Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning
May 3, 2021
Speakers
Longyue Wang
Speaker · 1 follower
Derek Wong
Speaker · 0 followers
Liang Ding
Speaker · 1 follower
Lidia Chao
Speaker · 0 followers
Zhaopeng Tu
Speaker · 2 followers
About
Encoder layer fusion (EncoderFusion) is a technique to fuse all the encoder layers (instead of the uppermost layer) for sequence-to-sequence (Seq2Seq) models, which has proven effective on various NLP tasks. However, it is still not entirely clear why and when EncoderFusion should work. In this paper, our main contribution is to take a step further in understanding EncoderFusion. Many of previous studies believe that the success of EncoderFusion comes from exploiting surface and syntactic information embedded in lower encoder layers. Unlike them, we find that the encoder embedding layer is more important than other intermediate encoder layers. In addition, the uppermost decoder layer consistently pays more attention to the encoder embedding layer across NLP tasks. Based on this observation, we propose a simple fusion method, SurfaceFusion, by fusing only the encoder embedding layer for the softmax layer. Experimental results show that SurfaceFusion outperforms EncoderFusion on several NLP benchmarks, including machine translation, text summarization, and grammatical error correction. It obtains the state-of-the-art performance on WMT16 Romanian-English and WMT14 English-French translation tasks. Extensive analyses reveal that SurfaceFusion learns more expressive bilingual word embeddings by building a closer relationship between relevant source and target embeddings. The source code will be released.Encoder layer fusion (EncoderFusion) is a technique to fuse all the encoder layers (instead of the uppermost layer) for sequence-to-sequence (Seq2Seq) models, which has proven effective on various NLP tasks. However, it is still not entirely clear why and when EncoderFusion should work. In this paper, our main contribution is to take a step further in understanding EncoderFusion. Many of previous studies believe that the success of EncoderFusion comes from exploiting surface and syntactic inform…
About ICLR 2021
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Intro & Welcome
Watch later
A Distributional Approach to Controlled Text Generation
Watch later
FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning
Watch later
Predicting Classification Accuracy when Adding New Unobserved Classes
Watch later
Graph Convolution with Low-rank Learnable Local Filters
Watch later
Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning
Watch later
Alihan Hüyük, …