Thailand

The choice of token vocabulary affects the performance of machine translation. 
This paper aims to figure out what is a good vocabulary and whether we can find the optimal vocabulary without trial training. To answer these questions, we first provide an alternative understanding of vocabulary from the perspective of information theory. It motivates us to formulate the quest of vocabularization -- finding the best token dictionary with a proper size -- as an optimal transport (OT) problem. We propose VOLT, a simple and efficient solution without trial training. 
Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation. For example, VOLT achieves 70% vocabulary size reduction and 0.5 BLEU gain on English-German translation. Also, compared to BPE-search, VOLT reduces the search time from 384 GPU hours to 30 GPU hours on English-German translation. Codes are available at https://github.com/Jingjing-NLP/VOLT.

IJCNLP-AACL 2021

Vocabulary Learning via Optimal Transport for Neural Machine Translation

optimal transport

vocabulary

**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

Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks such as WMT. However, there still exist significant issues such as robustness, domain generalization, etc. In this paper, we study NMT models from the perspective of compositional generalization by building a benchmark dataset, CoGnition, consisting of 216k clean and consistent sentence pairs. We quantitatively analyze effects of various factors using compound translation error rate, then demonstrate that the NMT model fails badly on compositional generalization, although it performs remarkably well under traditional metrics.

On Compositional Generalization of Neural Machine Translation

Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing alignments from neural machine translation models, which does not leverage the full context in the target sequence. In this paper, we propose Mask-Align, a self-supervised word alignment model that takes advantage of the full context on the target side. Our model masks out each target token and predicts it conditioned on both source and the remaining target tokens. This two-step process is based on the assumption that the source token contributing most to recovering the masked target token should be aligned. We also introduce an attention variant called leaky attention, which alleviates the problem of unexpected high cross-attention weights on special tokens such as periods. Experiments on four language pairs show that our model outperforms previous unsupervised neural aligners and obtains new state-of-the-art results.

Mask-Align: Self-Supervised Neural Word Alignment

Computer-aided translation (CAT), the use of software to assist a human translator in the translation process, has been proven to be useful in enhancing the productivity of human translators. Autocompletion, which suggests translation results according to the text pieces provided by human translators, is a core function of CAT. There are two limitations in previous research in this line. First, most research works on this topic focus on sentence-level autocompletion (i.e., generating the whole translation as a sentence based on human input), but word-level autocompletion is under-explored so far. Second, almost no public benchmarks are available for the autocompletion task of CAT. This might be among the reasons why research progress in CAT is much slower compared to automatic MT. In this paper, we propose the task of general word-level autocompletion (GWLAN) from a real-world CAT scenario, and construct the first public benchmark to facilitate research in this topic. In addition, we propose an effective method for GWLAN and compare it with several strong baselines. Experiments demonstrate that our proposed method can give significantly more accurate predictions than the baseline methods on our benchmark datasets.

GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation

Prior work has proved that Translation Memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval, we propose a new framework that uses monolingual memory and performs learnable memory retrieval in a cross-lingual manner. Our framework has unique advantages. First, the cross-lingual memory retriever allows abundant monolingual data to be TM. Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal. Experiments show that the proposed method obtains substantial improvements. Remarkably, it even outperforms strong TM-augmented NMT baselines using bilingual TM. Owning to the ability to leverage monolingual data, our model also demonstrates effectiveness in low-resource and domain adaptation scenarios.

Neural Machine Translation with Monolingual Translation Memory


With the rapid growth of social media in the past decade, the news are no longer controlled by just a few mainstream sources. Users themselves create large numbers of potentially fictitious rumours, necessitating automated veracity classification systems. Here we present a novel approach towards automatically classifying rumours circulating on Twitter with respect to their veracity. We use a model built on Variational Autoencoder which disentangles the informational content of a tweet from the manner in which the information is written. This is achieved by obtaining latent topic vectors in an adversarial learning setting using the auxiliary task of stance classification. The latent vectors learnt in this way are used to predict rumour veracity, obtaining state-of-the-art accuracy scores on the PHEME dataset.

