Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn the Influence of Masking Policies in Intermediate Pre-training
على تأثير سياسات إخفاء في التدريب المسبق المتوسط
251
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتم تدريب نماذج NLP الحالية في الغالب من خلال خط أنابيب ما قبل المرحلة من مرحلتين. لقد أظهر العمل المسبق أن إدراج مرحلة ما قبل التدريب الوسيط، باستخدام سياسات إخفاء الإرشادية لنمذجة لغة ملثم (MLM)، يمكن أن تحسن بشكل كبير الأداء النهائي. ومع ذلك، لا يزال غير واضح (1) في أي حالات مثل هذا التدريب المسبق الوسيط مفيد، (2) سواء كانت الأهداف المهمة المصنوعة يدويا هي مهمة معينة، و (3) ما إذا كانت سياسة إخفاء مصممة لمهمة واحدة تعزيم خارج تلك المهمة. في هذه الورقة، نقوم بإجراء دراسة تجريبية واسعة النطاق للتحقيق في تأثير سياسات اخفاء مختلفة في التدريب المسبق المتوسط مع تسع مهام مختارة عبر ثلاث فئات. من الأهمية، نقدم طرق لأتمتة اكتشاف سياسات إخفاء الأمثل عبر الإشراف المباشر أو التعلم التلوي. نستنتج أن نجاح التدريب المسبق الوسيط يعتمد على Corpus ما قبل القطارات المناسبة، واختيار تنسيق الإخراج (أي، يمثل الموافق أو الجملة الكاملة)، وفهم واضح للدور الذي يلعبه الامتيازات والرهون البحرية لمهمة المصب. بالإضافة إلى ذلك، نجد أن سياسات الاخفاء المتعلميتنا تتفوق على مزعجة إخفاء الكيانات المسماة على Triviaqa، والسياسات المستفادة من مهمة يمكن أن تنتقل بشكل إيجابي إلى مهام أخرى في بعض الحالات، مما يدعو إلى البحث في المستقبل في هذا الاتجاه.
Current NLP models are predominantly trained through a two-stage pre-train then fine-tune'' pipeline. Prior work has shown that inserting an intermediate pre-training stage, using heuristic masking policies for masked language modeling (MLM), can significantly improve final performance. However, it is still unclear (1) in what cases such intermediate pre-training is helpful, (2) whether hand-crafted heuristic objectives are optimal for a given task, and (3) whether a masking policy designed for one task is generalizable beyond that task. In this paper, we perform a large-scale empirical study to investigate the effect of various masking policies in intermediate pre-training with nine selected tasks across three categories. Crucially, we introduce methods to automate the discovery of optimal masking policies via direct supervision or meta-learning. We conclude that the success of intermediate pre-training is dependent on appropriate pre-train corpus, selection of output format (i.e., masked spans or full sentence), and clear understanding of the role that MLM plays for the downstream task. In addition, we find our learned masking policies outperform the heuristic of masking named entities on TriviaQA, and policies learned from one task can positively transfer to other tasks in certain cases, inviting future research in this direction.
References used
https://aclanthology.org/
rate research
Read More
We present the TAPAS contribution to the Shared Task on Statement Verification and Evidence Finding with Tables (SemEval 2021 Task 9, Wang et al. (2021)). SEM TAB FACT Task A is a classification task of recognizing if a statement is entailed, neutral
or refuted by the content of a given table. We adopt the binary TAPAS model of Eisenschlos et al. (2020) to this task. We learn two binary classification models: A first model to predict if a statement is neutral or non-neutral and a second one to predict if it is entailed or refuted. As the shared task training set contains only entailed or refuted examples, we generate artificial neutral examples to train the first model. Both models are pre-trained using a MASKLM objective, intermediate counter-factual and synthetic data (Eisenschlos et al., 2020) and TABFACT (Chen et al., 2020), a large table entailment dataset. We find that the artificial neutral examples are somewhat effective at training the first model, achieving 68.03 test F1 versus the 60.47 of a majority baseline. For the second stage, we find that the pre-training on the intermediate data and TABFACT improves the results over MASKLM pre-training (68.03 vs 57.01).
This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and effic
ient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model -- IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT.
Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a range of downstream tasks. In this paper we explore whether it is possible to learn disentangl
ed representations by identifying existing subnetworks within pretrained models that encode distinct, complementary aspects. Concretely, we learn binary masks over transformer weights or hidden units to uncover subsets of features that correlate with a specific factor of variation; this eliminates the need to train a disentangled model from scratch for a particular task. We evaluate this method with respect to its ability to disentangle representations of sentiment from genre in movie reviews, toxicity from dialect in Tweets, and syntax from semantics. By combining masking with magnitude pruning we find that we can identify sparse subnetworks within BERT that strongly encode particular aspects (e.g., semantics) while only weakly encoding others (e.g., syntax). Moreover, despite only learning masks, disentanglement-via-masking performs as well as --- and often better than ---previously proposed methods based on variational autoencoders and adversarial training.
Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low-resource ones. However, due to significant typological differences and
contradictions between some languages, such models usually perform poorly on many languages and cross-lingual settings, which shows the difficulty of learning a single model to handle massive diverse languages well at the same time. To alleviate this issue, we present a new multilingual pre-training pipeline. We propose to generate language representation from multilingual pre-trained model and conduct linguistic analysis to show that language representation similarity reflects linguistic similarity from multiple perspectives, including language family, geographical sprachbund, lexicostatistics, and syntax. Then we cluster all the target languages into multiple groups and name each group as a representation sprachbund. Thus, languages in the same representation sprachbund are supposed to boost each other in both pre-training and fine-tuning as they share rich linguistic similarity. We pre-train one multilingual model for each representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
Pre-training (PT) and back-translation (BT) are two simple and powerful methods to utilize monolingual data for improving the model performance of neural machine translation (NMT). This paper takes the first step to investigate the complementarity be
tween PT and BT. We introduce two probing tasks for PT and BT respectively and find that PT mainly contributes to the encoder module while BT brings more benefits to the decoder. Experimental results show that PT and BT are nicely complementary to each other, establishing state-of-the-art performances on the WMT16 English-Romanian and English-Russian benchmarks. Through extensive analyses on sentence originality and word frequency, we also demonstrate that combining Tagged BT with PT is more helpful to their complementarity, leading to better translation quality. Source code is freely available at https://github.com/SunbowLiu/PTvsBT.
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
