenated together with simple softmax classifiers for each UD task can result in state-of-the-art UPOS, UFeats, Lemmas, UAS, and LAS scores, without requiring any recurrent or language-specific components. We evaluate UDify …
Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural language processing. In this paper, we propose and analyze a neural POS tagging model that exploits AT. In our experiments on the Penn Treebank WSJ corpus and the Universal Dependencies (UD) dataset (27 languages), we find that AT not only improves the overall tagging accuracy, but also 1) prevents over-fitting well in low resource languages and 2) boosts t…
AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages
Princeton University（普林斯顿大学）；Laboratory for Artificial Intelligence, Princeton University（普林斯顿大学人工智能实验室）；Gaston Berger University（加斯顿·伯杰大学）；Mila, McGill University（麦吉尔大学米拉研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能教席）；Paris Nanterre University（巴黎南泰尔大学）；Paris-Saclay University（巴黎-萨克雷大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学实验室）；Université de Lorraine（洛林大学）；University of Trento（特伦托大学）；University of Minnesota–Twin Cities（明尼苏达大学双城分校）；Imperial College London（伦敦帝国学院）；Binghamton University（宾汉姆顿大学）；Makerere University（马凯雷雷大学）；Penn State University（宾夕法尼亚州立大学）；Mbarara University of Science and Technology（姆巴拉拉科技大学）；Chalmers University of Technology（查尔姆斯理工大学）；University of Ibadan（伊巴丹大学）；Nnamdi Azikiwe University（纳姆迪·阿齐基韦大学）；South African Centre for Digital Language Resources（南非数字语言资源中心）
While the highly multilingual Universal Dependencies (UD) project provides extensive guidelines for clausal structure as well as structure within canonical nominal phrases, a standard treatment is lacking for many "mischievous" nominal phenomena that break the mold. As a result, numerous inconsistencies within and across corpora can be found, even in languages with extensive UD treebanking work, such as English. This paper surveys the kinds of mischievous nominal expressions attested in English UD corpora and proposes solutions primarily with English in mind, but which may offer paths to solut…
The increasing diversity of languages used on the web introduces a new level of complexity to Information Retrieval (IR) systems. We can no longer assume that textual content is written in one language or even the same language family. In this paper, we demonstrate how to build massive multilingual annotators with minimal human expertise and intervention. We describe a system that builds Named Entity Recognition (NER) annotators for 40 major languages using Wikipedia and Freebase. Our approach does not require NER human annotated datasets or language specific resources like treebanks, parallel…
We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available. The method makes use of three steps: 1) a method for deriving cross-lingual word clusters, which can then be used in a multilingual parser; 2) a method for transferring lexical information from a target language to source language treebanks; 3) a method for integrating these steps with the density-driven annotation projection method of Rasooli and Collins (2015). Experiments show improvements over the state-of-the-art i…
