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 genera
lly 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. The codes and pre-trained models will be made publicly available.
In Visual Question Answering (VQA), existing bilinear methods focus on the interaction between images and questions. As a result, the answers are either spliced into the questions or utilized as labels only for classification. On the other hand, tril
inear models such as the CTI model efficiently utilize the inter-modality information between answers, questions, and images, while ignoring intra-modality information. Inspired by this observation, we propose a new trilinear interaction framework called MIRTT (Learning Multimodal Interaction Representations from Trilinear Transformers), incorporating the attention mechanisms for capturing inter-modality and intra-modality relationships. Moreover, we design a two-stage workflow where a bilinear model reduces the free-form, open-ended VQA problem into a multiple-choice VQA problem. Furthermore, to obtain accurate and generic multimodal representations, we pre-train MIRTT with masked language prediction. Our method achieves state-of-the-art performance on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperforms bilinear baselines on the VQA-2.0, TDIUC and GQA datasets.
Several NLP tasks need the effective repre-sentation of text documents.Arora et al.,2017 demonstrate that simple weighted aver-aging of word vectors frequently outperformsneural models. SCDV (Mekala et al., 2017)further extends this from sentences to
docu-ments by employing soft and sparse cluster-ing over pre-computed word vectors. How-ever, both techniques ignore the polysemyand contextual character of words.In thispaper, we address this issue by proposingSCDV+BERT(ctxd), a simple and effective un-supervised representation that combines con-textualized BERT (Devlin et al., 2019) basedword embedding for word sense disambigua-tion with SCDV soft clustering approach. Weshow that our embeddings outperform origi-nal SCDV, pre-train BERT, and several otherbaselines on many classification datasets. Wealso demonstrate our embeddings effective-ness on other tasks, such as concept match-ing and sentence similarity.In addition,we show that SCDV+BERT(ctxd) outperformsfine-tune BERT and different embedding ap-proaches in scenarios with limited data andonly few shots examples.
Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural networ
k (GNN), for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, comparing with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels.
Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle
relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.
Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models susceptible to degrad
ation from common types of noise and variation. Motivated by the robustness of human language processing, we propose the use of visual text representations, which dispense with a finite set of text embeddings in favor of continuous vocabularies created by processing visually rendered text with sliding windows. We show that models using visual text representations approach or match performance of traditional text models on small and larger datasets. More importantly, models with visual embeddings demonstrate significant robustness to varied types of noise, achieving e.g., 25.9 BLEU on a character permuted German--English task where subword models degrade to 1.9.
Natural language processing (NLP) is often the backbone of today's systems for user interactions, information retrieval and others. Many of such NLP applications rely on specialized learned representations (e.g. neural word embeddings, topic models)
that improve the ability to reason about the relationships between documents of a corpus. Paired with the progress in learned representations, the similarity metrics used to compare representations of documents are also evolving, with numerous proposals differing in computation time or interpretability. In this paper we propose an extension to a specific emerging hybrid document distance metric which combines topic models and word embeddings: the Hierarchical Optimal Topic Transport (HOTT). In specific, we extend HOTT by using context-enhanced word representations. We provide a validation of our approach on public datasets, using the language model BERT for a document categorization task. Results indicate competitive performance of the extended HOTT metric. We furthermore apply the HOTT metric and its extension to support educational media research, with a retrieval task of matching topics in German curricula to educational textbooks passages, along with offering an auxiliary explanatory document representing the dominant topic of the retrieved document. In a user study, our explanation method is preferred over regular topic keywords.
Relational knowledge bases (KBs) are commonly used to represent world knowledge in machines. However, while advantageous for their high degree of precision and interpretability, KBs are usually organized according to manually-defined schemas, which l
imit their expressiveness and require significant human efforts to engineer and maintain. In this review, we take a natural language processing perspective to these limitations, examining how they may be addressed in part by training deep contextual language models (LMs) to internalize and express relational knowledge in more flexible forms. We propose to organize knowledge representation strategies in LMs by the level of KB supervision provided, from no KB supervision at all to entity- and relation-level supervision. Our contributions are threefold: (1) We provide a high-level, extensible taxonomy for knowledge representation in LMs; (2) Within our taxonomy, we highlight notable models, evaluation tasks, and findings, in order to provide an up-to-date review of current knowledge representation capabilities in LMs; and (3) We suggest future research directions that build upon the complementary aspects of LMs and KBs as knowledge representations.
Multilingual and cross-lingual Semantic Role Labeling (SRL) have recently garnered increasing attention as multilingual text representation techniques have become more effective and widely available. While recent work has attained growing success, re
sults on gold multilingual benchmarks are still not easily comparable across languages, making it difficult to grasp where we stand. For example, in CoNLL-2009, the standard benchmark for multilingual SRL, language-to-language comparisons are affected by the fact that each language has its own dataset which differs from the others in size, domains, sets of labels and annotation guidelines. In this paper, we address this issue and propose UniteD-SRL, a new benchmark for multilingual and cross-lingual, span- and dependency-based SRL. UniteD-SRL provides expert-curated parallel annotations using a common predicate-argument structure inventory, allowing direct comparisons across languages and encouraging studies on cross-lingual transfer in SRL. We release UniteD-SRL v1.0 at https://github.com/SapienzaNLP/united-srl.
Recently, domain shift, which affects accuracy due to differences in data between source and target domains, has become a serious issue when using machine learning methods to solve natural language processing tasks. With additional pretraining and fi
ne-tuning using a target domain corpus, pretraining models such as BERT (Bidirectional Encoder Representations from Transformers) can address this issue. However, the additional pretraining of the BERT model is difficult because it requires significant computing resources. The efficiently learning an encoder that classifies token replacements accurately (ELECTRA) pretraining model replaces the BERT pretraining method's masked language modeling with a method called replaced token detection, which improves the computational efficiency and allows the additional pretraining of the model to a practical extent. Herein, we propose a method for addressing the computational efficiency of pretraining models in domain shift by constructing an ELECTRA pretraining model on a Japanese dataset and additional pretraining this model in a downstream task using a corpus from the target domain. We constructed a pretraining model for ELECTRA in Japanese and conducted experiments on a document classification task using data from Japanese news articles. Results show that even a model smaller than the pretrained model performs equally well.
