Thailand

Neural machine translation has achieved great success in bilingual settings, as well as in multilingual settings. With the increase of the number of languages, multilingual systems tend to underperform their bilingual counterparts. Model capacity has been found crucial for massively multilingual NMT to support language pairs with varying typological characteristics. Previous work increases the modeling capacity by deepening or widening the Transformer. However, modeling cardinality based on aggregating a set of transformations with the same topology has been proven more effective than going deeper or wider when increasing capacity. In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality. Unlike previous work which feeds the same input to several transformations and merges their outputs into one, we present a Multi-Input-Multi-Output (MIMO) architecture that allows each transformation of the block to have its own input. We also present a task-aware attention mechanism to learn to selectively utilize individual transformations from a set of transformations for different translation directions. Our model surpasses previous work and establishes a new state-of-the-art on the large scale OPUS-100 corpus while being 1.31 times as fast.

IJCNLP-AACL 2021

Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation

task attention

mimo cardinality

multilingual 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

Human activities can be seen as sequences of events, which are crucial to understanding societies. Disproportional event distribution for different demographic groups can manifest and amplify social stereotypes, and potentially jeopardize the ability of members in some groups to pursue certain goals. In this paper, we present the first event-centric study of gender biases in a Wikipedia corpus. To facilitate the study, we curate a corpus of career and personal life descriptions with demographic information consisting of 7,854 fragments from 10,412 celebrities. Then we detect events with a state-of-the-art event detection model, calibrate the results using strategically generated templates, and extract events that have asymmetric associations with genders. Our study discovers that the Wikipedia pages tend to intermingle personal life events with professional events for females but not for males, which calls for the awareness of the Wikipedia community to formalize guidelines and train the editors to mind the implicit biases that contributors carry. Our work also lays the foundation for future works on quantifying and discovering event biases at the corpus level.

Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia

This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has found that only a few attention heads are important in each mono-lingual Natural Language Processing (NLP) task and pruning the remaining heads leads to comparable or improved performance of the model. However, the impact of pruning attention heads is not yet clear in cross-lingual and multi-lingual tasks. Through extensive experiments, we show that (1) pruning a number of attention heads in a multi-lingual Transformer-based model has, in general, positive effects on its performance in cross-lingual and multi-lingual tasks and (2) the attention heads to be pruned can be ranked using gradients and identified with a few trial experiments. Our experiments focus on sequence labeling tasks, with potential applicability on other cross-lingual and multi-lingual tasks. For comprehensiveness, we examine two pre-trained multi-lingual models, namely multi-lingual BERT (mBERT) and XLM-R, on three tasks across 9 languages each. We also discuss the validity of our findings and their extensibility to truly resource-scarce languages and other task settings.

Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks

Effective adversary generation for neural machine translation (NMT) is a crucial prerequisite for building robust machine translation systems. In this work, we investigate veritable evaluations of NMT adversarial attacks, and propose a novel method to craft NMT adversarial examples. We first show the current NMT adversarial attacks may be improperly estimated by the commonly used mono-directional translation, and we propose to leverage the round-trip translation technique to build valid metrics for evaluating NMT adversarial attacks. Our intuition is that an effective NMT adversarial example, which imposes minor shifting on the source and degrades the translation dramatically, would naturally lead to a semantic-destroyed round-trip translation result. We then propose a promising black-box attack method called Word Saliency speedup Local Search (WSLS) that could effectively attack the mainstream NMT architectures. Comprehensive experiments demonstrate that the proposed metrics could accurately evaluate the attack effectiveness, and the proposed WSLS could significantly break the state-of-art NMT models with small perturbation. Besides, WSLS exhibits strong transferability on attacking Baidu and Bing online translators.

Crafting Adversarial Examples for Neural Machine Translation

Transfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks. However, annotated data for every target task in every target language is rare, especially for low-resource languages. We propose UXLA, a novel unsupervised data augmentation framework for zero-resource transfer learning scenarios. In particular, UXLA aims to solve cross-lingual adaptation problems from a source language task distribution to an unknown target language task distribution, assuming no training label in the target language. At its core, UXLA performs simultaneous self-training with data augmentation and unsupervised sample selection. To show its effectiveness, we conduct extensive experiments on three diverse zero-resource cross-lingual transfer tasks. UXLA achieves SoTA results in all the tasks, outperforming the baselines by a good margin. With an in-depth framework dissection, we demonstrate the cumulative contributions of different components to its success.

UXLA: A Robust Unsupervised Data Augmentation Framework for Cross-Lingual NLP

Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple decoding passes, leading to reduced speedup. We propose the Glancing Language Model (GLM) for single-pass parallel generation models. With GLM, we develop Glancing Transformer (GLAT) for machine translation. With only single-pass parallel decoding, GLAT is able to generate high-quality translation with 8×-15× speedup. Note that GLAT does not modify the network architecture, which is a training method to learn word interdependency. Experiments on multiple WMT language directions show that GLAT outperforms all previous single pass non-autoregressive methods, and is nearly comparable to Transformer, reducing the gap to 0.25-0.9 BLEU points.

