Thailand

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications. One line of model compression approaches considers knowledge distillation to distill large teacher models into small student models. Most of these studies focus on single-domain only, which ignores the transferable knowledge from other domains. We notice that training a teacher with transferable knowledge digested across domains can achieve better generalization capability to help knowledge distillation. Hence we propose a Meta-Knowledge Distillation (Meta-KD) framework to build a meta-teacher model that captures transferable knowledge across domains and passes such knowledge to students. Specifically, we explicitly force the meta-teacher to capture transferable knowledge at both instance-level and feature-level from multiple domains, and then propose a meta-distillation algorithm to learn single-domain student models with guidance from the meta-teacher. Experiments on public multi-domain NLP tasks show the effectiveness and superiority of the proposed Meta-KD framework. Further, we also demonstrate the capability of Meta-KD in the settings where the training data is scarce.

ACL-IJCNLP 2021

Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains

pre-trained language models

meta-learning

knowledge distillation

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

technical paper

Natural language processing (NLP) often faces the problem of data diversity such as different domains, themes, styles, and so on. Therefore, a single language model (LM) is insufficient to learn all knowledge from diverse samples. To solve this problem, we firstly propose an autoencoding topic model with a mixture prior (mATM) to perform clustering for the data, where the clusters defined in semantic space describes the data diversity. Having obtained the clustering assignment for each sample, we develop the ensemble LM (EnsLM) with the technique of weight modulation. Specifically, EnsLM contains a backbone that is adjusted by a few modulated weights to fit for different sample clusters. 
As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features. EnsLM can be trained jointly with mATM with a flexible LM backbone. We evaluate the effectiveness of both mATM and EnsLM on various tasks.

EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering

Pre-trained language models like BERT are performant in a wide range of natural language tasks. However, they are resource exhaustive and computationally expensive for industrial scenarios. Thus, early exits are adopted at each layer of BERT to perform adaptive computation by predicting easier samples with the first few layers to speed up the inference. In this work, to improve efficiency without performance drop, we propose a novel training scheme called Learned Early Exit for BERT (LeeBERT). First, we ask each exit to learn from each other, rather than learning only from the last layer. Second, the weights of different loss terms are learned, thus balancing off different objectives. We formulate the optimization of LeeBERT as a bi-level optimization problem, and we propose a novel cross-level optimization (CLO) algorithm to improve the optimization results. Experiments on the GLUE benchmark show that our proposed methods improve the performance of the state-of-the-art (SOTA) early exit methods for pre-trained models.

LeeBERT: Learned Early Exit for BERT with cross-level optimization

Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors. To this end, PLOME masks the chosen tokens with similar characters according to a confusion set rather than the fixed token ``[MASK]" as in BERT. Besides character prediction, PLOME also introduces pronunciation prediction to learn the misspelled knowledge on phonic level. Moreover, phonological and visual similarity knowledge is important to this task. PLOME utilizes GRU networks to model such knowledge based on characters' phonics and strokes. Experiments are conducted on widely used benchmarks. Our method achieves superior performance against state-of-the-art approaches by a remarkable margin. We release the source code and pre-trained model for further use by the community (https://github.com/liushulinle/PLOME).

PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction

Medical report generation task, which targets to produce long and coherent descriptions of medical images, has attracted growing research interests recently. Different from the general image captioning tasks, medical report generation is more challenging for data-driven neural models. This is mainly due to 1) the serious data bias and 2) the limited medical data. To alleviate the data bias and make best use of available data, we propose a Competence-based Multimodal Curriculum Learning framework (CMCL). Specifically, CMCL simulates the learning process of radiologists and optimizes the model in a step by step manner. Firstly, CMCL estimates the difficulty of each training instance and evaluates the competence of current model; Secondly, CMCL selects the most suitable batch of training instances considering current model competence. By iterating above two steps, CMCL can gradually improve the model's performance. The experiments on the public IU-Xray and MIMIC-CXR datasets show that CMCL can be incorporated into existing models to improve their performance.

Competence-based Multimodal Curriculum Learning for Medical Report Generation

Traditional toxicity detection models have focused on the single utterance level without deeper understanding of context. We introduce CONDA, a new dataset for in-game toxic language detection enabling joint intent classification and slot filling analysis, which is the core task of Natural Language Understanding (NLU). The dataset consists of 45K utterances from 12K conversations from the chat logs of 1.9K completed Dota 2 matches. We propose a robust dual semantic-level toxicity framework, which handles utterance and token-level patterns, and rich contextual chatting history. Accompanying the dataset is a thorough in-game toxicity analysis, which provides comprehensive understanding of context at utterance, token, and dual levels. Inspired by NLU, we also apply its metrics to the toxicity detection tasks for assessing toxicity and game-specific aspects. We evaluate strong NLU models on CONDA, providing fine-grained results for different intent classes and slot classes. Furthermore, we examine the coverage of toxicity nature in our dataset by comparing it with other toxicity datasets.

CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection

Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types. In real-world applications, ED typically does not have sufficient labeled data, thus can be formulated as a few-shot learning problem. To tackle the issue of low sample diversity in few-shot ED, we propose a novel knowledge-based few-shot event detection method which uses a definition-based encoder to introduce external event knowledge as the knowledge prior of event types. Furthermore, as external knowledge typically provides limited and imperfect coverage of event types, we introduce an adaptive knowledge-enhanced Bayesian meta-learning method to dynamically adjust the knowledge prior of event types. Experiments show our method consistently and substantially outperforms a number of baselines by at least 15 absolute $F_1$ points under the same few-shot settings.

Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection

Current storytelling systems focus on generating stories with coherent plots regardless of the narration style, which is important for controllable text generation. Therefore, we propose a new task, stylized story generation, namely generating stories with specified style given a leading context. To tackle the problem, we propose a novel generation model that first plans the stylized keywords and then generates the whole story with the guidance of the keywords. Besides, we propose two automatic metrics to evaluate the consistency between the generated story and the specified style. Experiments demonstrate that our model can controllably generate emotion-driven or event-driven stories based on the ROCStories dataset. Our study presents insights for stylized story generation in further research.

Stylized Story Generation with Style-Guided Planning

Chinese spelling check (CSC) is a task to detect and correct spelling errors in Chinese text. Most state-of-the-art works on the CSC task adopt a BERT-based non-autoregressive language model, which relies on the output independence assumption. The inappropriate independence assumption prevents BERT-based models from learning the dependencies among target tokens, resulting in an incoherent problem. To address the above issue, we propose a novel architecture named Dynamic Connected Networks (DCN), which generates the candidate Chinese characters via a Pinyin Enhanced Candidate Generator and then utilizes an attention-based network to model the dependencies between two adjacent Chinese characters. The experimental results show that our proposed method achieves a new state-of-the-art performance on three human-annotated datasets.

Dynamic Connected Networks for Chinese Spelling Check

End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in many scenarios but has not been fully investigated. 
In this work, we propose RealTranS, an end-to-end model for SST. To bridge the modality gap between speech and text, RealTranS gradually downsamples the input speech with interleaved convolution and unidirectional Transformer layers for acoustic modeling, and then maps speech features into text space with a weighted-shrinking operation and a semantic encoder. Besides, to improve the model performance in simultaneous scenarios, we propose a blank penalty to enhance the shrinking quality and a Wait-K-Stride-N strategy to allow local reranking during decoding.
Experiments on public and widely-used datasets show that RealTranS with the Wait-K-Stride-N strategy outperforms prior end-to-end models as well as cascaded models in diverse latency settings.

RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer

Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods typically demand massive computation resources. To accelerate pre-training, ELECTRA trains a discriminator that predicts whether each input token is replaced by a generator. However, this new task, as a binary classification, is less semantically informative. In this study, we present a new text encoder pre-training method that improves ELECTRA based on multi-task learning. Specifically, we train the discriminator to simultaneously detect replaced tokens and select original tokens from candidate sets. We further develop two techniques to effectively combine all pre-training tasks: (1) using attention-based networks for task-specific heads, and (2) sharing bottom layers of the generator and the discriminator. Extensive experiments on GLUE and SQuAD datasets demonstrate both the effectiveness and the efficiency of our proposed method.

Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains

Downloads

Next from ACL-IJCNLP 2021

EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering

Similar lecture

Weight Distillation: Transferring the Knowledge in Neural Network Parameters

Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL-IJCNLP 2021

EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering

Similar lecture

Weight Distillation: Transferring the Knowledge in Neural Network Parameters

Downloads