Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGenre as Weak Supervision for Cross-lingual Dependency Parsing
النوع كما هو ضعف الإشراف على تحليل التبعية عبر اللغات
372
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لقد أظهر العمل الحديث أن نماذج اللغة المحظورة غير المؤمنة تعلمت تمثيل مفاهيم تقلص البيانات من تباين اللغة والتي يمكن استخدامها لتحديد بيانات التدريب المستهدف بالمجال. تتوفر تسميات أنواع DataSet في كثير من الأحيان، ومع ذلك لا تزال غير مستكشفة إلى حد كبير في الإعدادات عبر اللغات. نستفيد هذا النوع من البيانات الوصفية باعتباره إشارة إشرافية ضعيفة لتحديد البيانات المستهدف في تحليل التبعية الصفرية. على وجه التحديد، نقوم بتعيين معلومات النوع من Treebank-Level لمستوى الجملة على مستوى الجملة الدقيقة، بهدف تضخيم المعلومات المخزنة ضمنيا في تمثيلات سياقية غير مدفوعة غير المدعومة. نوضح أن هذا النوع قابل للاسترداد من المدينات السياقية متعددة اللغات وأنه يوفر إشارة فعالة لتحديد بيانات التدريب في السيناريوهات عبر اللغات والصفرية. بالنسبة إلى 12 لغة Low-Resource Treebanks، ستة منها اختبار فقط، فإن أساليبنا الخاصة النوعية تفوقها بشكل كبير خطوط الأساس التنافسية وكذلك الأساليب القائمة على التضمين الحديثة لتحديد البيانات. علاوة على ذلك، يوفر اختيار البيانات المستندة إلى النوع من النوعين نتائج جديدة من الفنادق الجديدة لمدة ثلاثة من هذه اللغات المستهدفة.
Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized representations. We demonstrate that genre is recoverable from multilingual contextual embeddings and that it provides an effective signal for training data selection in cross-lingual, zero-shot scenarios. For 12 low-resource language treebanks, six of which are test-only, our genre-specific methods significantly outperform competitive baselines as well as recent embedding-based methods for data selection. Moreover, genre-based data selection provides new state-of-the-art results for three of these target languages.
References used
https://aclanthology.org/
rate research
Read More
Manually annotating a treebank is time-consuming and labor-intensive. We conduct delexicalized cross-lingual dependency parsing experiments, where we train the parser on one language and test on our target language. As our test case, we use Xibe, a s
everely under-resourced Tungusic language. We assume that choosing a closely related language as the source language will provide better results than more distant relatives. However, it is not clear how to determine those closely related languages. We investigate three different methods: choosing the typologically closest language, using LangRank, and choosing the most similar language based on perplexity. We train parsing models on the selected languages using UDify and test on different genres of Xibe data. The results show that languages selected based on typology and perplexity scores outperform those predicted by LangRank; Japanese is the optimal source language. In determining the source language, proximity to the target language is more important than large training sizes. Parsing is also influenced by genre differences, but they have little influence as long as the training data is at least as complex as the target.
State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such settings to a
utomatically generate weakly labeled training data. However, learning with weak rules is challenging due to their inherent heuristic and noisy nature. An additional challenge is rule coverage and overlap, where prior work on weak supervision only considers instances that are covered by weak rules, thus leaving valuable unlabeled data behind. In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task. To this end, we leverage task-specific unlabeled data through self-training with a model (student) that considers contextualized representations and predicts pseudo-labels for instances that may not be covered by weak rules. We further develop a rule attention network (teacher) that learns how to aggregate student pseudo-labels with weak rule labels, conditioned on their fidelity and the underlying context of an instance. Finally, we construct a semi-supervised learning objective for end-to-end training with unlabeled data, domain-specific rules, and a small amount of labeled data. Extensive experiments on six benchmark datasets for text classification demonstrate the effectiveness of our approach with significant improvements over state-of-the-art baselines.
Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervis
ed SRL training data are not abundant. Cross-lingual learning can improve performance in this setting by transferring knowledge from high-resource languages to low-resource ones. Moreover, we hypothesize that annotations of syntactic dependencies can be leveraged to further facilitate cross-lingual transfer. In this work, we perform an empirical exploration of the helpfulness of syntactic supervision for crosslingual SRL within a simple multitask learning scheme. With comprehensive evaluations across ten languages (in addition to English) and three SRL benchmark datasets, including both dependency- and span-based SRL, we show the effectiveness of syntactic supervision in low-resource scenarios.
In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in any language, we aim to captu
re its core semantic content through concepts connected by manifold types of semantic relations. Methods typically leverage large silver training data to learn a single model that is able to project non-English sentences to AMRs. However, we find that a simple baseline tends to be overlooked: translating the sentences to English and projecting their AMR with a monolingual AMR parser (translate+parse,T+P). In this paper, we revisit this simple two-step base-line, and enhance it with a strong NMT system and a strong AMR parser. Our experiments show that T+P outperforms a recent state-of-the-art system across all tested languages: German, Italian, Spanish and Mandarin with +14.6, +12.6, +14.3 and +16.0 Smatch points
Abstract Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependenc
y edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
