Thailand

Despite transformers&#39; 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/lengthadaptive-transformer.

IJCNLP-AACL 2021

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

evolutionary search

sequence length

anytime prediction

efficiency

transformer

**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).

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/lengthadaptive-transformer.

technical paper

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model’s performance by transferring teacher model’s knowledge on each training sample. However, previous work rarely discusses the different impacts and connections among these samples, which serve as the medium for transferring teacher knowledge. In this paper, we design a novel protocol that can effectively analyze the different impacts of samples by comparing various samples’ partitions. Based on above protocol, we conduct extensive experiments and find that the teacher’s knowledge is not the more, the better. Knowledge over specific samples may even hurt the whole performance of knowledge distillation. Finally, to address these issues, we propose two simple yet effective strategies, i.e., batch-level and global-level selections, to pick suitable samples for distillation. We evaluate our approaches on two large-scale machine translation tasks, WMT’14 English-German and WMT’19 Chinese-English. Experimental results show that our approaches yield up to +1.28 and +0.89 BLEU points improvements over the Transformer baseline, respectively.

Selective Knowledge Distillation for Neural Machine Translation

Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context, context from sentences other than those currently being translated. However, while many current methods present model architectures that theoretically can use this extra context, it is often not clear how much they do actually utilize it at translation time. In this paper, we introduce a new metric, conditional cross-mutual information, to quantify usage of context by these models. Using this metric, we measure how much document-level machine translation systems use particular varieties of context. We find that target context is referenced more than source context, and that including more context has a diminishing affect on results. We then introduce a new, simple training method, context-aware word dropout, to increase the usage of context by context-aware models. Experiments show that our method not only increases context usage, but also improves the translation quality according to metrics such as BLEU and COMET, as well as performance on anaphoric pronoun resolution and lexical cohesion contrastive datasets.

Measuring and Increasing Context Usage in Context-Aware Machine Translation

Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we propose an alternative approach that does not have this limitation, while requiring a weak seed dictionary (e.g., a list of identical words) as the only form of supervision. Rather than aligning two fixed embedding spaces, our method works by fixing the target language embeddings, and learning a new set of embeddings for the source language that are aligned with them. To that end, we use an extension of skip-gram that leverages translated context words as anchor points, and incorporates self-learning and iterative restarts to reduce the dependency on the initial dictionary. Our approach outperforms conventional mapping methods on bilingual lexicon induction, and obtains competitive results in the downstream XNLI task.

Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring

We introduce an Edit-Based Transformer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice. Building on recent models for non-autoregressive sequence generation (Gu et al., 2019), EDITOR generates new sequences by iteratively editing hypotheses. It relies on a novel reposition operation designed to disentangle lexical choice from word positioning decisions, while enabling efficient oracles for imitation learning and parallel edits at decoding time. Empirically, EDITOR uses soft lexical constraints more effectively than the Levenshtein Transformer (Gu et al., 2019) while speeding up decoding dramatically compared to constrained beam search (Post and Vilar, 2018). EDITOR also achieves comparable or better translation quality with faster decoding speed than the Levenshtein Transformer on standard Romanian-English, English-German, and English-Japanese machine translation tasks.

EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints

Emphasizing words in presentation slides allows viewers to direct their gaze to focal points without reading the entire slide, retaining their attention on the speaker. Despite many studies on automatic slide generation, few have addressed helping authors choose which words to emphasize.
Motivated by this, we study the problem of choosing candidates for emphasis by introducing a new dataset containing presentation slides with a wide variety of topics. 
We evaluated a range of state-of-the-art models on this novel dataset by organizing a shared task and inviting multiple researchers to model emphasis in slides.

PSED: A Dataset for Selecting Emphasis in Presentation Slides

As a language model that integrates traditional symbolic operations and flexible neural representations, recurrent neural network grammars (RNNGs) have attracted great attention from both scientific and engineering perspectives. However, RNNGs are known to be harder to scale due to the difficulty of batched training. In this paper, we propose effective batching for RNNGs, where every operation is computed in parallel with tensors across multiple sentences. Our PyTorch implementation effectively employs a GPU and achieves x6 speedup compared to the existing C++ DyNet implementation with model-independent auto-batching. Moreover, our batched RNNG also accelerates inference and achieves x20-150 speedup for beam search depending on beam sizes. Finally, we evaluate syntactic generalization performance of the scaled RNNG against the LSTM baseline, based on the large training data of 100M tokens from English Wikipedia and the broad-coverage targeted syntactic evaluation benchmark.\footnote{Our RNNG implementation is available at https://github.com/aistairc/rnng-pytorch/.}

Effective Batching for Recurrent Neural Network Grammars

Contextualized word representations have proven useful for various natural language processing tasks. However, it remains unclear to what extent these representations can cover hand-coded semantic information such as semantic frames, which specify the semantic role of the arguments associated with a predicate. In this paper, we focus on verbs that evoke different frames depending on the context, and we investigate how well contextualized word representations can recognize the difference of frames that the same verb evokes. We also explore which types of representation are suitable for semantic frame induction. In our experiments, we compare seven different contextualized word representations for two English frame-semantic resources, FrameNet and PropBank. We demonstrate that several contextualized word representations, especially BERT and its variants, are considerably informative for semantic frame induction. Furthermore, we examine the extent to which the contextualized representation of a verb can estimate the number of frames that the verb can evoke.

Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction

Neural topic modeling approach has been attracting much attention recently as it is able to leverage the advantages of both neural networks and probabilistic topic models. Previous works have proposed several models that are based on this framework and obtained impressive experimental results compared to traditional probabilistic models. However, the reported result is not consistent across the works, making them hard for gaining a rigorous assessment of these approaches. This work aims to address this issue by offering an extensive empirical evaluation of typical neural topic models in different aspects using large, diverse datasets as well as a thorough set of metrics. Precisely, we examine the performance of these models in three tasks, namely uncovering cohesive topics, modeling the input documents, and representing them for downstream classification. Our results show that while the neural topic models are better in the first and the third tasks, the traditional probabilistic models are still a strong baseline and are better in the second task in many cases. These findings give us more insights for choosing off-the-shelf topic modeling toolboxes in different contexts, as well as for designing more comprehensive evaluation for neural topic models.

Benchmarking Neural Topic Models: An Empirical Study

AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of the compositional tree structures for training. In the past, these were obtained using complex graphbank-specific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.

Learning compositional structures for semantic graph parsing

Transformer-based approaches have been successfully used to obtain state-of-the-art accuracy on natural language processing (NLP) tasks with semi-structured tables. These model architectures are typically deep, resulting in slow training and inference, especially for long inputs. To improve efficiency while maintaining a high accuracy, we propose a new architecture, DoT, a double transformer model, that decomposes the problem into two sub-tasks: A shallow pruning transformer that selects the top-K tokens, followed by a deep task-specific transformer that takes as input those K tokens. Additionally, we modify the task-specific attention to incorporate the pruning scores. The two transformers are jointly trained by optimizing the task-specific loss. We run experiments on three benchmarks, including entailment and question-answering. We show that for a small drop of accuracy, DoT improves training and inference time by at least 50%. We also show that the pruning transformer effectively selects relevant tokens enabling the end-to-end model to maintain similar accuracy as slower baseline models. Finally, we analyse the pruning and give some insight into its impact on the task model.

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

Downloads

Next from IJCNLP-AACL 2021

Selective Knowledge Distillation for Neural Machine Translation

Similar lecture

AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation

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

.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 IJCNLP-AACL 2021

Selective Knowledge Distillation for Neural Machine Translation

Similar lecture

AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation

Downloads