Yuto Nishida, Naoki Shikoda, Yosuke Kishinami, Ryo Fujii, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Recently, we have often observed hallucinated citations or references that do not correspond to any existing work in papers under review, preprints, or published papers.Such hallucinated citations pose a serious concern to scientific reliability.When they appear in accepted papers, they may also negatively affect the credibility of conferences.In this study, we refer to hallucinated citations as "HalluCitation" and systematically investigate their prevalence and impact.We analyze all papers published at ACL, NAACL, and EMNLP in 2024 and 2025, including main conference, Findings, and workshop papers.Our analysis reveals that over 300 papers contain at least one HalluCitation, most of which were published in 2025.Notably, half of these papers were identified at EMNLP 2025, the most recent conference, indicating that this issue is rapidly increasing.Moreover, more than 100 such papers were accepted as main conference and Findings papers at EMNLP 2025, affecting the credibility.

In generative commonsense reasoning tasks such as CommonGen, generative large language models (LLMs) compose sentences that include all given concepts.However, when focusing on instruction-following capabilities, if a prompt specifies a concept order, LLMs must generate sentences that adhere to the specified order.To address this, we propose Ordered CommonGen, a benchmark designed to evaluate the compositional generalization and instruction-following abilities of LLMs.This benchmark measures ordered coverage to assess whether concepts are generated in the specified order, enabling a simultaneous evaluation of both abilities.We conducted a comprehensive analysis using 36 LLMs and found that, while LLMs generally understand the intent of instructions, biases toward specific concept order patterns often lead to low-diversity outputs or identical results even when the concept order is altered.Moreover, even the most instructioncompliant LLM achieved only about 75% ordered coverage, highlighting the need for improvements in both instruction-following and compositional generalization capabilities. Concepts Coverage (↑) Similarlity (↓)Diversity (↑) Perplexity (↓) w/o order w/ order Ordered Rate pBLEU pBLEURT Distinct Diverse Rate

Yusuke Ide, Joshua Tanner, Adam Nohejl, Jacob Hoffman, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai, Katsuhiko Hayashi, Taro Watanabe. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability.However, high estimated probability does not always lead to high translation quality.Minimum Bayes Risk (MBR) decoding (Kumar and Byrne, 2004) offers an alternative by seeking hypotheses with the highest expected utility.Inspired by Quality Estimation (QE) reranking which uses the QE model as a ranker (Fernandes et al., 2022), we propose source-based MBR (sMBR) decoding, a novel approach that utilizes quasi-sources (generated via paraphrasing or back-translation) as "support hypotheses" and a reference-free quality estimation metric as the utility function, marking the first work to solely use sources in MBR decoding.Experiments show that sMBR outperforms QE reranking and the standard MBR decoding.Our findings suggest that sMBR is a promising approach for NMT decoding.1 NMT x h 0

The rise of large language models (LLMs) generating human-like text has raised concerns about misuse, especially in low-resource languages like Urdu. To address this gap, we introduce the HLU dataset, which consists of three datasets: Document, Paragraph, and Sentence level. The document-level dataset contains 1,014 instances of human-written and LLM-generated articles across 13 domains, while the paragraph and sentence-level datasets each contain 667 instances. We conducted both human and automatic evaluations. In the human evaluation, the average accuracy at the document level was 35%, while at the paragraph and sentence levels, accuracies were 75.68% and 88.45%, respectively. For automatic evaluation, we finetuned the XLMRoBERTa model for both monolingual and multilingual settings achieving consistent results in both. Additionally, we assessed the performance of GPT4 and Claude3Opus using zero-shot prompting. Our experiments and evaluations indicate that distinguishing between human and machine-generated text is challenging for both humans and LLMs, marking a significant step in addressing this issue in Urdu.

Large-scale Vision-Language Models (LVLMs) process both images and text, excelling in multimodal tasks such as image captioning and description generation. However, while these models excel at generating factual content, their ability to generate and evaluate texts reflecting perspectives on the same image, depending on the context, has not been sufficiently explored. To address this, we propose IRR: Image Review Rank, a novel evaluation framework designed to assess critic review texts from multiple perspectives. IRR evaluates LVLMs by measuring how closely their judgments align with human interpretations. We validate it using a dataset of images from 15 categories, each with five critic review texts and annotated rankings in both English and Japanese, totaling over 2,000 data instances. Our results indicate that, although LVLMs exhibited consistent performance across languages, their correlation with human annotations was insufficient, highlighting the need for further advancements. These findings highlight the limitations of current evaluation methods and the need for approaches that better capture human reasoning in Vision & Language tasks.