Learning Disentangled Latent Topics for Twitter Rumour Veracity Classification

We introduce a novel dataset of human judgments of machine-edited text and initial models of those perceptions. Six machine-editing methods ranging from character swapping to variational autoencoders are applied to collections of English-language social media text and scientific abstracts. The edits are judged in context for detectability and the extent to which they preserve the meaning of the original. Automated measures of semantic similarity and fluency are evaluated individually and combined to produce composite models of human perception. Both meaning preservation and detectability are predicted within 6% of the upper bound of human consensus labeling.

Perceptual Models of Machine-Edited Text

State of the art end-to-end coreference resolution models use expensive span representations and antecedent prediction mechanisms. These approaches are expensive both in terms of their memory requirements as well as compute time, and are particularly ill-suited for long documents. In this paper, we propose an approximation to end-to-end models which scales gracefully to documents of any length. Replacing span representations with token representations, we reduce the time/memory complexity via token windows and nearest neighbor sparsification methods for more efficient antecedent prediction. We show our approach's resulting reduction of training and inference time compared to state-of-the-art methods with only a minimal loss in accuracy.

Scaling Within Document Coreference to Long Texts

Many types of text style transfer can be achieved with only small, precise edits (e.g. sentiment transfer from "I had a terrible time..." to "I had a great time..."). We propose a coarse-to-fine editor for style transfer that transforms text using Levenshtein edit operations (e.g. insert, replace, delete). Unlike prior single-span edit methods, our method concurrently edits multiple spans in the source text. To train without parallel style text pairs (e.g. pairs of +/- sentiment statements), we propose an unsupervised data synthesis procedure. We first convert text to style-agnostic templates using style classifier attention (e.g. "I had a SLOT time..."), then fill in slots in these templates using fine-tuned pretrained language models. Our method outperforms existing generation and editing style transfer methods on sentiment (Yelp, Amazon) and politeness (Polite) transfer. In particular, multi-span editing achieves higher performance and more diverse output than single-span editing. Moreover, compared to previous methods on unsupervised data synthesis, our method results in higher quality parallel style pairs and improves model performance.

LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer

Word embedding techniques depend heavily on the frequencies of words in the corpus, and are negatively impacted by failures in providing reliable representations for low-frequency words or unseen words during training. To address this problem, we propose an algorithm to learn embeddings for rare words based on an Internet search engine and the spatial location relationships. Our algorithm proceeds in two steps. We firstly retrieve webpages corresponding to the rare word through the search engine and parse the returned results to extract a set of most related words. We average the vectors of the related words as the initial vector of the rare word. Then, the location of the rare word in the vector space is iteratively fine-tuned according to the order of its relevances to the related words. Compared to other approaches, our algorithm can learn more accurate representations for a wider range of vocabulary. We evaluate our learned rare-word embeddings on the word relatedness task, and the experimental results show that our algorithm achieves state-of-the-art performance.

Learning Embeddings for Rare Words Leveraging Internet Search Engine and Spatial Location Relationships

Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. However, they currently require large pretraining corpora or access to typologically similar languages. In this work, we address these obstacles by removing language identity signals from multilingual embeddings. We examine three approaches for this: (i) re-aligning the vector spaces of target languages (all together) to a pivot source language; (ii) removing language-specific means and variances, which yields better discriminativeness of embeddings as a by-product; and (iii) increasing input similarity across languages by removing morphological contractions and sentence reordering. We evaluate on XNLI and reference-free MT across 19 typologically diverse languages. Our findings expose the limitations of these approaches -- unlike vector normalization, vector space re-alignment and text normalization do not achieve consistent gains across encoders and languages. Due to the approaches' additive effects, their combination decreases the cross-lingual transfer gap by 8.9 points (m-BERT) and 18.2 points (XLM-R) on average across all tasks and languages, however. Our code and models are publicly available.

Vocabulary Learning via Optimal Transport for Neural Machine Translation

Downloads

Next from IJCNLP-AACL 2021

On Compositional Generalization of Neural Machine Translation

Similar lecture

MVP-BERT: Multi-Vocab Pre-training for Chinese BERT

Vocabulary Learning via Optimal Transport 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 IJCNLP-AACL 2021

On Compositional Generalization of Neural Machine Translation

Similar lecture

MVP-BERT: Multi-Vocab Pre-training for Chinese BERT

Downloads