Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userThe Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders
فرضية الخلايا الجذعية: معضلة وراء التعلم متعدد المهام مع تشفير المحولات
238
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
برزت التعلم المتعدد المهام مع ترميز المحولات (MTL) كتقنية قوية لتحسين الأداء على المهام ذات الصلة عن كثب لكل من الدقة والكفاءة في حين أن السؤال لا يزال يبقى ما إذا كان من شأنه أن يؤدي ذلك على المهام المميزة أم لا بشكل جيد في الطبيعة أم لا. نقوم أولا بإجراء نتائج MTL على خمس مهام NLP، POS، NER، DEP، CON، SRL، وتصوير نقصها على تعلم المهمة الفردية. ثم نقوم بإجراء تحليل جذري واسع النطاق لإظهار أن مجموعة معينة من رؤساء الاهتمام تعلن أن معظم المهام خلال MTL، والذين يتداخلون مع بعضهم البعض لضبط تلك الرؤوس لأهدافهم الخاصة. استنادا إلى هذا النتيجة، نقترح فرضية الخلايا الجذعية للكشف عن وجود اهتمام يرأس الموهوبين بشكل طبيعي للعديد من المهام التي لا يمكن تدريبها بشكل مشترك على إنشاء شرائح كافية لجميع تلك المهام. أخيرا، نقوم بتصميم تحقيقات خالية من المعلمات الجديدة لتبرير فرضيتنا وإظهار كيفية تحويل رؤساء الانتباه عبر المهام الخمسة خلال MTL من خلال تحليل الملصقات.
Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks that are distinct in nature. We first present MTL results on five NLP tasks, POS, NER, DEP, CON, and SRL, and depict its deficiency over single-task learning. We then conduct an extensive pruning analysis to show that a certain set of attention heads get claimed by most tasks during MTL, who interfere with one another to fine-tune those heads for their own objectives. Based on this finding, we propose the Stem Cell Hypothesis to reveal the existence of attention heads naturally talented for many tasks that cannot be jointly trained to create adequate embeddings for all of those tasks. Finally, we design novel parameter-free probes to justify our hypothesis and demonstrate how attention heads are transformed across the five tasks during MTL through label analysis.
References used
https://aclanthology.org/
rate research
Read More
We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using self-supervision, CoTexT is pre-trained on large programming language
corpora to learn a general understanding of language and code. CoTexT supports downstream NL-PL tasks such as code summarizing/documentation, code generation, defect detection, and code debugging. We train CoTexT on different combinations of available PL corpus including both bimodal'' and unimodal'' data. Here, bimodal data is the combination of text and corresponding code snippets, whereas unimodal data is merely code snippets. We first evaluate CoTexT with multi-task learning: we perform Code Summarization on 6 different programming languages and Code Refinement on both small and medium size featured in the CodeXGLUE dataset. We further conduct extensive experiments to investigate CoTexT on other tasks within the CodeXGlue dataset, including Code Generation and Defect Detection. We consistently achieve SOTA results in these tasks, demonstrating the versatility of our models.
Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine Translation (AT) k
nowledge to NAT models, e.g., with knowledge distillation. In this work, we hypothesize and empirically verify that AT and NAT encoders capture different linguistic properties of source sentences. Therefore, we propose to adopt multi-task learning to transfer the AT knowledge to NAT models through encoder sharing. Specifically, we take the AT model as an auxiliary task to enhance NAT model performance. Experimental results on WMT14 En-De and WMT16 En-Ro datasets show that the proposed Multi-Task NAT achieves significant improvements over the baseline NAT models. Furthermore, the performance on large-scale WMT19 and WMT20 En-De datasets confirm the consistency of our proposed method. In addition, experimental results demonstrate that our Multi-Task NAT is complementary to knowledge distillation, the standard knowledge transfer method for NAT.
Large-scale multi-modal classification aim to distinguish between different multi-modal data, and it has drawn dramatically attentions since last decade. In this paper, we propose a multi-task learning-based framework for the multimodal classificatio
n task, which consists of two branches: multi-modal autoencoder branch and attention-based multi-modal modeling branch. Multi-modal autoencoder can receive multi-modal features and obtain the interactive information which called multi-modal encoder feature, and use this feature to reconstitute all the input data. Besides, multi-modal encoder feature can be used to enrich the raw dataset, and improve the performance of downstream tasks (such as classification task). As for attention-based multimodal modeling branch, we first employ attention mechanism to make the model focused on important features, then we use the multi-modal encoder feature to enrich the input information, achieve a better performance. We conduct extensive experiments on different dataset, the results demonstrate the effectiveness of proposed framework.
This paper presents our contribution to the Social Media Mining for Health Applications Shared Task 2021. We addressed all the three subtasks of Task 1: Subtask A (classification of tweets containing adverse effects), Subtask B (extraction of text sp
ans containing adverse effects) and Subtask C (adverse effects resolution). We explored various pre-trained transformer-based language models and we focused on a multi-task training architecture. For the first subtask, we also applied adversarial augmentation techniques and we formed model ensembles in order to improve the robustness of the prediction. Our system ranked first at Subtask B with 0.51 F1 score, 0.514 precision and 0.514 recall. For Subtask A we obtained 0.44 F1 score, 0.49 precision and 0.39 recall and for Subtask C we obtained 0.16 F1 score with 0.16 precision and 0.17 recall.
We propose a neural event coreference model in which event coreference is jointly trained with five tasks: trigger detection, entity coreference, anaphoricity determination, realis detection, and argument extraction. To guide the learning of this com
plex model, we incorporate cross-task consistency constraints into the learning process as soft constraints via designing penalty functions. In addition, we propose the novel idea of viewing entity coreference and event coreference as a single coreference task, which we believe is a step towards a unified model of coreference resolution. The resulting model achieves state-of-the-art results on the KBP 2017 event coreference dataset.
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
