The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word representation in low-resource languages is notably under-aligned with that in high-resource languages in current models. To address this, we introduce a novel framework that explicitly aligns words between English and eight low-resource languages, utilizing off-the-shelf word alignment models. This framework incorporates three primary training objectives: aligned word prediction and word translation ranking, along with the widely used translation ranking. We evaluate our approach through experiments on the bitext retrieval task, which demonstrate substantial improvements on sentence embeddings in low-resource languages. In addition, the competitive performance of the proposed model across a broader range of tasks in high-resource languages underscores its practicality.

Learning multilingual sentence embeddings is a fundamental task in natural language processing. Recent trends in learning both monolingual and multilingual sentence embeddings are mainly based on contrastive learning (CL) among an anchor, one positive, and multiple negative instances. In this work, we argue that leveraging multiple positives should be considered for multilingual sentence embeddings because (1) positives in a diverse set of languages can benefit cross-lingual learning, and (2) transitive similarity across multiple positives can provide reliable structural information for learning.In order to investigate the impact of multiple positives in CL, we propose a novel approach, named MPCL, to effectively utilize multiple positive instances to improve the learning of multilingual sentence embeddings. Experimental results on various backbone models and downstream tasks demonstrate that MPCL leads to better retrieval, semantic similarity, and classification performance compared to conventional CL. We also observe that in unseen languages, sentence embedding models trained on multiple positives show better cross-lingual transfer performance than models trained on a single positive instance.

Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness. Here, to mitigate the dependence on manual data, we broaden the source of supervision by relaxing the requirement for correct, fully-aligned, and parallel sentences. Specifically, we make noisy, partially aligned, and non-parallel paragraphs in this paper. We then use such a large-scale weakly-supervised dataset for word alignment pre-training via span prediction. Extensive experiments with various settings empirically demonstrate that our approach, which is named WSPAlign, is an effective and scalable way to pre-train word aligners without manual data. When fine-tuned on standard benchmarks, WSPAlign has set a new state of the art by improving upon the best supervised baseline by 3.3 6.1 points in F1 and 1.5 6.1 points in AER. Furthermore, WSPAlign also achieves competitive performance compared with the corresponding baselines in few-shot, zero-shot and cross-lingual tests, which demonstrates that WSPAlign is potentially more practical for low-resource languages than existing methods.

We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e.g., M-BERT). It leverages the multilingual nature of Wikidata: entities in multiple languages representing the same concept are defined with a unique identifier. This enables entities described in multiple languages to be represented using shared embeddings. A model trained on entity features in a resource-rich language can thus be directly applied to other languages. Our experimental results on cross-lingual topic classification (using the MLDoc and TED-CLDC datasets) and entity typing (using the SHINRA2020-ML dataset) show that the proposed model consistently outperforms state-of-the-art models.

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong indicator of text semantics and thus should provide rich training signals for sentence embeddings; (2) entities are defined independently of languages and thus offer useful cross-lingual alignment supervision. We evaluate EASE against other unsupervised models both in monolingual and multilingual settings. We show that EASE exhibits competitive or better performance in English semantic textual similarity (STS) and short text clustering (STC) tasks and it significantly outperforms baseline methods in multilingual settings on a variety of tasks. Our source code, pre-trained models, and newly constructed multi-lingual STC dataset are available at https://github.com/studio-ousia/ease.

We investigate what kind of structural knowledge learned in neural network encoders is transferable to processing natural language. We design artificial languages with structural properties that mimic natural language, pretrain encoders on the data, and see how much performance the encoder exhibits on downstream tasks in natural language.Our experimental results show that pretraining with an artificial language with a nesting dependency structure provides some knowledge transferable to natural language.A follow-up probing analysis indicates that its success in the transfer is related to the amount of encoded contextual information and what is transferred is the knowledge of position-aware context dependence of language.Our results provide insights into how neural network encoders process human languages and the source of cross-lingual transferability of recent multilingual language models.

Recent studies have shown that multilingual pretrained language models can be effectively improved with cross-lingual alignment information from Wikipedia entities. However, existing methods only exploit entity information in pretraining and do not explicitly use entities in downstream tasks. In this study, we explore the effectiveness of leveraging entity representations for downstream cross-lingual tasks. We train a multilingual language model with 24 languages with entity representations and showthe model consistently outperforms word-based pretrained models in various cross-lingual transfer tasks. We also analyze the model and the key insight is that incorporating entity representations into the input allows us to extract more language-agnostic features. We also evaluate the model with a multilingual cloze prompt task with the mLAMA dataset. We show that entity-based prompt elicits correct factual knowledge more likely than using only word representations.

