Spain

Soft contextualized data augmentation is a recent method that replaces one-hot representation of words with soft posterior distributions of an external language model, smoothing the input of neural machine translation systems. Label smoothing is another effective method that penalizes over-confident model outputs by discounting some probability mass from the true target word, smoothing the output of neural machine translation systems. Having the benefit of updating all word vectors in each optimization step and better regularizing the models, the two smoothing methods are shown to bring significant improvements in translation performance. In this work, we study how to best combine the methods and stack the improvements. Specifically, we vary the prior distributions to smooth with, the hyperparameters that control the smoothing strength, and the token selection procedures. We conduct extensive experiments on small datasets, evaluate the recipes on larger datasets, and examine the implications when back-translation is further used. Our results confirm cumulative improvements when input and output smoothing are used in combination, giving up to +1.9 BLEU scores on standard machine translation tasks, and reveal reasons why these smoothing methods should be preferred.

COLING 2020

Unifying Input and Output Smoothing in Neural Machine Translation

soft contextualized data augmentation

label smoothing

machine translation

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

poster

Recently, many KB-to-text generation tasks have been proposed to bridge the gap between knowledge bases and natural language by directly converting a group of knowledge base triples into human-readable sentences. However, most of the existing models suffer from the off-topic problem, namely, the models are prone to generate some unrelated clauses that are somehow involved with certain input terms regardless of the given input data. This problem seriously degrades the quality of the generation results. In this paper, we propose a novel dynamic topic tracker for solving this problem. Different from existing models, our proposed model learns a global hidden representation for topics and recognizes the corresponding topic during each generation step. The recognized topic is used as additional information to guide the generation process and thus alleviates the off-topic problem.
The experimental results show that our proposed model can enhance the performance of sentence generation and the off-topic problem is significantly mitigated.

Dynamic Topic Tracker for KB-to-Text Generation

•Emotion prediction is a critical task in the field of Natural Language Processing (NLP).
•Code-Mixing, a progeny of multilingualism is a way in which multilingual people express themselves on social media by using linguistics units from different languages within a sentence or speech context.
•There has been work done on code-mixed social media corpus but not on emotion
prediction of Kannada-English code-mixed Twitter data.
• In this paper, we analyze the problem of emotion prediction on corpus obtained from code-mixed Kannada-English extracted from Twitter annotated with their respective ‘Emotion’ for each tweet.

Creation of Corpus and analysis in Code-Mixed Kannada-English Twitter data for Emotion Prediction

We propose a simple and robust method, which can effectively alleviate the posterior collapse issue of VAE via timestep-wise regularisation. Our approach is generic which can be applied to any RNN-based VAE models. Our approach outperforms the state-of-art on language modelling and yields better or comparable performance on dialogue response generation.

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation

We present experiments on biomedical text simplification in French. We use two kinds of corpora -- parallel sentences extracted from existing health comparable corpora in French and WikiLarge corpus translated from English to French -- and a lexicon that associates medical terms with paraphrases. Then, we train neural models on these parallel corpora using different ratios of general and specialized sentences. We evaluate the results with BLEU, SARI and Kandel scores. The results point out that little specialized data helps significantly the simplification.

French Biomedical Text Simplification: When Small and Precise Helps

We present a method for completing multilingual translation dictionaries. Our probabilistic approach can synthesize new word forms, allowing it to operate in settings where correct translations have not been observed in text (cf. cross-lingual embeddings). 

In addition, we propose an approximate Maximum Mutual Information (MMI) decoding objective to further improve performance in both many-to-one and one-to-one word level translation tasks where we use either multiple input languages for a single target language or more typical single language pair translation. We focus on 6 languages: French, Spanish, Italian, Portuguese, Romanian, and Turkish.


Neural Transduction for Multilingual Lexical Translation

Distantly Supervised Relation Extraction (DSRE) has proven to be effective to find relational facts from texts, but it still suffers from two main problems: the wrong labeling problem and the long-tail problem. Most of the existing approaches address these two problems through flat classification, which lacks hierarchical information of relations. To leverage the informative relation hierarchies, we formulate DSRE as a hierarchical classification task and propose a novel hierarchical classification framework, which extracts the relation in a top-down manner. Specifically, in our proposed framework, 1) we use a hierarchically-refined representation method to achieve hierarchy-specific representation; 2) a top-down classification strategy is introduced instead of training a set of local classifiers. The experiments on NYT dataset demonstrate that our approach significantly outperforms other state-of-the-art approaches, especially for the long-tail problem.

ToHRE: A Top-Down Classification Strategy with Hierarchical Bag
Representation for Distantly Supervised Relation Extraction

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models. Few works explore the potential of deep contextualized knowledge representation when injecting knowledge. In this work, we propose the Contextualized Language and Knowledge Embedding (CoLAKE), which jointly learns contextualized representation for both language and knowledge with the extended MLM objective. Instead of injecting only entity embeddings, CoLAKE extracts the knowledge context of an entity from large-scale knowledge bases. To handle the heterogeneity of knowledge context and language context, we integrate them in a unified data structure, word-knowledge graph (WK graph). CoLAKE is pre-trained on large-scale WK graphs with the modified Transformer encoder. We conduct experiments on knowledge-driven tasks, knowledge probing tasks, and language understanding tasks. Experimental results show that CoLAKE outperforms previous counterparts on most of the tasks.

CoLAKE: Contextualized Language and Knowledge Embedding

Research on document-level Neural Machine Translation (NMT) models has attracted increasing attention in recent years. Although the proposed works has proved that the inter-sentence information is helpful for improving the performance of the NMT models, what information should be regarded as context remains ambiguous. To solve this problem, we proposed a novel cache-based document-level NMT models which conducts dynamic caching guided by theme-rheme information. The experiments on NIST evaluation sets demonstrate that our proposed model achieves substantial improvements over the state-of-the-art baseline NMT models. As far as we know, we are the first to introduce theme-rheme theory into the field of machine translation.

A Document-Level Neural Machine Translation Model with Dynamic Caching
Guided by Theme-Rheme Information

Regardless of different word embedding and hidden layer structures of the neural architectures that are used in named entity recognition, a conditional random field layer is commonly used for the output. This work proposes to use a neural language model as an alternative to the conditional random field layer, which is more flexible for the size of the corpus. Experimental results show that the proposed system has a significant advantage in terms of training speed.

Neural Language Modeling for Named Entity Recognition

Most recent works in the field of grammatical error correction (GEC) rely on neural machine translation-based models. Although these models boast impressive performance, they require a massive amount of data to properly train. Furthermore, NMT-based systems treat GEC purely as a translation task and overlook the editing aspect of it. In this work we propose a heterogeneous approach to Chinese GEC, composed of a NMT-based model, a sequence editing model, and a spell checker. Our methodology not only achieves a new state-of-the-art performance for Chinese GEC, but also does so without relying on data augmentation or GEC-specific architecture changes. We further experiment with all possible configurations of our system with respect to model composition order and number of rounds of correction. A detailed analysis of each model and their contributions to the correction process is performed by adapting the ERRANT scorer to be able to score Chinese sentences.

Unifying Input and Output Smoothing in Neural Machine Translation

Downloads

Next from COLING 2020

Dynamic Topic Tracker for KB-to-Text Generation

Similar lecture

PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents

Unifying Input and Output Smoothing in 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 COLING 2020

Dynamic Topic Tracker for KB-to-Text Generation

Similar lecture

PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents

Downloads