Glancing Transformer for Non-Autoregressive Neural Machine Translation

Neural sequence models can generate highly fluent sentences, but recent studies have also shown that they are also prone to hallucinate additional content not supported by the input.
This variety of fluent but wrong text is particularly problematic, as it will not be possible for users to tell they are being presented incorrect content.
To detect these errors, we propose a task to predict whether each token in the output sequence is hallucinated (not contained in the input) and collect new manually annotated evaluation sets for this task.
We also introduce a novel method for learning to model hallucination detection, using pretrained language models fine tuned on synthetic data that includes automatically inserted hallucinations. 
Experiments on machine translation and abstractive text summarization demonstrate the effectiveness of our proposed approach --- we consistently outperform strong baselines across all the benchmark datasets.
Furthermore, we demonstrate how to use the token-level hallucination labels to define a fine-grained loss over the target sequence in low-resource machine translation and achieve significant improvements over strong baseline methods.
We also apply our method to word-level quality estimation for MT and show its effectiveness in both the supervised and unsupervised settings.

Detecting Hallucinated Content in Conditional Neural Sequence Generation

We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa. Existing methods typically update the original parameters of pre-trained models when injecting knowledge. However, when multiple kinds of knowledge are injected, the historically injected knowledge would be flushed away. To address this, we propose K-Adapter, a framework that retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused model. Taking RoBERTa as the backbone model, K-Adapter has a neural adapter for each kind of infused knowledge, like a plug-in connected to RoBERTa. There is no information flow between different adapters, thus multiple adapters can be efficiently trained in a distributed way. As a case study, we inject two kinds of knowledge in this work, including (1) factual knowledge obtained from automatically aligned text-triplets on Wikipedia and Wikidata and (2) linguistic knowledge obtained via dependency parsing. Results on three knowledge-driven tasks, including relation classification, entity typing, and question answering, demonstrate that each adapter improves the performance and the combination of both adapters brings further improvements. Further analysis indicates that K-Adapter captures versatile knowledge than RoBERTa.

{K-Adapter}: {I}nfusing {K}nowledge into {P}re-{T}rained {M}odels with {A}dapters

Recent progress has been made in using BERT framework for Chinese spelling error correction (CSC). However, most existing methods correct words based on local contextual information, without considering the influence of error words in sentences. Imposing attention on error contextual information could mislead and decrease the overall performance of CSC. To address this issue, we propose a Global Attention Decoder (GAD) approach for CSC. Specifically, the proposed method learns the global relationship of the potential correct input characters and the candidates of potential error characters. Rich global contextual information is obtained to alleviate the impact of the local error contextual information. In addition, a BERT with Confusion set guided Replacement Strategy (BERT CRS) is designed to narrow the gap between BERT and CSC. The candidates generated by BERT CRS covering the correct character with more than 99.9% probability. To demonstrate the effectiveness of our proposed framework, we test our method on three human-annotated datasets. The experimental results show that our approach outperforms all competitor models by a large margin of up to 6.2%, achieving state-of-the-art methods on all datasets.

Global Attention Decoder for {C}hinese Spelling Error Correction

Rhetorical implicit emotion identification is one of important and challenging tasks in natural language processing. We observe that each rhetoric may express certain evidence of semantic and syntactic patterns. Then, we design a gate mechanism based classification module to capture respective rhetorical representation and identify each rhetoric. Moreover, sentences carved with rhetoric tends to express emotions in subtle ways. We thus propose a new multi-task learning framework that can encode the categorical correlation between tasks to improve the performance of rhetoric and emotion identification problem. Experimental results validate the benefit of the proposed model over state-of-the-art baselines for rhetoric and emotion identification tasks. In addition, a new Chinese rhetorical implicit emotion dataset was constructed and will be released in this work.

Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning

We present a new approach to encourage neural machine translation to satisfy lexical constraints. Our method acts at the training step and thereby avoiding the introduction of any extra computational overhead at inference step. The proposed method combines three main ingredients. The first one consists in augmenting the training data to specify the constraints. Intuitively, this encourages the model to learn a copy behavior when it encounters constraint terms. Compared to previous work, we use a simplified augmentation strategy without source factors. The second ingredient is constraint token masking, which makes it even easier for the model to learn the copy behavior and generalize better. The third one, is a modification of the standard cross entropy loss to bias the model towards assigning high probabilities to constraint words. Empirical results show that our method improves upon related baselines in terms of both BLEU score and the percentage of generated constraint terms.

Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation

Downloads

Next from IJCNLP-AACL 2021

Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia

Similar lecture

Importance-based Neuron Allocation for Multilingual Neural Machine Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Modeling Task-Aware MIMO Cardinality for Efficient Multilingual 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 IJCNLP-AACL 2021

Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia

Similar lecture

Importance-based Neuron Allocation for Multilingual Neural Machine Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads