ترغب بنشر مسار تعليمي؟ اضغط هنا

Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search

121   0   0.0 ( 0 )
 نشر من قبل Gyuwan Kim
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Despite transformers impressive accuracy, their computational cost is often prohibitive to use with limited computational resources. Most previous approaches to improve inference efficiency require a separate model for each possible computational budget. In this paper, we extend PoWER-BERT (Goyal et al., 2020) and propose Length-Adaptive Transformer that can be used for various inference scenarios after one-shot training. We train a transformer with LengthDrop, a structural variant of dropout, which stochastically determines a sequence length at each layer. We then conduct a multi-objective evolutionary search to find a length configuration that maximizes the accuracy and minimizes the efficiency metric under any given computational budget. Additionally, we significantly extend the applicability of PoWER-BERT beyond sequence-level classification into token-level classification with Drop-and-Restore process that drops word-vectors temporarily in intermediate layers and restores at the last layer if necessary. We empirically verify the utility of the proposed approach by demonstrating the superior accuracy-efficiency trade-off under various setups, including span-based question answering and text classification. Code is available at https://github.com/clovaai/length-adaptive-transformer.



قيم البحث

اقرأ أيضاً

Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure (Structured Procrastination) that provably achie ves near optimal performance with high probability and with nearly minimal runtime in the worst case. It also offers an $textit{anytime}$ property: it keeps tightening its optimality guarantees the longer it is run. Unfortunately, Structured Procrastination is not $textit{adaptive}$ to characteristics of the parameterized algorithm: it treats every input like the worst case. Follow-up work (LeapsAndBounds) achieves adaptivity but trades away the anytime property. This paper introduces a new algorithm, Structured Procrastination with Confidence, that preserves the near-optimality and anytime properties of Structured Procrastination while adding adaptivity. In particular, the new algorithm will perform dramatically faster in settings where many algorithm configurations perform poorly. We show empirically both that such settings arise frequently in practice and that the anytime property is useful for finding good configurations quickly.
With the development of deep learning (DL), natural language processing (NLP) makes it possible for us to analyze and understand a large amount of language texts. Accordingly, we can achieve a semantic communication in terms of joint semantic source and channel coding over a noisy channel with the help of NLP. However, the existing method to realize this goal is to use a fixed transformer of NLP while ignoring the difference of semantic information contained in each sentence. To solve this problem, we propose a new semantic communication system based on Universal Transformer. Compared with the traditional transformer, an adaptive circulation mechanism is introduced in the Universal Transformer. Through the introduction of the circulation mechanism, the new semantic communication system can be more flexible to transmit sentences with different semantic information, and achieve better end-to-end performance under various channel conditions.
We propose a new length-controllable abstractive summarization model. Recent state-of-the-art abstractive summarization models based on encoder-decoder models generate only one summary per source text. However, controllable summarization, especially of the length, is an important aspect for practical applications. Previous studies on length-controllable abstractive summarization incorporate length embeddings in the decoder module for controlling the summary length. Although the length embeddings can control where to stop decoding, they do not decide which information should be included in the summary within the length constraint. Unlike the previous models, our length-controllable abstractive summarization model incorporates a word-level extractive module in the encoder-decoder model instead of length embeddings. Our model generates a summary in two steps. First, our word-level extractor extracts a sequence of important words (we call it the prototype text) from the source text according to the word-level importance scores and the length constraint. Second, the prototype text is used as additional input to the encoder-decoder model, which generates a summary by jointly encoding and copying words from both the prototype text and source text. Since the prototype text is a guide to both the content and length of the summary, our model can generate an informative and length-controlled summary. Experiments with the CNN/Daily Mail dataset and the NEWSROOM dataset show that our model outperformed previous models in length-controlled settings.
83 - Yu Shi 2021
The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract high-level semant ic abstraction features. In this paper, two approaches are introduced to improve the performance of Transformers. We calculated the attention score by multiplying the part-of-speech weight vector with the correlation coefficient, which helps extract the words with more practical meaning. The weight vector is obtained by the input text sequence based on the importance of the part-of-speech. Furthermore, we fuse the features of each layer to make the sentence representation results more comprehensive and accurate. In experiments, we demonstrate the effectiveness of our model Transformer-F on three standard text classification datasets. Experimental results show that our proposed model significantly boosts the performance of text classification as compared to the baseline model. Specifically, we obtain a 5.28% relative improvement over the vanilla Transformer on the simple tasks.
Browsing news articles on multiple devices is now possible. The lengths of news article headlines have precise upper bounds, dictated by the size of the display of the relevant device or interface. Therefore, controlling the length of headlines is es sential when applying the task of headline generation to news production. However, because there is no corpus of headlines of multiple lengths for a given article, previous research on controlling output length in headline generation has not discussed whether the system outputs could be adequately evaluated without multiple references of different lengths. In this paper, we introduce two corpora, which are Japanese News Corpus (JNC) and JApanese MUlti-Length Headline Corpus (JAMUL), to confirm the validity of previous evaluation settings. The JNC provides common supervision data for headline generation. The JAMUL is a large-scale evaluation dataset for headlines of three different lengths composed by professional editors. We report new findings on these corpora; for example, although the longest length reference summary can appropriately evaluate the existing methods controlling output length, this evaluation setting has several problems.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا