Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities. In the zero-shot transfer setting, only English training data is used, and the fine-tuned model i
s evaluated on another target language. While this works surprisingly well, substantial variance has been observed in target language performance between different fine-tuning runs, and in the zero-shot setup, no target-language development data is available to select among multiple fine-tuned models. Prior work has relied on English dev data to select among models that are fine-tuned with different learning rates, number of steps and other hyperparameters, often resulting in suboptimal choices. In this paper, we show that it is possible to select consistently better models when small amounts of annotated data are available in auxiliary pivot languages. We propose a machine learning approach to model selection that uses the fine-tuned model's own internal representations to predict its cross-lingual capabilities. In extensive experiments we find that this method consistently selects better models than English validation data across twenty five languages (including eight low-resource languages), and often achieves results that are comparable to model selection using target language development data.
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can b
e infeasible because of the labeling cost, task characteristics, and privacy concerns. This paper proposes an alternative solution that uses only task-independent word embeddings of high-resource languages and bilingual dictionaries. First, we construct a dictionary-based heterogeneous graph (DHG) from bilingual dictionaries. This opens the possibility to use graph neural networks for cross-lingual transfer. The remaining challenge is the heterogeneity of DHG because multiple languages are considered. To address this challenge, we propose dictionary-based heterogeneous graph neural network (DHGNet) that effectively handles the heterogeneity of DHG by two-step aggregations, which are word-level and language-level aggregations. Experimental results demonstrate that our method outperforms pretrained models even though it does not access to large corpora. Furthermore, it can perform well even though dictionaries contain many incorrect translations. Its robustness allows the usage of a wider range of dictionaries such as an automatically constructed dictionary and crowdsourced dictionary, which are convenient for real-world applications.
Dense retrieval has shown great success for passage ranking in English. However, its effectiveness for non-English languages remains unexplored due to limitation in training resources. In this work, we explore different transfer techniques for docume
nt ranking from English annotations to non-English languages. Our experiments reveal that zero-shot model-based transfer using mBERT improves search quality. We find that weakly-supervised target language transfer is competitive compared to generation-based target language transfer, which requires translation models.
This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify pre-trained models' transferability, we test the pre-trained models on
text classification tasks with meanings of tokens mismatches, and real-world non-text token sequence classification data, including amino acid, DNA, and music. We find that even on non-text data, the models pre-trained on text converge faster, perform better than the randomly initialized models, and only slightly worse than the models using task-specific knowledge. We also find that the representations of the text and non-text pre-trained models share non-trivial similarities.
Many recent works use consistency regularisation' to improve the generalisation of fine-tuned pre-trained models, both multilingual and English-only. These works encourage model outputs to be similar between a perturbed and normal version of the inpu
t, usually via penalising the Kullback--Leibler (KL) divergence between the probability distribution of the perturbed and normal model. We believe that consistency losses may be implicitly regularizing the loss landscape. In particular, we build on work hypothesising that implicitly or explicitly regularizing trace of the Fisher Information Matrix (FIM), amplifies the implicit bias of SGD to avoid memorization. Our initial results show both empirically and theoretically that consistency losses are related to the FIM, and show that the flat minima implied by a small trace of the FIM improves performance when fine-tuning a multilingual model on additional languages. We aim to confirm these initial results on more datasets, and use our insights to develop better multilingual fine-tuning techniques.
For programmers, learning the usage of APIs (Application Programming Interfaces) of a software library is important yet difficult. API recommendation tools can help developers use APIs by recommending which APIs to be used next given the APIs that ha
ve been written. Traditionally, language models such as N-gram are applied to API recommendation. However, because the software libraries keep changing and new libraries keep emerging, new APIs are common. These new APIs can be seen as OOV (out of vocabulary) words and cannot be handled well by existing API recommendation approaches due to the lack of training data. In this paper, we propose APIRecX, the first cross-library API recommendation approach, which uses BPE to split each API call in each API sequence and pre-trains a GPT based language model. It then recommends APIs by fine-tuning the pre-trained model. APIRecX can migrate the knowledge of existing libraries to a new library, and can recommend APIs that are previously regarded as OOV. We evaluate APIRecX on six libraries and the results confirm its effectiveness by comparing with two typical API recommendation approaches.
Cross-lingual word embeddings (CLWEs) have proven indispensable for various natural language processing tasks, e.g., bilingual lexicon induction (BLI). However, the lack of data often impairs the quality of representations. Various approaches requiri
ng only weak cross-lingual supervision were proposed, but current methods still fail to learn good CLWEs for languages with only a small monolingual corpus. We therefore claim that it is necessary to explore further datasets to improve CLWEs in low-resource setups. In this paper we propose to incorporate data of related high-resource languages. In contrast to previous approaches which leverage independently pre-trained embeddings of languages, we (i) train CLWEs for the low-resource and a related language jointly and (ii) map them to the target language to build the final multilingual space. In our experiments we focus on Occitan, a low-resource Romance language which is often neglected due to lack of resources. We leverage data from French, Spanish and Catalan for training and evaluate on the Occitan-English BLI task. By incorporating supporting languages our method outperforms previous approaches by a large margin. Furthermore, our analysis shows that the degree of relatedness between an incorporated language and the low-resource language is critically important.
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.
Aspect terms extraction (ATE) and aspect sentiment classification (ASC) are two fundamental and fine-grained sub-tasks in aspect-level sentiment analysis (ALSA). In the textual analysis, joint extracting both aspect terms and sentiment polarities has
been drawn much attention due to the better applications than individual sub-task. However, in the multi-modal scenario, the existing studies are limited to handle each sub-task independently, which fails to model the innate connection between the above two objectives and ignores the better applications. Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA). Specifically, we first build an auxiliary text-image relation detection module to control the proper exploitation of visual information. Second, we adopt the hierarchical framework to bridge the multi-modal connection between MATE and MASC, as well as separately visual guiding for each sub module. Finally, we can obtain all aspect-level sentiment polarities dependent on the jointly extracted specific aspects. Extensive experiments show the effectiveness of our approach against the joint textual approaches, pipeline and collapsed multi-modal approaches.
We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously transla
tes and reconstructs an input sentence. Through sharing model parameters among different languages, our model jointly trains the word embeddings in a common cross-lingual space. We also propose to combine word and subword embeddings to make use of orthographic similarities across different languages. We base our experiments on real-world data from endangered languages, namely Yongning Na, Shipibo-Konibo, and Griko. Our experiments on bilingual lexicon induction and word alignment tasks show that our model outperforms existing methods by a large margin for most language pairs. These results demonstrate that, contrary to common belief, an encoder-decoder translation model is beneficial for learning cross-lingual representations even in extremely low-resource conditions. Furthermore, our model also works well on high-resource conditions, achieving state-of-the-art performance on a German-English word-alignment task.