Unsupervised cross-lingual word embedding(CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingual corpora. This method relies on the assumption that the two embedding spaces are structurally similar, which does not necessarily hold true in general. In this paper, we argue that using a pseudo-parallel corpus generated by an unsupervised machine translation model facilitates the structural similarity of the two embedding spaces and improves the quality of CLWEs in the unsupervised mapping method. We show that our approach outperforms other alternative approaches given the same amount of data, and, through detailed analysis, we show that data augmentation with the pseudo data from unsupervised machine translation is especially effective for mapping-based CLWEs because (1) the pseudo data makes the source and target corpora (partially) parallel; (2) the pseudo data contains information on the original language that helps to learn similar embedding spaces between the source and target languages.

Placeholder translation systems enable the users to specify how a specific phrase is translated in the output sentence. The system is trained to output special placeholder tokens and the user-specified term is injected into the output through the context-free replacement of the placeholder token. However and this approach could result in ungrammatical sentences because it is often the case that the specified term needs to be inflected according to the context of the output and which is unknown before the translation. To address this problem and we propose a novel method of placeholder translation that can inflect specified terms according to the grammatical construction of the output sentence. We extend the seq2seq architecture with a character-level decoder that takes the lemma of a user-specified term and the words generated from the word-level decoder to output a correct inflected form of the lemma. We evaluate our approach with a Japanese-to-English translation task in the scientific writing domain and and show our model can incorporate specified terms in a correct form more successfully than other comparable models.

For Japanese-to-English translation, zero pronouns in Japanese pose a challenge, since the model needs to infer and produce the corresponding pronoun in the target side of the English sentence. However, although fully resolving zero pronouns often needs discourse context, in some cases, the local context within a sentence gives clues to the inference of the zero pronoun. In this study, we propose a data augmentation method that provides additional training signals for the translation model to learn correlations between local context and zero pronouns. We show that the proposed method significantly improves the accuracy of zero pronoun translation with machine translation experiments in the conversational domain.

Existing approaches to mapping-based cross-lingual word embeddings are based on the assumption that the source and target embedding spaces are structurally similar. The structures of embedding spaces largely depend on the co-occurrence statistics of each word, which the choice of context window determines. Despite this obvious connection between the context window and mapping-based cross-lingual embeddings, their relationship has been underexplored in prior work. In this work, we provide a thorough evaluation, in various languages, domains, and tasks, of bilingual embeddings trained with different context windows. The highlight of our findings is that increasing the size of both the source and target window sizes improves the performance of bilingual lexicon induction, especially the performance on frequent nouns.

Traditional model training for sentence generation employs cross-entropy loss as the loss function. While cross-entropy loss has convenient properties for supervised learning, it is unable to evaluate sentences as a whole, and lacks flexibility. We present the approach of training the generation model using the estimated semantic similarity between the output and reference sentences to alleviate the problems faced by the training with cross-entropy loss. We use the BERT-based scorer fine-tuned to the Semantic Textual Similarity (STS) task for semantic similarity estimation, and train the model with the estimated scores through reinforcement learning (RL). Our experiments show that reinforcement learning with semantic similarity reward improves the BLEU scores from the baseline LSTM NMT model.

A major obstacle in reinforcement learning-based sentence generation is the large action space whose size is equal to the vocabulary size of the target-side language. To improve the efficiency of reinforcement learning, we present a novel approach for reducing the action space based on dynamic vocabulary prediction. Our method first predicts a fixed-size small vocabulary for each input to generate its target sentence. The input-specific vocabularies are then used at supervised and reinforcement learning steps, and also at test time. In our experiments on six machine translation and two image captioning datasets, our method achieves faster reinforcement learning (~2.7x faster) with less GPU memory (~2.3x less) than the full-vocabulary counterpart. We also show that our method more effectively receives rewards with fewer iterations of supervised pre-training.

