Dominican Republic

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.

EMNLP 2021

Enlivening Redundant Heads in Multi-head Self-attention for 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

Neural Machine Translation (NMT) has shown a strong ability to utilize local context to disambiguate the meaning of words. However, it remains a challenge for NMT to leverage broader context information like topics. In this paper, we propose heterogeneous ways of embedding topic information at the sentence level into an NMT model to improve translation performance. Specifically, the topic information can be incorporated as pre-encoder topic embedding, post-encoder topic embedding, and decoder topic embedding to increase the likelihood of selecting target words from the same topic of the source sentence. Experimental results show that NMT models with the proposed topic knowledge embedding outperform the baselines on the English -> German and English -> French translation tasks.

Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings

Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity. To this end, we propose an algorithm VoCap to determine the desired vocabulary capacity of each language. However, increasing the vocabulary size significantly slows down the pre-training speed. In order to address the issues, we propose k-NN-based target sampling to accelerate the expensive softmax. Our experiments show that the multilingual vocabulary learned with VoCap benefits cross-lingual language model pre-training. Moreover, k-NN-based target sampling mitigates the side-effects of increasing the vocabulary size while achieving comparable performance and faster pre-training speed. The code and the pretrained multilingual vocabularies are available at https://github.com/bozheng-hit/VoCapXLM.

Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training

Recent research questions the importance of the dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. In this paper, we push further in this research line and propose a novel substitute mechanism for self-attention: Recurrent AtteNtion (RAN). RAN directly learns attention weights without any token-to-token interaction and further improves their capacity by layer-to-layer interaction.

Recurrent Attention for Neural Machine Translation

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

Automatic detection of stylistic devices is an important tool for literary studies, e.g., for stylometric analysis or argument mining. A particularly striking device is the rhetorical figure called chiasmus, which involves the inversion of semantically or syntactically related words. Existing works focus on a special case of chiasmi that involve identical words in an A B B A pattern, so-called antimetaboles. In contrast, we propose an approach targeting the more general and challenging case A B B' A', where the words A, A' and B, B' constituting the chiasmus do not need to be identical but just related in meaning. To this end, we generalize the established candidate phrase mining strategy from antimetaboles to general chiasmi and propose novel features based on word embeddings and lemmata for capturing both semantic and syntactic information. These features serve as input for a logistic regression classifier, which learns to distinguish between rhetorical chiasmi and coincidental chiastic word orders without special meaning. We evaluate our approach on two datasets consisting of classical German dramas, four texts with annotated chiasmi and 500 unannotated texts. Compared to previous methods for chiasmus detection, our novel features improve the average precision from 17% to 28% and the precision among the top 100 results from 13% to 35%.

Data-Driven Detection of General Chiasmi Using Lexical and Semantic Features

Tracing the influence of individuals or groups
in social networks is an increasingly popular
task in sociolinguistic studies. While methods
to determine someone’s influence in shortterm
contexts (e.g., social media, on-line political
debates) are widespread, influence in longterm
contexts is less investigated and may be
harder to capture. We study the diffusion of
scientific terms in an English diachronic scientific
corpus, applying Hawkes Processes to
capture the role of individual scientists as "influencers"
or "influencees" in the diffusion of
new concepts. Our findings on two major
scientific discoveries in chemistry and astronomy
of the 18th century reveal that modelling
both the introduction and diffusion of scientific
terms in a historical corpus as Hawkes Processes
allows detecting patterns of influence
between authors on a long-term scale.

The diffusion of scientific terms -- tracing individuals' influence in the history of science for English

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."

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

Downloads

Next from EMNLP 2021

Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings

Similar lecture

Translation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation