Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExplicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle
بناء جملة النمذجة بشكل صريح في نماذج اللغة مع تحليل تدريجي و Oracle الديناميكي
308
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
بناء الجملة أساسي في تفكيرنا حول اللغة.الفشل في التقاط هيكل لغة الإدخال قد يؤدي إلى مشاكل تعميم وتعامل معهم.في العمل الحالي، نقترح نموذجا جديدا للغة في مجال بناء الجملة: ذاكرة ترتيب سنوية (SOM).نماذج النموذج صراحة الهيكل مع محلل تدريجي وتحافظ على إعداد الاحتمالات الشرطي لطراز اللغة القياسية (من اليسار إلى اليمين).لتدريب المحلل التدريجي وتجنب تحيز التعرض، نقترح أيضا أوراكل ديناميكية جديدة، بحيث يكون SOM أكثر قوة لقرارات تحليل خاطئة.تظهر التجارب أن SOM يمكن أن يحقق نتائج قوية في نمذجة اللغة، والتحليل الإضافي، واختبارات التعميم النحوي أثناء استخدام معلمات أقل من النماذج الأخرى.
Syntax is fundamental to our thinking about language. Failing to capture the structure of input language could lead to generalization problems and over-parametrization. In the present work, we propose a new syntax-aware language model: Syntactic Ordered Memory (SOM). The model explicitly models the structure with an incremental parser and maintains the conditional probability setting of a standard language model (left-to-right). To train the incremental parser and avoid exposure bias, we also propose a novel dynamic oracle, so that SOM is more robust to wrong parsing decisions. Experiments show that SOM can achieve strong results in language modeling, incremental parsing, and syntactic generalization tests while using fewer parameters than other models.
References used
https://aclanthology.org/
rate research
Read More
Coarse-grained linguistic information, such as named entities or phrases, facilitates adequately representation learning in pre-training. Previous works mainly focus on extending the objective of BERT's Masked Language Modeling (MLM) from masking ind
ividual tokens to contiguous sequences of n tokens. We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information. As an alternative, we propose ERNIE-Gram, an explicitly n-gram masking method to enhance the integration of coarse-grained information into pre-training. In ERNIE-Gram, n-grams are masked and predicted directly using explicit n-gram identities rather than contiguous sequences of n tokens. Furthermore, ERNIE-Gram employs a generator model to sample plausible n-gram identities as optional n-gram masks and predict them in both coarse-grained and fine-grained manners to enable comprehensive n-gram prediction and relation modeling. We pre-train ERNIE-Gram on English and Chinese text corpora and fine-tune on 19 downstream tasks. Experimental results show that ERNIE-Gram outperforms previous pre-training models like XLNet and RoBERTa by a large margin, and achieves comparable results with state-of-the-art methods. The source codes and pre-trained models have been released at https://github.com/PaddlePaddle/ERNIE.
Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pre-trained models contain entangled semantic and syntactic information, and therefore cannot be directly used to derive use
ful semantic sentence embeddings for some tasks. Paraphrase pairs offer an effective way of learning the distinction between semantics and syntax, as they naturally share semantics and often vary in syntax. In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings obtained by pre-trained language models. ParaBART is trained to perform syntax-guided paraphrasing, based on a source sentence that shares semantics with the target paraphrase, and a parse tree that specifies the target syntax. In this way, ParaBART learns disentangled semantic and syntactic representations from their respective inputs with separate encoders. Experiments in English show that ParaBART outperforms state-of-the-art sentence embedding models on unsupervised semantic similarity tasks. Additionally, we show that our approach can effectively remove syntactic information from semantic sentence embeddings, leading to better robustness against syntactic variation on downstream semantic tasks.
Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passag
es of text (e.g., 1000 tokens), especially when the models are fine-tuned to the target domain on a small corpus. Previous planning-then-generation methods also fall short of producing such long text in various domains. To overcome the limitations, we propose a simple but effective method of generating text in a progressive manner, inspired by generating images from low to high resolution. Our method first produces domain-specific content keywords and then progressively refines them into complete passages in multiple stages. The simple design allows our approach to take advantage of pretrained LMs at each stage and effectively adapt to any target domain given only a small set of examples. We conduct a comprehensive empirical study with a broad set of evaluation metrics, and show that our approach significantly improves upon the fine-tuned large LMs and various planning-then-generation methods in terms of quality and sample efficiency. Human evaluation also validates that our model generations are more coherent.
This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks
that have always been beneficial from informative syntactic clues since a long time ago, though the advance from end-to-end deep learning models shows new results. In this tutorial, we will first introduce the background and the latest progress of syntactic parsing and SRL/NMT. Then, we will summarize the key evidence about the syntactic impacts over these two concerning tasks, and explore the behind reasons from both computational and linguistic backgrounds.
Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to syntax make t
hem appealing as distant information sources to incorporate into unsupervised constituency parsing. But they are noisy and incomplete; to address this challenge, we develop a partial-brackets-aware structured ramp loss in learning. Experiments demonstrate that our distantly-supervised models trained on naturally-occurring bracketing data are more accurate in inducing syntactic structures than competing unsupervised systems. On the English WSJ corpus, our models achieve an unlabeled F1 score of 68.9 for constituency parsing.
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
