Dominican Republic

Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the gap between training and inference. However, vanilla scheduled sampling is merely based on training steps and equally treats all decoding steps. Namely, it simulates an inference scene with uniform error rates, which disobeys the real inference scene, where larger decoding steps usually have higher error rates due to error accumulations. To alleviate the above discrepancy, we propose scheduled sampling methods based on decoding steps, increasing the selection chance of predicted tokens with the growth of decoding steps. Consequently, we can more realistically simulate the inference scene during training, thus better bridging the gap between training and inference. Moreover, we investigate scheduled sampling based on both training steps and decoding steps for further improvements. Experimentally, our approaches significantly outperform the Transformer baseline and vanilla scheduled sampling on three large-scale WMT tasks. Additionally, our approaches also generalize well to the text summarization task and achieve state-of-the-art performance in 4 of 6 criteria on CNN/DailyMail and Gigaword.

EMNLP 2021

Scheduled Sampling Based on Decoding Steps for Neural Machine Translation

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

poster

Multi-head self-attention recently attracts enormous interest owing to its specialized functions, significant parallelizable computation, and flexible extensibility. However, very recent empirical studies show that some self-attention heads make little contribution and can be pruned as redundant heads. This work takes a novel perspective of identifying and then vitalizing redundant heads. We propose a redundant head enlivening (RHE) method to precisely identify redundant heads, and then vitalize their potential by learning syntactic relations and prior knowledge in text without sacrificing the roles of important heads. Two novel syntax-enhanced attention (SEA) mechanisms: a dependency mask bias and a relative local-phrasal position bias, are introduced to revise self-attention distributions for syntactic enhancement in machine translation. The importance of individual heads is dynamically evaluated during the redundant heads identification, on which we apply SEA to vitalize redundant heads while maintaining the strength of important heads.

Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation

Multilingual T5 (mT5; Xue et al. 2020) pretrains a sequence-to-sequence model on massive monolingual texts, which has shown promising results on many cross-lingual tasks. In this paper, we improve multilingual text-to-text transfer Transformer with translation pairs (mT6). Specifically, we explore three cross-lingual text-to-text pre-training tasks, namely, machine translation, translation pair span corruption, and translation span corruption. In addition, we propose a partially nonautoregressive objective for text-to-text pretraining. We evaluate the methods on seven multilingual benchmark datasets, including sentence classification, named entity recognition, question answering, and abstractive summarization. Experimental results show that the proposed mT6 improves cross-lingual transferability over mT5.

mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs

Machine translation usually relies on parallel corpora to provide parallel signals for training. The advent of unsupervised machine translation has brought machine translation away from this reliance, though performance still lags behind traditional supervised machine translation. In unsupervised machine translation, the model seeks symmetric language similarities as a source of weak parallel signal to achieve translation. Chomsky's Universal Grammar theory postulates that grammar is an innate form of knowledge to humans and is governed by universal principles and constraints. Therefore, in this paper, we seek to leverage such shared grammar clues to provide more explicit language parallel signals to enhance the training of unsupervised machine translation models. Through experiments on multiple typical language pairs, we demonstrate the effectiveness of our proposed approaches.

Unsupervised Neural Machine Translation with Universal Grammar

Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in real world. One common practice is to adjust the share of each corpus in the training, so that the learning process is balanced and low-resource cases can benefit from the high resource ones. However, automatic balancing methods usually depend on the intra- and inter-dataset characteristics, which is usually agnostic or requires human priors. In this work, we propose an approach, MultiUAT, that dynamically adjusts the training data usage based on the model's uncertainty on a small set of trusted clean data for multi-corpus machine translation. We experiments with two classes of uncertainty measures on multilingual (16 languages with 4 settings) and multi-domain settings (4 for in-domain and 2 for out-of-domain on English-German translation) and demonstrate our approach MultiUAT substantially outperforms its baselines, including both static and dynamic strategies. We analyze the cross-domain transfer and show the deficiency of static and similarity based methods.

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training

Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is generally acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose ERNIE-M, a new training method that encourages the model to align the representation of multiple languages with monolingual corpora, to overcome the constraint that the parallel corpus size places on the model performance. Our key insight is to integrate back-translation into the pre-training process. We generate pseudo-parallel sentence pairs on a monolingual corpus to enable the learning of semantic alignments between different languages, thereby enhancing the semantic modeling of cross-lingual models. Experimental results show that ERNIE-M outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-lingual downstream tasks.

ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora

This paper proposes a novel architecture, Cross Attention Augmented Transducer (CAAT), for simultaneous translation. The framework aims to jointly optimize the policy and translation models. To effectively consider all possible READ-WRITE simultaneous translation action paths, we adapt the online automatic speech recognition (ASR) model, RNN-T, but remove the strong monotonic constraint, which is critical for the translation task to consider reordering. To make CAAT work, we introduce a novel latency loss whose expectation can be optimized by a forward-backward algorithm. We implement CAAT with Transformer while the general CAAT architecture can also be implemented with other attention-based encoder-decoder frameworks. Experiments on both speech-to-text (S2T) and text-to-text (T2T) simultaneous translation tasks show that CAAT achieves significantly better latency-quality trade-offs compared to the state-of-the-art simultaneous translation approaches.

Cross Attention Augmented Transducer Networks for Simultaneous Translation

Schema translation is the task of automatically translating headers of tabular data from one language to another. High-quality schema translation plays an important role in cross-lingual table searching, understanding and analysis. Despite its importance, schema translation is not well studied in the community, and state-of-the-art neural machine translation models cannot work well on this task because of two intrinsic differences between plain text and tabular data: morphological difference and context difference. To facilitate the research study, we construct the first parallel dataset for schema translation, which consists of 3,158 tables with 11,979 headers written in 6 different languages, including English, Chinese, French, German, Spanish, and Japanese. Also, we propose the first schema translation model called CAST, which is a header-to-header neural machine translation model augmented with schema context. Specifically, we model a target header and its context as a directed graph to represent their entity types and relations. Then CAST encodes the graph with a relational-aware transformer and uses another transformer to decode the header in the target language. Experiments on our dataset demonstrate that CAST significantly outperforms state-of-the-art neural machine translation models.

Translating Headers of Tabular Data: A Pilot Study of Schema Translation

This work presents a pilot study to automatic linguistic preprocessing of Ancient and Byzantine Greek, and morphological analysis more specifically. To this end, a novel subword-based BERT language model was trained on the basis of a varied corpus of Modern, Ancient and Post-classical Greek texts. Consequently, the obtained BERT embeddings were incorporated to train a fine-grained Part-of-Speech tagger for Ancient and Byzantine Greek. In addition, a corpus of Greek Epigrams was manually annotated and the resulting gold standard was used to evaluate the performance of the morphological analyser on Byzantine Greek.
The experimental results show very good perplexity scores (4.9) for the BERT language model and state-of-the-art performance for the fine-grained Part-of-Speech tagger for in-domain data (treebanks containing a mixture of Classical and Medieval Greek), as well as for the newly created Byzantine Greek gold standard data set. The language models and associated code are made available for use at https://github.com/pranaydeeps/Ancient-Greek-BERT

A Pilot Study for BERT Language Modelling and Morphological Analysis for Ancient and Medieval Greek

The knowledge of the European silk textile production is a typical case for which the information collected is heterogeneous, spread across many museums and sparse since rarely complete. Knowledge Graphs for this cultural heritage domain, when being developed with appropriate ontologies and vocabularies, enable to integrate and reconcile this diverse information. However, many of these original museum records still have some metadata gaps. In this paper, we present a zero-shot learning approach that leverages the ConceptNet common sense knowledge graph to predict categorical metadata informing about the silk objects production. We compared the performance of our approach with traditional supervised deep learning-based methods that do require training data. We demonstrate promising and competitive performance for similar datasets and circumstances and the ability to predict sometimes more fine-grained information. Our results can be reproduced using the code and datasets published at https://github.com/silknow/ZSL-KG-silk.

Zero-Shot Information Extraction to Enhance a Knowledge Graph Describing Silk Textiles

We explore Boccaccio's Decameron to see how digital humanities tools can be used for tasks that have limited data in a language no longer in contemporary use: medieval Italian. We focus our analysis on the question: Do the different storytellers in the text exhibit distinct personalities? To answer this question, we curate and release a dataset based on the authoritative edition of the text. We use supervised classification methods to predict storytellers based on the stories they tell, confirming the difficulty of the task, and demonstrate that topic modeling can extract thematic storyteller "profiles."

Scheduled Sampling Based on Decoding Steps for Neural Machine Translation

Downloads

Next from EMNLP 2021

Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation

Similar lecture

Subword Mapping and Anchoring across Languages