Dominican Republic

Intermediate layer matching is shown as an effective approach for improving knowledge distillation (KD). However, this technique applies matching in the hidden spaces of two different networks (i.e. student and teacher), which lacks clear interpretability. Moreover, intermediate layer KD cannot easily deal with other problems such as layer mapping search and architecture mismatch (i.e. it requires the teacher and student to be of the same model type). To tackle the aforementioned problems all together, we propose Universal-KD to match intermediate layers of the teacher and the student in the output space (by adding pseudo classifiers on intermediate layers) via the attention-based layer projection. By doing this, our unified approach has three merits: (i) it can be flexibly combined with current intermediate layer distillation techniques to improve their results (ii) the pseudo classifiers of the teacher can be deployed instead of extra expensive teacher assistant networks to address the capacity gap problem in KD which is a common issue when the gap between the size of the teacher and student networks becomes too large; (iii) it can be used in cross-architecture intermediate layer KD. We did comprehensive experiments in distilling BERT-base into BERT-4, RoBERTa-large into DistilRoBERTa and BERT-base into CNN and LSTM-based models. Results on the GLUE tasks show that our approach is able to outperform other KD techniques.

EMNLP 2021

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

poster

Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models. However, there is little attempt to combine these two types of models, which inituitively possess complementary advantages. In this paper, we propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering.

Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings

Multimodal Transformers achieve superior performance in multimodal learning tasks. However, the quadratic complexity of the self-attention mechanism in Transformers limits their deployment in low-resource devices and makes their inference and training computationally expensive. We propose multimodal Sparse Phased Transformer (SPT) to alleviate the problem of self-attention complexity and memory footprint. SPT uses a sampling function to generate a sparse attention matrix and compress a long sequence to a shorter sequence of hidden states. SPT concurrently captures interactions between the hidden states of different modalities at every layer. To further improve the efficiency of our method, we use Layer-wise parameter sharing and Factorized Co-Attention that share parameters between Cross Attention Blocks, with minimal impact on task performance. We evaluate our model with three sentiment analysis datasets and achieve comparable or superior performance compared with the existing methods, with a 90% reduction in the number of parameters. We conclude that (SPT) along with parameter sharing can capture multimodal interactions with reduced model size and improved sample efficiency.

Multimodal Phased Transformer for Sentiment Analysis

Implicit discourse relation recognition (IDRR) is a critical task in discourse analysis. Previous studies only regard it as a classification task and lack an in-depth understanding of the semantics of different relations. Therefore, we first view IDRR as a generation task and further propose a method joint modeling of the classification and generation. Specifically, we propose a joint model, CG-T5, to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. Furthermore, we design three target sentence forms, including the question form, for the generation model to incorporate prior knowledge. To address the issue that large discourse units are hardly embedded into the target sentence, we also propose a target sentence construction mechanism that automatically extracts core sentences from those large discourse units. Experimental results both on Chinese MCDTB and English PDTB datasets show that our model CG-T5 achieves the best performance against several state-of-the-art systems.

Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation

Discourse segmentation and sentence-level discourse parsing play important roles for various NLP tasks to consider textual coherence. Despite recent achievements in both tasks, there is still room for improvement due to the scarcity of labeled data. To solve the problem, we propose a language model-based generative classifier (LMGC) for using more information from labels by treating the labels as an input while enhancing label representations by embedding descriptions for each label. Moreover, since this enables LMGC to make ready the representations for labels, unseen in the pre-training step, we can effectively use a pretrained language model in LMGC. Experimental results on the RST-DT dataset show that our LMGC achieved the state-of-the-art F1 score of 96.72 in discourse segmentation. It further achieved the state-of-the-art relation F1 scores of 84.69 with gold EDU boundaries and 81.18 with automatically segmented boundaries, respectively, in sentence-level discourse parsing.

A Language Model-based Generative Classifier for Sentence-level Discourse Parsing

We present IndoBERTweet, the first large-scale pretrained model for Indonesian Twitter that is trained by extending a monolingually-trained Indonesian BERT model with additive domain-specific vocabulary. We focus in particular on efficient model adaptation under vocabulary mismatch, and benchmark different ways of initializing the BERT embedding layer for new word types. We find that initializing with the average BERT subword embedding makes pretraining five times faster, and is more effective than proposed methods for vocabulary adaptation in terms of extrinsic evaluation over seven Twitter-based datasets.

IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese network for this task, which obtains the sentence embeddings through modeling the context-response semantic relevance by applying a feed-forward network on top of the sentence encoders. However, as the semantic textual similarity is commonly measured through the element-wise distance metrics (e.g. cosine and L2 distance), such architecture yields a large gap between training and evaluating. In this paper, we propose DialogueCSE, a dialogue-based contrastive learning approach to tackle this issue. DialogueCSE first introduces a novel matching-guided embedding (MGE) mechanism, which generates a context-aware embedding for each candidate response embedding (i.e. the context-free embedding) according to the guidance of the multi-turn context-response matching matrices. Then it pairs each context-aware embedding with its corresponding context-free embedding and finally minimizes the contrastive loss across all pairs. We evaluate our model on three multi-turn dialogue datasets: the Microsoft Dialogue Corpus, the Jing Dong Dialogue Corpus, and the E-commerce Dialogue Corpus. Evaluation results show that our approach significantly outperforms the baselines across all three datasets in terms of MAP and Spearman's correlation measures, demonstrating its effectiveness. Further quantitative experiments show that our approach achieves better performance when leveraging more dialogue context and remains robust when less training data is provided.

DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected teacher model on the pre-defined training dataset. In this paper, we explore whether a dynamic knowledge distillation that empowers the student to adjust the learning procedure according to its competency, regarding the student performance and learning efficiency. We explore the dynamical adjustments on three aspects: teacher model adoption, data selection, and KD objective adaptation. Experimental results show that (1) proper selection of teacher model can boost the performance of student model; (2) conducting KD with 10% informative instances achieves comparable performance while greatly accelerates the training; (3) the student performance can be boosted by adjusting the supervision contribution of different alignment objective. We find dynamic knowledge distillation is promising and provide discussions on potential future directions towards more efficient KD methods.

Dynamic Knowledge Distillation for Pre-trained Language Models

A recent variation of Transformer, Performer, scales Transformer to longer sequences with a linear attention mechanism. However, it is not compatible with relative position encoding, which has advantages over absolute position encoding. In this paper, we discuss possible ways to add relative position encoding to Performer. Based on the analysis, we propose PermuteFormer, a Performer-based model with relative position encoding that scales linearly on long sequences. PermuteFormer applies position-dependent transformation on queries and keys to encode positional information into the attention module. This transformation is carefully crafted so that the final output of self-attention is not affected by absolute positions of tokens. PermuteFormer introduces negligible computational overhead by design that it runs as fast as Performer. We evaluate PermuteFormer on Long-Range Arena, a dataset for long sequences, as well as WikiText-103, a language modeling dataset. The experiments show that PermuteFormer uniformly improves the performance of Performer with almost no computational overhead and outperforms vanilla Transformer on most of the tasks.

PermuteFormer: Efficient Relative Position Encoding for Long Sequences

Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English. However, improvements on Chinese SC task are still quite few due to several difficulties: scarce of parallel corpora, different segmentation granularity of Chinese sentences, and imperfect performance of syntactic analyses. Furthermore, entire neural Chinese SC models have been under-investigated so far. In this work, we construct an SC dataset of Chinese colloquial sentences from a real-life question answering system in the telecommunication domain, and then, we propose a neural Chinese SC model enhanced with a Self-Organizing Map (SOM-NCSCM), to gain a valuable insight from the data and improve the performance of the whole neural Chinese SC model in a valid manner. Experimental results show that our SOM-NCSCM can significantly benefit from the deep investigation of similarity among data, and achieve a promising F1 score of 89.655 and BLEU4 score of 70.116, which also provides a baseline for further research on the Chinese SC task.

SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce environments, transfers the knowledge on individual word representations learned without restrictions. In this paper, inspired by the recent observations that language representations are relatively positioned and have more semantic knowledge as a whole, we present a new knowledge distillation objective for language representation learning that transfers the contextual knowledge via two types of relationships across representations: Word Relation and Layer Transforming Relation. Unlike other recent distillation techniques for the language models, our contextual distillation does not have any restrictions on architectural changes between teacher and student. We validate the effectiveness of our method on challenging benchmarks of language understanding tasks, not only in architectures of various sizes, but also in combination with DynaBERT, the recently proposed adaptive size pruning method.

Downloads

Next from EMNLP 2021

Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings

Similar lecture

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

.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 EMNLP 2021

Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings

Similar lecture

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

Downloads