Thailand

Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS to jointly train a single unified multilingual MT model. LaSS learns Language Specific Sub-network (LaSS) for each language pair to counter parameter interference. Comprehensive experiments on IWSLT and WMT datasets with various Transformer architectures show that LaSS obtains gains on 36 language pairs by up to 1.2 BLEU. Besides, LaSS shows its strong generalization performance at easy adaptation to new language pairs and zero-shot translation. LaSS boosts zero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codes and trained models are available at https://github.com/NLP-Playground/LaSS.

IJCNLP-AACL 2021

Learning Language Specific Sub-network for Multilingual Machine Translation

lass

multilingual 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

Continual learning has gained increasing attention in recent years, thanks to its biological interpretation and efficiency in many real-world applications. As a typical task of continual learning, continual relation extraction (CRE) aims to extract relations between entities from texts, where the samples of different relations are delivered into the model continuously. Some previous works have proved that storing typical samples of old relations in memory can help the model keep a stable understanding of old relations and avoid forgetting them. However, most methods heavily depend on the memory size in that they simply replay these memorized samples in subsequent tasks. To fully utilize memorized samples, in this paper, we employ relation prototype to extract useful information of each relation. Specifically, the prototype embedding for a specific relation is computed based on memorized samples of this relation, which is collected by K-means algorithm. The prototypes of all observed relations at current learning stage are used to re-initialize a memory network to refine subsequent sample embeddings, which ensures the model's stable understanding on all observed relations when learning a new task. Compared with previous CRE models, our model utilizes the memory information sufficiently and efficiently, resulting in enhanced CRE performance. Our experiments show that the proposed model outperforms the state-of-the-art CRE models and has great advantage in avoiding catastrophic forgetting. The code and datasets are released on https://github.com/fd2014cl/RP-CRE.

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. Our intuition is based on the hypothesis that a universal cross-language representation leads to better multilingual translation performance. To this end, we propose mRASP2, a training method to obtain a single unified multilingual translation model. mRASP2 is empowered by two techniques: a) a contrastive learning scheme to close the gap among representations of different languages, and b) data augmentation on both multiple parallel and monolingual data to further align token representations. For English-centric directions, mRASP2 achieves competitive or even better performance than a strong pre-trained model mBART on tens of WMT benchmarks. For non-English directions, mRASP2 achieves an improvement of average 10+ BLEU compared with the multilingual baseline

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search -- the de facto standard inference algorithm in NMT -- and Eikema & Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead.

In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

One of the reasons Transformer translation models are popular is that self-attention networks for context modelling can be easily parallelized at sequence level. However, the computational complexity of a self-attention network is $O(n^2)$, increasing quadratically with sequence length. By contrast, the complexity of LSTM-based approaches is only O(n). In practice, however, LSTMs are much slower to train than self-attention networks as they cannot be parallelized at sequence level: to model context, the current LSTM state relies on the full LSTM computation of the preceding state. This has to be computed n times for a sequence of length n. The linear transformations involved in the LSTM gate and state computations are the major cost factors in this. To enable sequence-level parallelization of LSTMs, we approximate full LSTM context modelling by computing hidden states and gates with the current input and a simple bag-of-words representation of the preceding tokens context. This allows us to compute each input step efficiently in parallel, avoiding the formerly costly sequential linear transformations. We then connect the outputs of each parallel step with computationally cheap element-wise computations. We call this the Highly Parallelized LSTM. To further constrain the number of LSTM parameters, we compute several small HPLSTMs in parallel like multi-head attention in the Transformer. The experiments show that our MHPLSTM decoder achieves significant BLEU improvements, while being even slightly faster than the self-attention network in training, and much faster than the standard LSTM.

Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation

Word alignment and machine translation are two closely related tasks. Neural translation models, such as RNN-based and Transformer models, employ a target-to-source attention mechanism which can provide rough word alignments, but with a rather low accuracy. High-quality word alignment can help
neural machine translation in many different ways, such as missing word detection, annotation transfer and lexicon injection. Existing methods for learning word alignment include statistical word aligners (e.g. GIZA++) and recently neural word alignment models. This paper presents a bidirectional Transformer based alignment (BTBA) model for unsupervised learning of the word alignment task. Our BTBA model predicts the current target word by attending the source context and both left-side and right-side target context to produce accurate target-to-source attention (alignment). We further fine-tune the target-to-source attention in the BTBA model to obtain better alignments using a full context based optimization
method and self-supervised training. We test our method on three word alignment tasks and show that our method outperforms both previous neural word alignment approaches and the popular statistical word aligner GIZA++.

