著者

Ryo Fukuda Katsuhito Sudoh Satoshi Nakamura

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.29, no.2, pp.344-366, 2022 (Released:2022-06-15)

参考文献数

42

---

Recent studies consider knowledge distillation as a promising method for speech translation (ST) using end-to-end models. However, its usefulness in cascade ST with automatic speech recognition (ASR) and machine translation (MT) models has not yet been clarified. An ASR output typically contains speech recognition errors. An MT model trained only on human transcripts performs poorly on error-containing ASR results. Thus, it should be trained considering the presence of ASR errors during inference. In this paper, we propose using knowledge distillation for training of the MT model for cascade ST to achieve robustness against ASR errors. We distilled knowledge from a teacher model based on human transcripts to a student model based on erroneous transcriptions. Our experimental results showed that the proposed method improves the translation performance on erroneous transcriptions. Further investigation by combining knowledge distillation and fine-tuning consistently improved the performance on two different datasets: MuST-C English--Italian and Fisher Spanish--English.

著者

Kosuke Takahashi Katsuhito Sudoh Satoshi Nakamura

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.29, no.1, pp.3-22, 2022 (Released:2022-03-15)

参考文献数

23

被引用文献数

1

---

As the performance of machine translation has improved, the need for a human-like automatic evaluation metric has been increasing. The use of multiple reference translations against a system translation (a hypothesis) has been adopted as a strategy to improve the performance of such evaluation metrics. However, preparing multiple references is highly expensive and impractical. In this study, we propose an automatic evaluation method for machine translation that uses source sentences as additional pseudo-references. The proposed method evaluates a translation hypothesis via regression to assign a real-valued score. The model takes the paired source, reference, and hypothesis sentences together as input. A pre-trained large-scale cross-lingual language model encodes the input to sentence vectors, with which the model predicts a human evaluation score. The results of experiments show that our proposed method exhibited stably higher correlation with human judgements than baseline methods that solely depend on hypothesis and reference sentences, especially when the hypotheses were very high- or low-quality translations.

著者

Shohei Higashiyama Masao Utiyama Eiichiro Sumita Masao Ideuchi Yoshiaki Oida Yohei Sakamoto Isaac Okada Yuji Matsumoto

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.27, no.3, pp.499-530, 2020-09-15 (Released:2020-12-15)

参考文献数

54

被引用文献数

2

---

Although limited effort has been devoted to exploring neural models in Japanese word segmentation, much effort has been actively applied to Chinese word segmentation because of the ability to minimize effort in feature engineering. In this work, we propose a character-based neural model that makes joint use of word information useful for disambiguating word boundaries. For each character in a sentence, our model uses an attention mechanism to estimate the importance of multiple candidate words that contain the character. Experimental results show that learning attention to proper words leads to accurate segmentations and that our model achieves better performance than existing statistical and neural models on both in-domain and cross-domain Japanese word segmentation datasets.

著者

Van-Hien Tran Hiroki Ouchi Hiroyuki Shindo Yuji Matsumoto Taro Watanabe

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.30, no.2, pp.304-329, 2023 (Released:2023-06-15)

参考文献数

52

---

Zero-shot relation extraction aims to recognize (new) unseen relations that cannot be observed during training. Due to this point, recognizing unseen relations with no corresponding labeled training instances is a challenging task. Recognizing an unseen relation between two entities in an input instance at the testing time, a model needs to grasp the semantic relationship between the instance and all unseen relations to make a prediction. This study argues that enhancing the semantic correlation between instances and relations is key to effectively solving the zero-shot relation extraction task. A new model entirely devoted to this goal through three main aspects was proposed: learning effective relation representation, designing purposeful mini-batches, and binding two-way semantic consistency. Experimental results on two benchmark datasets demonstrate that our approach significantly improves task performance and achieves state-of-the-art results. Our source code and data are publicly available.

著者

Michael Paul Andrew Finch Eiichiro Sumita

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.20, no.4, pp.563-583, 2013-09-13 (Released:2013-12-12)

参考文献数

29

---

Recent research on multilingual statistical machine translation (SMT) focuses on the usage of pivot languages in order to overcome resource limitations for certain language pairs. This paper proposes a new method to translate a dialect language into a foreign language by integrating transliteration approaches based on Bayesian alignment (BA) models with pivot-based SMT approaches. The advantages of the proposed method with respect to standard SMT approaches are threefold: (1) it uses a standard language as the pivot language and acquires knowledge about the relation between dialects and a standard language automatically, (2) it avoids segmentation mismatches between the input and the translation model by mapping the character sequences of the dialect language to the word segmentation of the standard language, and (3) it reduces the translation task complexity by using monotone decoding techniques. Experiment results translating five Japanese dialects (Kumamoto, Kyoto, Nagoya, Okinawa, Osaka) into four Indo-European languages (English, German, Russian, Hindi) and two Asian languages (Chinese, Korean) revealed that the proposed method improves the translation quality of dialect translation tasks and outperforms standard pivot translation approaches concatenating SMT engines for the majority of the investigated language pairs.

