Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect Extraction
Dilbert: تخصيص ما قبل التدريب لتكييف المجال مع تحول الفئة، مع تطبيق لاستخراج الجانب
287
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أسفرت صعود النماذج اللغوية المدربة مسبقا تقدما كبيرا في الغالبية العظمى من مهام معالجة اللغة الطبيعية (NLP). ومع ذلك، يمكن أن يكون النهج العام باتجاه الإجراء المسبق للتدريب بطبيعة الحال في بعض الحالات. بشكل خاص، قم بضبط نموذج لغة مدرب مسبقا في مجال المصدر ثم تطبيقه على نطاق مستهدف مختلف، يؤدي إلى انخفاض أداء حاد من المصنف النهائي للعديد من أزواج المجال المستهدف المصدر. علاوة على ذلك، في بعض مهام NLP، تختلف فئات الإخراج بشكل كبير بين المجالات، مما يجعل التكيف أكثر تحديا. هذا، على سبيل المثال، يحدث في مهمة استخراج الجانب، حيث قد تكون جوانب اهتمام الاستعراضات، على سبيل المثال، المطاعم أو الأجهزة الإلكترونية مختلفة للغاية. تقدم هذه الورقة مخططا جديدا للضبط في بيرت، والتي تهدف إلى معالجة التحديات المذكورة أعلاه. نحن نسمي هذا المخطط Dilbert: تعلم المجال الثابتة مع Bert، وتخصيصه لاستخراج الجانب في إعداد تكيف المجال غير المقترح. يسخر Dilbert المعلومات الفئوية لكل من المصدر والمجالات المستهدفة لتوجيه عملية التدريب المسبق نحو تمثيل ثنائي النطاق والفئة، مما يغلق الفجوة بين المجالات. نظهر أن Dilbert يعطي تحسينات كبيرة على خطوط الأساس الحديثة أثناء استخدام جزء صغير من البيانات غير المسبقة، لا سيما في إعدادات تكيف مجال أكثر تحديا.
The rise of pre-trained language models has yielded substantial progress in the vast majority of Natural Language Processing (NLP) tasks. However, a generic approach towards the pre-training procedure can naturally be sub-optimal in some cases. Particularly, fine-tuning a pre-trained language model on a source domain and then applying it to a different target domain, results in a sharp performance decline of the eventual classifier for many source-target domain pairs. Moreover, in some NLP tasks, the output categories substantially differ between domains, making adaptation even more challenging. This, for example, happens in the task of aspect extraction, where the aspects of interest of reviews of, e.g., restaurants or electronic devices may be very different. This paper presents a new fine-tuning scheme for BERT, which aims to address the above challenges. We name this scheme DILBERT: Domain Invariant Learning with BERT, and customize it for aspect extraction in the unsupervised domain adaptation setting. DILBERT harnesses the categorical information of both the source and the target domains to guide the pre-training process towards a more domain and category invariant representation, thus closing the gap between the domains. We show that DILBERT yields substantial improvements over state-of-the-art baselines while using a fraction of the unlabeled data, particularly in more challenging domain adaptation setups.
References used
https://aclanthology.org/
rate research
Read More
Recent researches show that pre-trained models (PTMs) are beneficial to Chinese Word Segmentation (CWS). However, PTMs used in previous works usually adopt language modeling as pre-training tasks, lacking task-specific prior segmentation knowledge an
d ignoring the discrepancy between pre-training tasks and downstream CWS tasks. In this paper, we propose a CWS-specific pre-trained model MetaSeg, which employs a unified architecture and incorporates meta learning algorithm into a multi-criteria pre-training task. Empirical results show that MetaSeg could utilize common prior segmentation knowledge from different existing criteria and alleviate the discrepancy between pre-trained models and downstream CWS tasks. Besides, MetaSeg can achieve new state-of-the-art performance on twelve widely-used CWS datasets and significantly improve model performance in low-resource settings.
Recent work has demonstrated that pre-training in-domain language models can boost performance when adapting to a new domain. However, the costs associated with pre-training raise an important question: given a fixed budget, what steps should an NLP
practitioner take to maximize performance? In this paper, we study domain adaptation under budget constraints, and approach it as a customer choice problem between data annotation and pre-training. Specifically, we measure the annotation cost of three procedural text datasets and the pre-training cost of three in-domain language models. Then we evaluate the utility of different combinations of pre-training and data annotation under varying budget constraints to assess which combination strategy works best. We find that, for small budgets, spending all funds on annotation leads to the best performance; once the budget becomes large enough, a combination of data annotation and in-domain pre-training works more optimally. We therefore suggest that task-specific data annotation should be part of an economical strategy when adapting an NLP model to a new domain.
Aspect term extraction aims to extract aspect terms from a review sentence that users have expressed opinions on. One of the remaining challenges for aspect term extraction resides in the lack of sufficient annotated data. While self-training is pote
ntially an effective method to address this issue, the pseudo-labels it yields on unlabeled data could induce noise. In this paper, we use two means to alleviate the noise in the pseudo-labels. One is that inspired by the curriculum learning, we refine the conventional self-training to progressive self-training. Specifically, the base model infers pseudo-labels on a progressive subset at each iteration, where samples in the subset become harder and more numerous as the iteration proceeds. The other is that we use a discriminator to filter the noisy pseudo-labels. Experimental results on four SemEval datasets show that our model significantly outperforms the previous baselines and achieves state-of-the-art performance.
In this paper, we investigate the Aspect Category Sentiment Analysis (ACSA) task from a novel perspective by exploring a Beta Distribution guided aspect-aware graph construction based on external knowledge. That is, we are no longer entangled about h
ow to laboriously search the sentiment clues for coarse-grained aspects from the context, but how to preferably find the words highly related to the aspects in the context and determine their importance based on the public knowledge base. In this way, the contextual sentiment clues can be explicitly tracked in ACSA for the aspects in the light of these aspect-related words. To be specific, we first regard each aspect as a pivot to derive aspect-aware words that are highly related to the aspect from external affective commonsense knowledge. Then, we employ Beta Distribution to educe the aspect-aware weight, which reflects the importance to the aspect, for each aspect-aware word. Afterward, the aspect-aware words are served as the substitutes of the coarse-grained aspect to construct graphs for leveraging the aspect-related contextual sentiment dependencies in ACSA. Experiments on 6 benchmark datasets show that our approach significantly outperforms the state-of-the-art baseline methods.
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.
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
