Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSwitch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching
التبديل نقطة منحازة التدريب الذاتي: إعادة صياغة نماذج مسبقا لتبديل التعليمات البرمجية
150
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لا يزال التبديل (CS)، ظاهرة في كل مكان بسبب سهولة الاتصالات التي تقدمها في المجتمعات متعددة اللغات لا تزال مشكلة متفائلة في معالجة اللغة. الأسباب الرئيسية وراء ذلك هي: (1) الحد الأدنى من الجهود في الاستفادة من نماذج متعددة اللغات متعددة اللغات الكبيرة، و (2) عدم وجود بيانات مشروح. حالة التمييز بين الأداء المنخفض للنماذج متعددة اللغات في CS هي خلط اللغات داخل الجملة التي تؤدي إلى تبديل النقاط. نقوم أولا بقياس مهام وضع العلامات على التسلسل - POS و NER على 4 أزواج لغة مختلفة مع مجموعة من النماذج المحددة مسبقا لتحديد المشكلات وتحديد أفضل نموذج أداء شار Bert فيما بينها (معالجة (1)). ثم نقترح طريقة تدريب ذاتية لإعادة توجيه النماذج المحددة مسبقا باستخدام تحيز نقطة التبديل عن طريق الاستفادة من البيانات غير الموحدة (معالجة (2)). نوضح أخيرا أن نهجنا ينفذ جيدا على كلا المهام عن طريق تقليل الفجوة بين أداء نقطة التبديل مع الاحتفاظ بالأداء العام على أزواج لغتين متميزة في كلتا المهامتين. نحن نخطط لإطلاق سراح نماذجنا والرمز لجميع تجاربنا.
Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks -- POS and NER on 4 different language pairs with a suite of pretrained models to identify the problems and select the best performing char-BERT model among them (addressing (1)). We then propose a self training method to repurpose the existing pretrained models using a switch-point bias by leveraging unannotated data (addressing (2)). We finally demonstrate that our approach performs well on both tasks by reducing the gap between the switch point performance while retaining the overall performance on two distinct language pairs in both the tasks. We plan to release our models and the code for all our experiments.
References used
https://aclanthology.org/
rate research
Read More
Language models used in speech recognition are often either evaluated intrinsically using perplexity on test data, or extrinsically with an automatic speech recognition (ASR) system. The former evaluation does not always correlate well with ASR perfo
rmance, while the latter could be specific to particular ASR systems. Recent work proposed to evaluate language models by using them to classify ground truth sentences among alternative phonetically similar sentences generated by a fine state transducer. Underlying such an evaluation is the assumption that the generated sentences are linguistically incorrect. In this paper, we first put this assumption into question, and observe that alternatively generated sentences could often be linguistically correct when they differ from the ground truth by only one edit. Secondly, we showed that by using multi-lingual BERT, we can achieve better performance than previous work on two code-switching data sets. Our implementation is publicly available on Github at https://github.com/sikfeng/language-modelling-for-code-switching.
Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of labeled d
ata that is costly to collect. To address this drawback, we adopt a transfer learning approach and propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking (DB). To enforce a surface form dissimilar from the input, whenever the language model emits a token contained in the source sequence, DB prevents the model from outputting the subsequent source token for the next generation step. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair (QQP) and the ParaNMT datasets and is robust to domain shift between the two datasets of distinct distributions. We also demonstrate that our model transfers to paraphrasing in other languages without any additional finetuning.
Fine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the fine-tuning stage. We study the problem of fine-tuning pre-trained LMs u
sing only weak supervision, without any labeled data. This problem is challenging because the high capacity of LMs makes them prone to overfitting the noisy labels generated by weak supervision. To address this problem, we develop a contrastive self-training framework, COSINE, to enable fine-tuning LMs with weak supervision. Underpinned by contrastive regularization and confidence-based reweighting, our framework gradually improves model fitting while effectively suppressing error propagation. Experiments on sequence, token, and sentence pair classification tasks show that our model outperforms the strongest baseline by large margins and achieves competitive performance with fully-supervised fine-tuning methods. Our implementation is available on https://github.com/yueyu1030/COSINE.
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words i
n pre-training could further improve the performance of PrLMs. However, given that span-level clues are introduced and fixed in pre-training, previous methods are time-consuming and lack of flexibility. To alleviate the inconvenience, this paper presents a novel span fine-tuning method for PrLMs, which facilitates the span setting to be adaptively determined by specific downstream tasks during the fine-tuning phase. In detail, any sentences processed by the PrLM will be segmented into multiple spans according to a pre-sampled dictionary. Then the segmentation information will be sent through a hierarchical CNN module together with the representation outputs of the PrLM and ultimately generate a span-enhanced representation. Experiments on GLUE benchmark show that the proposed span fine-tuning method significantly enhances the PrLM, and at the same time, offer more flexibility in an efficient way.
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.
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
