paper-with-me

홈 › Papers

Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors

2021-03-29 · NAACL (DeeLIO) 2021 6 · Zeyu Yun, Yubei Chen, Bruno A Olshausen, Yann Lecun

Transformer networks have revolutionized NLP representation learning since they were introduced. Though a great effort has been made to explain the representation in transformers, it is widely recognized that our understanding is not sufficient. One important reason is that there lack enough visualization tools for detailed analysis. In this paper, we propose to use dictionary learning to open up these "black boxes" as linear superpositions of transformer factors. Through visualization, we demonstrate the hierarchical semantic structures captured by the transformer factors, e.g., word-level polysemy disambiguation, sentence-level pattern formation, and long-range dependency. While some of these patterns confirm the conventional prior linguistic knowledge, the rest are relatively unexpected, which may provide new insights. We hope this visualization tool can bring further knowledge and a better understanding of how transformer networks work. The code is available at https://github.com/zeyuyun1/TransformerVis

📄 PDF Abstract BibTeX arXiv:2103.15949

Code (1)

zeyuyun1/transformervis 공식 구현 pytorch

Tasks

Dictionary LearningRepresentation LearningSentence

Similar Papers 제목 키워드 기반

Word Embedding Visualization Via Dictionary Learning

2019-10-09 · Juexiao Zhang, Yubei Chen, Brian Cheung, Bruno A. Olshausen

Co-occurrence statistics based word embedding techniques have proved to be very useful in extracting the semantic and syntactic representation of words as low dimensional continuous vectors. In this work, we discovered t…

Dictionary Learning

BL.Research at SemEval-2022 Task 1: Deep networks for Reverse Dictionary using embeddings and LSTM autoencoders

2022-07-01 · SemEval (NAACL) 2022 7 · Nihed Bendahman, Julien Breton, Lina Nicolaieff, Mokhtar Boumedyen Billami 외

This paper describes our two deep learning systems that competed at SemEval-2022 Task 1 “CODWOE: Comparing Dictionaries and WOrd Embeddings”. We participated in the subtask for the reverse dictionary which consists in ge…

PositionReverse DictionaryWord Embeddings

Extracting Similar Questions From Naturally-occurring Business Conversations

2022-06-03 · Xiliang Zhu, David Rossouw, Shayna Gardiner, Simon Corston-Oliver

Pre-trained contextualized embedding models such as BERT are a standard building block in many natural language processing systems. We demonstrate that the sentence-level representations produced by some off-the-shelf co…

Sentence

Topic-aware Contextualized Transformers

2021-01-01 · Ruiying Lu, Bo Chen, Dan dan Guo, Dongsheng Wang 외

Training on disjoint fixed-length segments, Transformers successfully transform static word embeddings into contextualized word representations. However, they often restrict the context of a token to the segment it resid…

Word Embeddings

Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task

2020-05-01 · LREC 2020 5 · Md Tahmid Rahman Laskar, Jimmy Xiangji Huang, Enamul Hoque

Word embeddings that consider context have attracted great attention for various natural language processing tasks in recent years. In this paper, we utilize contextualized word embeddings with the transformer encoder fo…

Answer SelectionSentenceSentence SimilarityWord Embeddings