Ashmari Pramodya, Nirasha Nelki, Heshan Shalinda, Chamila Liyanage, Yusuke Sakai, Randil Pushpananda, Ruvan Weerasinghe, Hidetaka Kamigaito, Taro Watanabe. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Hongyu Sun, Yusuke Sakai, Haruki Sakajo, Shintaro Ozaki, Kazuki Hayashi, Hidetaka Kamigaito, Taro Watanabe. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

We introduce J-ORA, a novel multimodal dataset that bridges the gap in robot perception by providing detailed object attribute annotations within Japanese human-robot dialogue scenarios. J-ORA is designed to support three critical perception tasks, object identification, reference resolution, and next-action prediction, by leveraging a comprehensive template of attributes (e.g., category, color, shape, size, material, and spatial relations). Extensive evaluations with both proprietary and open-source Vision Language Models (VLMs) reveal that incorporating detailed object attributes substantially improves multimodal perception performance compared to without object attributes. Despite the improvement, we find that there still exists a gap between proprietary and open-source VLMs. In addition, our analysis of object affordances demonstrates varying abilities in understanding object functionality and contextual relationships across different VLMs. These findings underscore the importance of rich, context-sensitive attribute annotations in advancing robot perception in dynamic environments. Code and data available at https://github.com/jatuhurrra/J-ORA.

Yusuke Ide, Yuto Nishida, Justin Vasselli, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Haruki Sakajo, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

In this paper, we propose a simple method for annotating reading order based on the measurement of manga reading behavior, which automatically estimates reading order by obtaining a scanpath from eye movements measured by an eye tracker with a built-in HMD. Our method reduces the cost of work and measures natural reading behavior, which is difficult to achieve with conventional GUI-based manual labeling and image analysis-based methods for manga reading order annotation tasks. First, Gaze samples captured with an HMD built-in eye tracker are mapped to their corresponding panels, after which time-series clustering is applied. Then, we extract the most extended fixation duration for every panel and sort panels in ascending order of that duration to infer an individual reading sequence. Also, as needed, it integrates by voting across multiple estimation results, then yields a consensus—i.e., tendentious— reading order for the page. In addition, we evaluated it on 99 pages selected from 33 commercially published works, using recordings from five adult readers. The automatically inferred sequences were compared against expert manual annotations, achieving a mean Kendall’s rank correlation coefficient of 0.82. This result indicates that the proposed method can be extended to annotation tasks based on more natural reading behavior while maintaining estimation accuracy. At the same time, the observed variability among individual sequences highlights the importance of modeling reader-specific behaviors in future work.

Paraphrase detection is a task to identify if two sentences are semantically similar or not. It plays an important role in maintaining the integrity of written work such as plagiarism detection and text reuse detection. Formerly, researchers focused on developing large corpora for English. However, no research has been conducted on sentence-level paraphrase detection in low-resource Pashto language. To bridge this gap, we introduce the first fully manually annotated Pashto sentential paraphrase detection corpus collected from authentic cases in journalism covering 10 different domains, including Sports, Health, Environment, and more. Our proposed corpus contains 6,727 sentences, encompassing 3,687 paraphrased and 3,040 non-paraphrased. Experimental findings reveal that our proposed corpus is sufficient to train XLM-RoBERTa to accurately detect paraphrased sentence pairs in Pashto with an F1 score of 84%. To compare our corpus with those in other languages, we also applied our fine-tuned model to the Indonesian and English paraphrase datasets in a zero-shot manner, achieving F1 scores of 82% and 78%, respectively. This result indicates that the quality of our corpus is not less than commonly used datasets. It‘s a pioneering contribution to the field. We will publicize a subset of 1,800 instances from our corpus, free from any licensing issues.

Multilingual neural machine translation aims to encapsulate multiple languages into a single model. However, it requires an enormous dataset, leaving the low-resource language (LRL) underdeveloped. As LRLs may benefit from shared knowledge of multilingual representation, we aspire to find effective ways to integrate unseen languages in a pre-trained model. Nevertheless, the intricacy of shared representation among languages hinders its full utilisation. To resolve this problem, we employed target language prediction and a central language-aware layer to improve representation in integrating LRLs. Focusing on improving LRLs in the linguistically diverse country of Indonesia, we evaluated five languages using a parallel corpus of 1,000 instances each, with experimental results measured by BLEU showing zero-shot improvement of 7.4 from the baseline score of 7.1 to a score of 15.5 at best. Further analysis showed that the gains in performance are attributed more to the disentanglement of multilingual representation in the encoder with the shift of the target language-specific representation in the decoder.

Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

In Simultaneous Machine Translation (SiMT), training with a simultaneous interpretation (SI) corpus is an effective method for achieving high-quality yet low-latency systems.However, constructing such a corpus is challenging due to high costs, and limitations in annotator capabilities, and as a result, existing SI corpora are limited.Therefore, we propose a method to convert existing speech translation (ST) corpora into interpretation-style corpora, maintaining the original word order and preserving the entire source content using Large Language Models (LLM-SI-Corpus).We demonstrated that fine-tuning SiMT models using the LLM-SI-Corpus reduces latencies while achieving better quality compared to models fine-tuned with other corpora in both speechto-text and text-to-text settings.

Multilingual neural machine translation models support fine-tuning hundreds of languages simultaneously.However, fine-tuning on full parameters solely is inefficient potentially leading to negative interactions among languages.In this work, we demonstrate that the fine-tuning for a language occurs in its intrinsic languagespecific subspace with a tiny fraction of entire parameters.Thus, we propose languagespecific LoRA to isolate intrinsic languagespecific subspaces.Furthermore, we propose architecture learning techniques and introduce a gradual pruning schedule during fine-tuning to exhaustively explore the optimal setting and the minimal intrinsic subspaces for each language, resulting in a lightweight yet effective fine-tuning procedure.The experimental results on a 12-language subset and a 30language subset of FLORES-101 show that our methods not only outperform full-parameter fine-tuning up to 2.25 spBLEU scores but also reduce trainable parameters to 0.4% for high and medium-resource languages and 1.6% for low-resource ones.Codes are available at https://github.com/Spike0924/LSLo.

Scaling the context size of large language models (LLMs) enables them to perform various new tasks, e.g., book summarization.However, the memory cost of the Key and Value (KV) cache in attention significantly limits the practical applications of LLMs.Recent works have explored token pruning for KV cache reduction in LLMs, relying solely on attention scores as a token importance indicator.However, our investigation into value vector norms revealed a notably non-uniform pattern questioning their reliance only on attention scores.Inspired by this, we propose a new method: Value-Aware Token Pruning (VATP) which uses both attention scores and the ℓ 1 norm of value vectors to evaluate token importance.Extensive experiments on LLaMA2-7B-chat and Vicuna-v1.5-7Bacross 16 LongBench tasks demonstrate that VATP outperforms attention-score-only baselines in over 12 tasks, confirming the effectiveness of incorporating value vector norms into token importance evaluation of LLMs. 1

This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks.For the future advance of NER in safety-critical fields like healthcare and finance, it is essential to achieve accurate predictions with calibrated confidence when applying Deep Neural Networks (DNNs), including Pretrained Language Models (PLMs), as a realworld application.However, DNNs are prone to miscalibration, which limits their applicability.Moreover, existing methods for calibration and uncertainty estimation are computational expensive.Our investigation in NER found that data augmentation improves calibration and uncertainty in cross-genre and cross-lingual setting, especially in-domain setting.Furthermore, we showed that the calibration for NER tends to be more effective when the perplexity of the sentences generated by data augmentation is lower, and that increasing the size of the augmentation further improves calibration and uncertainty.

Simultaneous Speech Translation (SiST) begins translating before the entire source input is received, making it crucial to balance quality and latency.In real interpreting situations, interpreters manage this simultaneity by breaking sentences into smaller segments and translating them while maintaining the source order as much as possible.SiST could benefit from this approach to balance quality and latency.However, current corpora used for simultaneous tasks often involve significant word reordering in translation, which is not ideal given that interpreters faithfully follow source syntax as much as possible.Inspired by conference interpreting by humans utilizing the salami technique, we introduce the Simul-MuST-C 1 , a dataset created by leveraging the Large Language Model (LLM), specifically GPT-4o, which aligns the target text as closely as possible to the source text by using minimal chunks that contain enough information to be interpreted.Experiments on three language pairs show that the effectiveness of segmentedbase monotonicity in training data varies with the grammatical distance between the source and the target, with grammatically distant language pairs benefiting the most in achieving quality while minimizing latency.

Ad text generation is vital for automatic advertising in various fields through search engine advertising (SEA) to avoid the cost problem caused by laborious human efforts for creating ad texts.Even though ad creators create the landing page (LP) for advertising and we can expect its quality, conventional approaches with reinforcement learning (RL) mostly focus on advertising keywords rather than LP information.This work investigates and shows the effective usage of LP information as a reward in RL-based ad text generation through automatic and human evaluations.Our analysis of the actually generated ad text shows that LP information can be a crucial reward by appropriately scaling its value range to improve ad text generation performance.

Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Numerous effective methods have been developed to improve query-focused summarization (QFS) performance, e.g., pre-trained model-based and query-answer relevance-based methods. However, these methods still suffer from missing or redundant information due to the inability to capture and effectively utilize the interrelationship between the query and the source document, as well as between the source document and its generated summary, resulting in the summary being unable to answer the query or containing additional unrequired information. To mitigate this problem, we propose an end-to-end hierarchical two-stage summarization model, that first predicts essential content, and then generates a summary by emphasizing the predicted important sentences while maintaining separate encodings for the query and the source, so that it can comprehend not only the query itself but also the essential information in the source. We evaluated the proposed model on two QFS datasets, and the results indicated its overall effectiveness and that of each component.

Abstract Despite significant improvements in enhancing the quality of translation, context-aware machine translation (MT) models underperform in many cases. One of the main reasons is that they fail to utilize the correct features from context when the context is too long or their models are overly complex. This can lead to the explain-away effect, wherein the models only consider features easier to explain predictions, resulting in inaccurate translations. To address this issue, we propose a model that explains the decisions made for translation by predicting coreference features in the input. We construct a model for input coreference by exploiting contextual features from both the input and translation output representations on top of an existing MT model. We evaluate and analyze our method in the WMT document-level translation task of English-German dataset, the English-Russian dataset, and the multilingual TED talk dataset, demonstrating an improvement of over 1.0 BLEU score when compared with other context-aware models.

Continual learning aims to accumulate knowledge to solve new tasks without catastrophic forgetting for previously learned tasks.Research on continual learning has led to the development of generative replay, which prevents catastrophic forgetting by generating pseudosamples for previous tasks and learning them together with new tasks.Inspired by the biological brain, we propose the hippocampal memory indexing to enhance the generative replay by controlling sample generation using compressed features of previous training samples.It enables the generation of a specific training sample from previous tasks, thus improving the balance and quality of generated replay samples.Experimental results indicate that our method effectively controls the sample generation and consistently outperforms the performance of current generative replay methods. 1

Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Negative sampling (NS) loss plays an important role in learning knowledge graph embedding (KGE) to handle a huge number of entities. However, the performance of KGE degrades without hyperparameters such as the margin term and number of negative samples in NS loss being appropriately selected. Currently, empirical hyperparameter tuning addresses this problem at the cost of computational time. To solve this problem, we theoretically analyzed NS loss to assist hyperparameter tuning and understand the better use of the NS loss in KGE learning. Our theoretical analysis showed that scoring methods with restricted value ranges, such as TransE and RotatE, require appropriate adjustment of the margin term or the number of negative samples different from those without restricted value ranges, such as RESCAL, ComplEx, and DistMult. We also propose subsampling methods specialized for the NS loss in KGE studied from a theoretical aspect. Our empirical analysis on the FB15k-237, WN18RR, and YAGO3-10 datasets showed that the results of actually trained models agree with our theoretical findings.

Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Jingyi You, Dongyuan Li, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Hidetaka Kamigaito, Katsuhiko Hayashi. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura, Hiroya Takamura. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Dynamic community detection (or graph clustering) in temporal networks has attracted much attention because it is promising for revealing the underlying mechanism of complex real-world systems. Current methods are criticized for the independence of graph representation learning and graph clustering, considerable noise during temporal information smoothing, and high time complexity. We propose a R obust T emporal S moothing C lustering method (RTSC), which involves joint graph representation learning and graph clustering, to solve these problems. RTSC can be formulated as a constrained multi-objective optimization problem. Specifically, three-order successive snapshots are first projected into the same subspace via graph embedding. We then use the embedding matrices to learn a common low-rank block-diagonal matrix that contains current clustering information and specific noise matrices with a sparse constraint to remove noise at each time step. To efficiently solve the challenging optimization problem, we also propose an optimization procedure based on the augmented Lagrangian multiplier (ALM) scheme. Experimental results on six artificial datasets and four real-world dynamic network datasets indicate that RTSC performs better than six state-of-the-art algorithms for dynamic clustering in temporal networks.