Neural machine translation (NMT) has shown great success as a new alternative to the traditional Statistical Machine Translation model in multiple languages. Early NMT models are based on sequence-to-sequence learning that encodes a sequence of source words into a vector space and generates another sequence of target words from the vector. In those NMT models, sentences are simply treated as sequences of words without any internal structure. In this article, we focus on the role of the syntactic structure of source sentences and propose a novel end-to-end syntactic NMT model, which we call a tree-to-sequence NMT model, extending a sequence-to-sequence model with the source-side phrase structure. Our proposed model has an attention mechanism that enables the decoder to generate a translated word while softly aligning it with phrases as well as words of the source sentence. We have empirically compared the proposed model with sequence-to-sequence models in various settings on Chinese-to-Japanese and English-to-Japanese translation tasks. Our experimental results suggest that the use of syntactic structure can be beneficial when the training data set is small, but is not as effective as using a bi-directional encoder. As the size of training data set increases, the benefits of using a syntactic tree tends to diminish.

This paper presents a novel neural machine translation model which jointly learns translation and source-side latent graph representations of sentences. Unlike existing pipelined approaches using syntactic parsers, our end-to-end model learns a latent graph parser as part of the encoder of an attention-based neural machine translation model, and thus the parser is optimized according to the translation objective. In experiments, we first show that our model compares favorably with state-of-the-art sequential and pipelined syntax-based NMT models. We also show that the performance of our model can be further improved by pre-training it with a small amount of treebank annotations. Our final ensemble model significantly outperforms the previous best models on the standard English-to-Japanese translation dataset.

Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax and semantics would benefit each other by being trained in a single model. We introduce a joint many-task model together with a strategy for successively growing its depth to solve increasingly complex tasks. Higher layers include shortcut connections to lower-level task predictions to reflect linguistic hierarchies. We use a simple regularization term to allow for optimizing all model weights to improve one task’s loss without exhibiting catastrophic interference of the other tasks. Our single end-to-end model obtains state-of-the-art or competitive results on five different tasks from tagging, parsing, relatedness, and entailment tasks.

There has been relatively little attention to incorporating linguistic prior to neural machine translation. Much of the previous work was further constrained to considering linguistic prior on the source side. In this paper, we propose a hybrid model, called NMT+RNNG, that learns to parse and translate by combining the recurrent neural network grammar into the attention-based neural machine translation. Our approach encourages the neural machine translation model to incorporate linguistic prior during training, and lets it translate on its own afterward. Extensive experiments with four language pairs show the effectiveness of the proposed NMT+RNNG.

This paper describes our UT-KAY system that participated in the Workshop on Asian Translation 2016. Based on an Attention-based Neural Machine Translation (ANMT) model, we build our system by incorporating a domain adaptation method for multiple domains and an attention-based unknown word replacement method. In experiments, we verify that the attention-based unknown word replacement method is effective in improving translation scores in Chinese-to-Japanese machine translation. We further show results of manual analysis on the replaced unknown words.

This paper reports our systems (UT-AKY) submitted in the 3rd Workshop of Asian Translation 2016 (WAT’16) and their results in the English-to-Japanese translation task. Our model is based on the tree-to-sequence Attention-based NMT (ANMT) model proposed by Eriguchi et al. (2016). We submitted two ANMT systems: one with a word-based decoder and the other with a character-based decoder. Experimenting on the English-to-Japanese translation task, we have confirmed that the character-based decoder can cover almost the full vocabulary in the target language and generate translations much faster than the word-based model.

In recent years there has been a surge of interest in the natural language prosessing related to the real world, such as symbol grounding, language generation, and nonlinguistic data search by natural language queries. In order to concentrate on language ambiguities, we propose to use a well-defined “real world,” that is game states. We built a corpus consisting of pairs of sentences and a game state. The game we focus on is shogi (Japanese chess). We collected 742,286 commentary sentences in Japanese. They are spontaneously generated contrary to natural language annotations in many image datasets provided by human workers on Amazon Mechanical Turk. We defined domain specific named entities and we segmented 2,508 sentences into words manually and annotated each word with a named entity tag. We describe a detailed definition of named entities and show some statistics of our game commentary corpus. We also show the results of the experiments of word segmentation and named entity recognition. The accuracies are as high as those on general domain texts indicating that we are ready to tackle various new problems related to the real world.

Many systems have been developed in the past few years to assist researchers in the discovery of knowledge published as English text, for example in the PubMed database. At the same time, higher level collective knowledge is often published using a graphical notation representing all the entities in a pathway and their interactions. We believe that these pathway visualizations could serve as an effective user interface for knowledge discovery if they can be linked to the text in publications. Since the graphical elements in a Pathway are of a very different nature than their corresponding descriptions in English text, we developed a prototype system called PathText. The goal of PathText is to serve as a bridge between these two different representations. In this paper, we first describe the overall architecture and the interfaces of the PathText system, and then provide some details about the core Text Mining components.