Search

Volitionality and subject animacy are fundamental and closely related properties of an event. Their classification is challenging because it requires contextual text understanding and a huge amount of labeled data. This paper proposes a novel method that jointly learns volitionality and subject animacy at a low cost, heuristically labeling events in a raw corpus. Volitionality labels are assigned using a small lexicon of volitional and non-volitional adverbs such as “deliberately” and “accidentally”; subject animacy labels are assigned using a list of animate and inanimate nouns obtained from ontological knowledge. We then consider the problem of learning a classifier from the labeled data so that it can perform well on unlabeled events without the words used for labeling. We regard the problem as a bias reduction or unsupervised domain adaptation problem and apply the techniques. We conduct experiments with crowdsourced gold data in Japanese and English and show that our method effectively learns volitionality and subject animacy without manually labeled data.

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, multiple training procedures, the use of a large amount of data, or inefficient model architectures result in heavy computation to train a new model according to our preferred languages and domains. To resolve this issue, we introduce efficient and effective massively multilingual sentence representation learning (EMS), using cross-lingual sentence reconstruction (XTR) and sentence-level contrastive learning as training objectives. Compared with related studies, the proposed model can be efficiently trained using significantly fewer parallel sentences and GPU computation resources without depending on large-scale pre-trained models. Empirical results show that the proposed model significantly yields better or comparable results with regard to bi-text mining, zero-shot cross-lingual genre classification, and sentiment classification. Ablative analyses demonstrate the effectiveness of each component of the proposed model. We release the codes for model training and the EMS pre-trained model, which supports 62 languages (https://github.com/Mao-KU/EMS)., Comment: This work is an extension of arXiv:2105.13856. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Dravidian languages, such as Kannada and Tamil, are notoriously difficult to translate by state-of-the-art neural models. This stems from the fact that these languages are morphologically very rich as well as being low-resourced. In this paper, we focus on subword segmentation and evaluate Linguistically Motivated Vocabulary Reduction (LMVR) against the more commonly used SentencePiece (SP) for the task of translating from English into four different Dravidian languages. Additionally we investigate the optimal subword vocabulary size for each language. We find that SP is the overall best choice for segmentation, and that larger dictionary sizes lead to higher translation quality.

ニューラルネットワークに基づく係り受け解析モデルは，近年の深層学習を利用した言語処理研究の中でも大きな潮流となっている．しかしながら，こうした係り受け解析モデルを中国語などの言語に適用した際には，パイプラインモデルとして同時に用いられる単語分割や品詞タグ付けモデルの無視できない誤りによって性能が伸び悩む問題が存在する．これに対しては，単語分割・品詞タグ付けと係り受け解析の統合モデルを利用し，単語分割と構文木作成とを同時に行うことでその双方の改善が期待される．加えて，中国語においては個々の文字が固有の意味を持ち，構文解析では，文字やその組み合わせである文字列もしくは部分単語の情報が単語単位の情報と並んで本質的な役割を果たすことが期待される．本研究では，ニューラルネットワークに基づいて，単語分割と品詞タグ付け，もしくは単語分割と品詞タグ付け，係り受け解析の統合構文解析を行うモデルを提案する．また，同時に，文字列や部分単語の情報を捉えるために，文字や単語の分散表現に加えて，文字列の分散表現を利用する．, Recently, dependency parsers with neural networks have outperformed existing parsers. When these parsing models are applied to Chinese sentences, they are used in a pipeline model with word segmentation and POS tagging models. In such cases, parsing models do not work well because of word segmentation and POS tagging errors. This can be solved by joint models of word segmentation, POS tagging and dependency parsing. In addition to this, Chinese characters have their own meanings, so the meanings of characters, character strings and sub-words are as important as the meanings of words in dependency parsing. In this study, we propose a neural network-based joint word-segmentation, POS tagging and dependency parsing model in addition to a joint word-segmentation and POS tagging model. We exploit not only word and character embeddings but also character string embeddings in all our models.

Guidelines for a versatile annotation scheme for Japanese medical/clinical text. This scheme proposes clinical named entities and their relations so that training corpora for natural language processing models can be built.This guideline text is manually translated from the original Japanese version: https://doi.org/10.6084/m9.figshare.16418787.v1

Intelligent dialogue systems are expected to be a new interface between humans and machines. An ideal intelligent dialogue system should estimate the user’s internal states and incorporate the estimation results into its response appropriately. In this paper, we focus on the movie recommendation dialogues and propose a dialogue system that considers the user’s internal state. First, we build a movie recommendation dialogue system and collect dialogue data. Based on the analysis of the collected dialogue data, we model and annotate the user’s internal states in three aspects: knowledge, interest, and engagement. Second, we train the user’s internal state estimators on the dialogue corpus with the annotations of the user’s internal states. The trained estimator achieved high accuracy on the annotated corpus. Further, we design a set of rules that modify the system’s responses according to each user’s internal state. We confirmed that the response modifications based on the results of the user’s internal state estimator improve the naturalness of the system utterances in both dialogue evaluation and utterance evaluation.

In machine translation of spoken language, it is known that phenomena specific to spoken language have a negative impact on translation accuracy. Therefore, in this study, as a preprocessing step for Japanese-English translation in our university lecture translation system, we improve the translation accuracy by automatically converting spoken-style Japanese texts to written-style. First, we create a corpus consisting of Japanese transcriptions of university lectures, their conversions into written language, and the corresponding English texts. Next, we train spoken-written conversion models and Japanese-English translation models using the corpus. As a result, we show that spoken-written Japanese conversion improves the accuracy of Japanese-English translation. In addition, we quantify which phenomena affect translation accuracy and to what extent.