Thailand

Document-level MT models are still far from satisfactory. Existing work extend translation unit from single sentence to multiple sentences. However, study shows that when we further enlarge the translation unit to a whole document, supervised training of Transformer can fail. In this paper, we find such failure is not caused by overfitting, but by sticking around local minima during training. Our analysis shows that the increased complexity of target-to-source attention is a reason for the failure. As a solution, we propose G-Transformer, introducing locality assumption as an inductive bias into Transformer, reducing the hypothesis space of the attention from target to source. Experiments show that G-Transformer converges faster and more stably than Transformer, achieving new state-of-the-art BLEU scores for both nonpretraining and pre-training settings on three benchmark datasets.

ACL-IJCNLP 2021

G-Transformer for Document-Level Machine Translation

transformer failure

g-transformer

document-level machine translation

**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).

technical paper

Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to-sequence (BART) models boosts content preservation, and that this is possible even with limited amounts of parallel data. Augmenting these models with rewards that target style and content –the two core aspects of the task– we achieve a new state-of-the-art.

Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer

Existing works for aspect-based sentiment analysis (ABSA) have adopted a unified approach, which allows the interactive relations among subtasks. However, we observe that these methods tend to predict polarities based on the literal meaning of aspect and opinion terms and mainly consider relations implicitly among subtasks at the word level. In addition, identifying multiple aspect--opinion pairs with their polarities is much more challenging. Therefore, a comprehensive understanding of contextual information w.r.t. the aspect and opinion are further required in ABSA. In this paper, we propose Deep Contextualized Relation-Aware Network (DCRAN), which allows interactive relations among subtasks with deep contextual information based on two modules (i.e., Aspect and Opinion Propagation and Explicit Self-Supervised Strategies). Especially, we design novel self-supervised strategies for ABSA, which have strengths in dealing with multiple aspects. Experimental results show that DCRAN significantly outperforms previous state-of-the-art methods by large margins on three widely used benchmarks.

Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) has received increasing attention recently. Most existing work tackles ABSA in a discriminative manner, designing various task-specific classification networks for the prediction. Despite their effectiveness, these methods ignore the rich label semantics in ABSA problems and require extensive task-specific designs. In this paper, we propose to tackle various ABSA tasks in a unified generative framework. Two types of paradigms, namely annotation-style and extraction-style modeling, are designed to enable the training process by formulating each ABSA task as a text generation problem. We conduct experiments on four ABSA tasks across multiple benchmark datasets where our proposed generative approach achieves new state-of-the-art results in almost all cases. This also validates the strong generality of the proposed framework which can be easily adapted to arbitrary ABSA task without additional task-specific model design.

Towards Generative Aspect-Based Sentiment Analysis

Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we use example consistency regularization to penalize the prediction sensitivity to four types of data augmentations, i.e., subword sampling, Gaussian noise, code-switch substitution, and machine translation. In addition, we employ model consistency to regularize the models trained with two augmented versions of the same training set. Experimental results on the XTREME benchmark show that our method significantly improves cross-lingual fine-tuning across various tasks, including text classification, question answering, and sequence labeling.

Consistency Regularization for Cross-Lingual Fine-Tuning

The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task. Specifically, the model first self-label word alignments for parallel sentences. Then we randomly mask tokens in a bitext pair. Given a masked token, the model uses a pointer network to predict the aligned token in the other language. We alternately perform the above two steps in an expectation-maximization manner. Experimental results show that our method improves cross-lingual transferability on various datasets, especially on the token-level tasks, such as question answering, and structured prediction. Moreover, the model can serve as a pretrained word aligner, which achieves reasonably low error rate on the alignment benchmarks. The code and pretrained parameters are available at github.com/CZWin32768/XLM-Align.

Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment

Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-frequency words between the distilled and the original data, leading to more errors on predicting low-frequency words. To alleviate the problem, we directly expose the raw data into NAT by leveraging pretraining. By analyzing directed alignments, we found that KD makes low-frequency source words aligned with targets more deterministically but fails to align sufficient low-frequency words from target to source. Accordingly, we propose reverse KD to rejuvenate more alignments for low-frequency target words. To make the most of authentic and synthetic data, we combine these complementary approaches as a new training strategy for further boosting NAT performance. We conduct experiments on five translation benchmarks over two advanced architectures. Results demonstrate that the proposed approach can significantly and universally improve translation quality by reducing translation errors on low-frequency words. Encouragingly, our approach achieves 28.2 and 33.9 BLEU points on the WMT14 English-German and WMT16 Romanian-English datasets, respectively. Our code, data, and trained models are available at \url{https://github.com/longyuewangdcu/RLFW-NAT}.

Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation

sequence-to-sequence models usually transfer all encoder outputs to the decoder for generation. In this work, by contrast, we hypothesize that these encoder outputs can be compressed to shorten the sequence delivered for decoding. We take Transformer as the testbed and introduce a layer of stochastic gates in-between the encoder and the decoder. The gates are regularized using the expected value of the sparsity inducing L0 penalty, resulting in completely masking-out a subset of encoder outputs. In other words, via joint training, the L0DROP layer forces Transformer to route information through a subset of its encoder states. We investigate the effects of this sparsification on two machine translation and two summarization tasks. Experiments show that, depending on the task, around 40–70% of source encodings can be pruned without significantly compromising quality. The decrease of the output length endows L0DROP with the potential of improving decoding efficiency, where it yields a speedup of up to 1.65x on document summarization and 1.20x on character-based machine translation against the standard Transformer. We analyze the L0DROP behaviour and observe that it exhibits systematic preferences for pruning certain word types, e.g., function words and punctuation get pruned most. Inspired by these observations, we explore the feasibility of specifying rule-based patterns that mask out encoder outputs based on information such as part-of-speech tags, word frequency and word position.

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Hypernym discovery aims to identify all possible hypernyms of a given term. The most recent hypernym discovery models exploit multiple mapping functions to project a term to different semantic spaces and then aggregate these embeddings to a general representation for further classification. We refer to this model as a parallel style model. In this work, we observe that there are hierarchical relations between a target terms' hypernyms. However, these hierarchical relations were not sufficiently considered in the previous parallel style model. To leverage the hierarchical relations, we propose a sequential style model that recurrently maps the query words to their hypernyms, starting from the most specific ones to the less specific ones. Empirical studies on SemEval-2018 Task 9 confirm the effectiveness of the presented model.

Hypernym Discovery via a Recurrent Mapping Model

Prior studies on event knowledge in sentence comprehension have shown that the aspect of the main verb plays an important role in the processing of non-core semantic roles, such as locations: when the aspect of the main verb is imperfective, locations become more salient in the mental representation of the event and are easier for human comprehenders to process.

In our study, we tested the popular language model BERT on two datasets derived from experimental studies to determine whether BERT's predictions of prototypical event locations were also influenced by aspect. We found that, although BERT efficiently modelled the typicality of locations, it did so independently of the verb aspect. Even when the transformer was forced to focus on the verb phrase by masking the context words in the sentence, the typicality predictions were still accurate; in addition, we found aspect to have a stronger influence on the scores, with locations in the imperfective setting being associated with lower surprisal values.

Modeling the Influence of Verb Aspect on the Activation of Typical Event Locations with BERT

Bilingual Lexicon Induction (BLI) aims to map words in one language to their translations in another, and are typically through learning linear projections to align monolingual word representation spaces. Two classes of word representations have been explored for BLI: static word embeddings and contextual representations, but there is no studies to combine both. In this paper, we propose a simple yet effective mechanism to combine static word embeddings and contextual representations to utilize the advantages of both paradigms. We test the combination mechanism on various language pairs under the supervised and unsupervised BLI benchmark settings. Experiments show that our mechanism consistently improves performances over robust BLI baselines on all language pairs by averagely improving 3.2 points in the supervised setting, and 3.1 points in the unsupervised setting.

Downloads

Next from ACL-IJCNLP 2021

Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer

Similar lecture

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

.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 ACL-IJCNLP 2021

Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer

Similar lecture

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

Downloads