Thailand

Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem. However, previous approaches only use static word frequency information in the target language without considering the source language, which is insufficient for bilingual tasks like machine translation. In this paper, we propose a novel bilingual mutual information (BMI) based adaptive objective, which measures the learning difficulty for each target token from the perspective of bilingualism, and assigns an adaptive weight accordingly to improve token-level adaptive training. This method assigns larger training weights to tokens with higher BMI, so that easy tokens are updated with coarse granularity while difficult tokens are updated with fine granularity. Experimental results on WMT14 English-to-German and WMT19 Chinese-to-English demonstrate the superiority of our approach compared with the Transformer baseline and previous token-level adaptive training approaches. Further analyses confirm that our method can improve the lexical diversity.

ACL-IJCNLP 2021

Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

bilingual mutual information

adaptive training

neural 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

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

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.

G-Transformer for Document-Level Machine Translation

he Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation. Therefore, the NMT model naturally involves the mechanism of the Language Model (LM) that predicts the next token only based on partial translation. Despite its success, NMT still suffers from the hallucination problem, generating fluent but inadequate translations. The main reason is that NMT pays excessive attention to the partial translation while neglecting the source sentence to some extent, namely overconfidence of the LM. Accordingly, we define the Margin between the NMT and the LM, calculated by subtracting the predicted probability of the LM from that of the NMT model for each token. The Margin is negatively correlated to the overconfidence degree of the LM. Based on the property, we propose a Margin-based Token-level Objective (MTO) and a Margin-based Sentence-level Objective (MSO) to maximize the Margin for preventing the LM from being overconfident. Experiments on WMT14 English-to-German, WMT19 Chinese-to-English, and WMT14 English-to-French translation tasks demonstrate the effectiveness of our approach, with 1.36, 1.50, and 0.63 BLEU improvements, respectively, compared to the Transformer baseline. The human evaluation further verifies that our approaches improve translation adequacy as well as fluency.

Prevent the Language Model from being Overconfident in Neural Machine Translation

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.

Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence architectures, by masking parts of the input and reconstructing them in the decoder. In this work, we systematically compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context. We pretrain models with different methods on English-German, English-Nepali and English-Sinhala monolingual data, and evaluate them on NMT, obtaining very unexpected results. In (semi-) supervised NMT, varying the pretraining objective leads to surprisingly small differences in the finetuned performance, whereas unsupervised NMT is much more sensitive to it. To understand these results, we thoroughly study the pretrained models using a series of probes and verify that they encode and use information in different ways. We conclude that finetuning on *parallel data* is most sensitive to few properties that are shared by most models, such as a strong decoder, in contrast to unsupervised NMT that also requires models with strong cross-lingual abilities.

Exploring Unsupervised Pretraining Objectives for Machine Translation

Dialogue generation has been improved through injecting knowledge into generative models. However, addition of knowledge through simple selection of sentences or paragraphs is likely to introduce noise and diminish the effectiveness of the generative models. In this paper, we present a novel Knowledge Term Weighting Model (KTWM) that incorporates term-level de-noising of the selected knowledge. KTWM includes a module for generating Simulated Response Vectors (SRVs) and uses SRVs attention distributions with the knowledge embeddings to determine knowledge term weights. Our experiments demonstrate that KTWM, combined with various knowledge selection algorithms, consistently achieves statistically significant improvements over methods without term weighting when applied to two publicly available datasets Wizard of Wikipedia (Wiz) and Holl-E. The results are particularly improved for the Wiz test data with unseen topics, demonstrating the robustness of the KTWM noise-reduction approach.

Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

Downloads

Next from ACL-IJCNLP 2021

Consistency Regularization for Cross-Lingual Fine-Tuning

Similar lecture

Revisiting Negation in Neural Machine Translation

Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

.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

Consistency Regularization for Cross-Lingual Fine-Tuning

Similar lecture

Revisiting Negation in Neural Machine Translation

Downloads