著者

Kazuaki Hanawa Ryo Nagata Kentaro Inui

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.29, no.3, pp.901-924, 2022 (Released:2022-09-15)

参考文献数

26

---

Feedback comment generation is the task of generating explanatory notes for language learners. Although various generation techniques are available, little is known about which methods are appropriate for this task. Nagata (2019) demonstrates the effectiveness of neural-retrieval-based methods in generating feedback comments for preposition use. Retrieval-based methods have limitations in that they can only output feedback comments existing in the given training data. Besides, feedback comments can be made on other grammatical and writing items other than preposition use, which has not yet been addressed. To shed light on these points, we investigate a wider range of methods for generating various types of feedback comments in this study. Our close analysis of the features of the task leads us to investigate three different architectures for comment generation: (i) a neural-retrieval-based method as a baseline, (ii) a pointer-generator-based generation method as a neural seq2seq method, (iii) a retrieve-and-edit method, a hybrid of (i) and (ii). Intuitively, the pointer-generator should outperform neural-retrieval, and retrieve-and-edit should perform the best. However, in our experiments, this expectation is completely overturned. We closely analyze the results to reveal the major causes of these counter-intuitive results and report on our findings from the experiments, which will lead to further developments of feedback comment generation.

著者

Raj Dabre

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.29, no.1, pp.230-236, 2022 (Released:2022-03-15)

著者

Yiran Wang Hiroyuki Shindo Yuji Matsumoto Taro Watanabe

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.29, no.1, pp.23-52, 2022 (Released:2022-03-15)

参考文献数

44

被引用文献数

2

---

This paper presents a novel method for nested named entity recognition. As a layered method, our method extends the prior second-best path recognition method by explicitly excluding the influence of the best path. Our method maintains a set of hidden states at each time step and selectively leverages them to build a different potential function for recognition at each level. In addition, we demonstrate that recognizing innermost entities first results in better performance than the conventional outermost entities first scheme. We provide extensive experimental results on ACE2004, ACE2005, GENIA, and NNE datasets to show the effectiveness and efficiency of our proposed method.

著者

Manabu Okumura Kiyoaki Shirai Kanako Komiya Hikaru Yokono

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.18, no.3, pp.293-307, 2011 (Released:2011-10-04)

参考文献数

12

被引用文献数

4 4

---

An overview of the SemEval-2 Japanese WSD task is presented. The new characteristics of our task are (1) the task will use the first balanced Japanese sense-tagged corpus, and (2) the task will take into account not only the instances that have a sense in the given set but also the instances that have a sense that cannot be found in the set. It is a lexical sample task, and word senses are defined according to a Japanese dictionary, the Iwanami Kokugo Jiten. This dictionary and a training corpus were distributed to participants. The number of target words was 50, with 22 nouns, 23 verbs, and 5 adjectives. Fifty instances of each target word were provided, consisting of a total of 2,500 instances for the evaluation. Nine systems from four organizations participated in the task.

著者

Arseny Tolmachev Daisuke Kawahara Sadao Kurohashi

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.27, no.1, pp.89-132, 2020-03-15 (Released:2020-06-15)

参考文献数

34

被引用文献数

2 3

---

An NLP tool is practical when it is fast in addition to having high accuracy. We describe the architecture and the used methods to achieve 250× analysis speed improvement on the Juman++ morphological analyzer together with slight accuracy improvements. This information should be useful for implementors of high-performance NLP and machine-learning based software.

著者

Yui Oka Katsuhito Sudoh Satoshi Nakamura

出版者

The Association for Natural Language Processing

雑誌

自然言語処理 (ISSN:13407619)

巻号頁・発行日

vol.28, no.3, pp.778-801, 2021 (Released:2021-09-15)

参考文献数

25

---

Neural machine translation often suffers from an under-translation problem owing to its limited modeling of the output sequence lengths. In this study, we propose a novel approach to training a Transformer model using length constraints based on length-aware positional encoding (PE). Because length constraints with exact target sentence lengths degrade the translation performance, we add a random perturbation with a uniform distribution within a certain range to the length constraints in the PE during the training. In the inference step, we predicted the output lengths from the input sequences using a length prediction model based on a large-scale pre-trained language model. In Japanese-to-English and English-to-Japanese translation, experimental results show that the proposed perturbation injection improves the robustness of the length prediction errors, particularly within a certain range.