A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment

Recently, chest X-ray report generation, which aims to automatically generate descriptions of given chest X-ray images, has received growing research interests. The key challenge of chest X-ray report generation is to accurately capture and describe the abnormal regions. In most cases, the normal regions dominate the entire chest X-ray image, and the corresponding descriptions of these normal regions dominate the final report. Due to such data bias, learning-based models may fail to attend to abnormal regions. In this work, to effectively capture and describe abnormal regions, we propose the Contrastive Attention (CA) model. Instead of solely focusing on the current input image, the CA model compares the current input image with normal images to distill the contrastive information. The acquired contrastive information can better represent the visual features of abnormal regions. According to the experiments on the public IU-X-ray and MIMIC-CXR datasets, incorporating our CA into several existing models can boost their performance across most metrics. In addition, according to the analysis, the CA model can help existing models better attend to the abnormal regions and provide more accurate descriptions which are crucial for an interpretable diagnosis. Specifically, we achieve the state-of-the-art results on the two public datasets.

Contrastive Attention for Automatic Chest X-ray Report Generation

A long-standing challenge in Chinese–English machine translation is that sentence boundaries are ambiguous in Chinese orthography, but inferring good splits is necessary for obtaining high quality translations. To solve this, we use reinforcement learning to train a segmentation policy that splits Chinese texts into segments that can be independently translated so as to maximise the overall translation quality. We compare to a variety of segmentation strategies and find that our approach improves the baseline BLEU score on the WMT2020 Chinese–English news translation task by +0.3 BLEU overall and improves the score on input segments that contain more than 60 words by +3 BLEU.

Better {C}hinese Sentence Segmentation with Reinforcement Learning

Transfer learning has become the dominant paradigm for many natural language processing tasks. In addition to models being pretrained on large datasets, they can be further trained on intermediate (supervised) tasks that are similar to the target task. For small Natural Language Inference (NLI) datasets, language modelling is typically followed by pretraining on a large (labelled) NLI dataset before fine-tuning with each NLI subtask.
In this work, we explore Gradient Boosted Decision Trees (GBDTs) as an alternative to the commonly used Multi-Layer Perceptron (MLP) classification head. GBDTs have desirable properties such as good performance on dense, numerical features and are effective where the ratio of the number of samples w.r.t the number of features is low.
In addition, we introduce FreeGBDT, a method of fitting a GBDT head on the features computed during fine-tuning to increase performance without additional computation by the neural network. We demonstrate the effectiveness of our method on several NLI datasets using a strong baseline model (RoBERTa-large with MNLI pretraining). The FreeGBDT shows a consistent improvement over the standard MLP classification head.

Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning

Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training method by proposing an empirical error generation approach that employs a sequence-to-sequence model trained to perform translation from error-free to erroneous text. Using an OCR engine, we generated a large parallel text corpus for training and produced several real-world noisy sequence labeling benchmarks for evaluation. Moreover, to overcome the data sparsity problem that exacerbates in the case of imperfect textual input, we learned noisy language model-based embeddings. Our approach outperformed the baseline noise generation and error correction techniques on the erroneous sequence labeling data sets. To facilitate future research on robustness, we make our code, embeddings, and data conversion scripts publicly available.

Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer.
In this paper, we propose a simple and effective passage reranking method, named Reader-guIDEd Reranker (RIDER), which does not involve training and reranks the retrieved passages solely based on the top predictions of the reader before reranking.
We show that RIDER, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) gains without refining the retriever or reader.
In addition, RIDER, without any training, outperforms state-of-the-art transformer-based supervised rerankers.
Remarkably, RIDER achieves 48.3 EM on the Natural Questions dataset and 66.4 EM on the TriviaQA dataset when only 1,024 tokens (7.8 passages on average) are used as the reader input after passage reranking.

Learning Language Specific Sub-network for Multilingual Machine Translation

Downloads

Next from IJCNLP-AACL 2021

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

Similar lecture

Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event

Learning Language Specific Sub-network for Multilingual 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

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

Similar lecture

Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event

Downloads