Chenlong Hu, Yukun Feng, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Soichiro Murakami, Sora Tanaka, Masatsugu Hangyo, Hidetaka Kamigaito, Kotaro Funakoshi, Hiroya Takamura, Manabu Okumura. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Manabu Okumura, Hiroya Takamura. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Sentence extractive summarization shortens a document by selecting sentences for a summary while preserving its important contents.However, constructing a coherent and informative summary is difficult using a pre-trained BERT-based encoder since it is not explicitly trained for representing the information of sentences in a document.We propose a nested tree-based extractive summarization model on RoBERTa (NeRoBERTa), where nested tree structures consist of syntactic and discourse trees in a given document.Experimental results on the CNN/DailyMail dataset showed that NeRoBERTa outperforms baseline models in ROUGE.Human evaluation results also showed that NeRoBERTa achieves significantly better scores than the baselines in terms of coherence and yields comparable scores to the state-of-the-art models.

Discourse segmentation and sentence-level discourse parsing play important roles for various NLP tasks to consider textual coherence.Despite recent achievements in both tasks, there is still room for improvement due to the scarcity of labeled data.To solve the problem, we propose a language model-based generative classifier (LMGC) for using more information from labels by treating the labels as an input while enhancing label representations by embedding descriptions for each label.Moreover, since this enables LMGC to make ready the representations for labels, unseen in the pre-training step, we can effectively use a pretrained language model in LMGC.Experimental results on the RST-DT dataset show that our LMGC achieved the state-of-the-art F 1 score of 96.72 in discourse segmentation.It further achieved the state-of-the-art relation F 1 scores of 84.69 with gold EDU boundaries and 81.18 with automatically segmented boundaries, respectively, in sentence-level discourse parsing.

Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words. In sequence-to-sequence (Seq2Seq) based models, the decoder unidirectionally decides to retain or delete words. Thus, it cannot usually explicitly capture the relationships between decoded words and unseen words that will be decoded in the future time steps. Therefore, to avoid generating ungrammatical sentences, the decoder sometimes drops important words in compressing sentences. To solve this problem, we propose a novel Seq2Seq model, syntactically look-ahead attention network (SLAHAN), that can generate informative summaries by explicitly tracking both dependency parent and child words during decoding and capturing important words that will be decoded in the future. The results of the automatic evaluation on the Google sentence compression dataset showed that SLAHAN achieved the best kept-token-based-F1, ROUGE-1, ROUGE-2 and ROUGE-L scores of 85.5, 79.3, 71.3 and 79.1, respectively. SLAHAN also improved the summarization performance on longer sentences. Furthermore, in the human evaluation, SLAHAN improved informativeness without losing readability.

Some downstream NLP tasks exploit discourse dependency trees converted from RST trees. To obtain better discourse dependency trees, we need to improve the accuracy of RST trees at the upper parts of the structures. Thus, we propose a novel neural top-down RST parsing method. Then, we exploit three levels of granularity in a document, paragraphs, sentences and Elementary Discourse Units (EDUs), to parse a document accurately and efficiently. The parsing is done in a top-down manner for each granularity level, by recursively splitting a larger text span into two smaller ones while predicting nuclearity and relation labels for the divided spans. The results on the RST-DT corpus show that our method achieved the state-of-the-art results, 87.0 unlabeled span score, 74.6 nuclearity labeled span score, and the comparable result with the state-of-the-art, 60.0 relation labeled span score. Furthermore, discourse dependency trees converted from our RST trees also achieved the state-of-the-art results, 64.9 unlabeled attachment score and 48.5 labeled attachment score.

We tackle the task of automatically generating a function name from source code.Existing generators face difficulties in generating low-frequency or out-of-vocabulary subwords.In this paper, we propose two strategies for copying low-frequency or out-of-vocabulary subwords in inputs.Our best performing model showed an improvement over the conventional method in terms of our modified F1 and accuracy on the Java-small and Java-large datasets.

We propose neural models that can normalize text by considering the similarities of word strings and sounds.We experimentally compared a model that considers the similarities of both word strings and sounds, a model that considers only the similarity of word strings or of sounds, and a model without the similarities as a baseline.Results showed that leveraging the word string similarity succeeded in dealing with misspellings and abbreviations, and taking into account the sound similarity succeeded in dealing with phonetic substitutions and emphasized characters.So that the proposed models achieved higher F 1 scores than the baseline.

Recently, automatic trivia fact extraction has attracted much research interest.Modern search engines have begun to provide trivia facts as the information for entities because they can motivate more user engagement.In this paper, we propose a new unsupervised algorithm that automatically mines trivia facts for a given entity.Unlike previous studies, the proposed algorithm targets at a single Wikipedia article and leverages its hierarchical structure via top-down processing.Thus, the proposed algorithm offers two distinctive advantages: it does not incur high computation time, and it provides a domain-independent approach for extracting trivia facts.Experimental results demonstrate that the proposed algorithm is over 100 times faster than the existing method which considers Wikipedia categories.Human evaluation demonstrates that the proposed algorithm can mine better trivia facts regardless of the target entity domain and outperforms the existing methods.

We propose a simple and effective method to inject word-level information into characteraware neural language models.Unlike previous approaches which usually inject wordlevel information at the input of a long shortterm memory (LSTM) network, we inject it into the softmax function.The resultant model can be seen as a combination of characteraware language model and simple word-level language model.Our injection method can also be used together with previous methods.Through the experiments on 14 typologically diverse languages, we empirically show that our injection method, when used together with the previous methods, works better than the previous methods, including a gating mechanism, averaging, and concatenation of word vectors.We also provide a comprehensive comparison of these injection methods.

Naoki Kobayashi, Tsutomu Hirao, Kengo Nakamura, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Small images of emojis have unique characteristics as additional information in understanding writers’ intentions. They enable social media users to emphasize their emotions and to express gestural movements in their posts. In addition to emojis, kaomojis (emoticons or facemarks) also behave in a similar way. They are composed of a sequence of characters, which are popularized especially in Asian countries. Although both emojis and kaomojis fulfill similar functions and share the same meaning that can be clues in opinion mining or sentiment analysis, the previous researches have been biased to explore emojis and kaomojis separately. In this paper, we align emojis and kaomojis together as a single token in the Japanese context to offer a bridge between them. Specifically, we aim to judge whether emojis and kaomojis share the same meaning or are similar with each other. We assume that emojis and kaomojis are both a single word in order to obtain their linguistic information with the skip-gram model. Furthermore, we present a new approach to consider the appearances of emojis and kaomojis in themselves, meaning that we explore the information of their visually similar shapes. We regard both of them as a single image to take into account their visual information with the CNN model. We merge two different perspectives toward emojis and kaomojis by exploring their linguistic and visual information simultaneously on the same space. The experimental results showed that we can align an unlimited number of emojis and kaomojis together with their representations (embeddings), and adding the visual information to the linguistic information can improve their representations.

This paper tackles automation of the pyramid method, a reliable manual evaluation framework.To construct a pyramid, we transform human-made reference summaries into extractive reference summaries that consist of Elementary Discourse Units (EDUs) obtained from source documents and then weight every EDU by counting the number of extractive reference summaries that contain the EDU.A summary is scored by the correspondences between EDUs in the summary and those in the pyramid.Experiments on DUC and TAC data sets show that our methods strongly correlate with various manual evaluations.Ref.

Hidetaka Kamigaito, Katsuhiko Hayashi, Tsutomu Hirao, Masaaki Nagata. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

In hierarchical phrase-based machine translation, a rule table is automatically learned by heuristically extracting syn-chronous rules from a parallel corpus. As a result, spuriously many rules are extracted which may be composed of various incorrect rules. The larger rule table incurs more run time for decoding and may result in lower translation quality. To resolve the problems, we propose a hierarchical back-off model for Hiero grammar, an instance of a synchronous context free grammar (SCFG), on the basis of the hierarchical Pitman-Yor process. The model can extract a compact rule and phrase table without resorting to any heuristics by hierarchically backing off to smaller phrases under SCFG. Inference is efficiently carried out using two-step synchronous parsing of Xiao et al., (2012) combined with slice sampling. In our experiments, the proposed model achieved higher or at least comparable translation quality against a previous Bayesian model on various language pairs; German/French/Spanish/Japanese-English. When compared against heuristic models, our model achieved comparable translation quality on a full size German-English language pair in Europarl v7 corpus with significantly smaller grammar size; less than 10 % of that for heuristic model. 1

Generative word alignment models, such as IBM Models, are restricted to oneto-many alignment, and cannot explicitly represent many-to-many relationships in a bilingual text.The problem is partially solved either by introducing heuristics or by agreement constraints such that two directional word alignments agree with each other.In this paper, we focus on the posterior regularization framework (Ganchev et al., 2010) that can force two directional word alignment models to agree with each other during training, and propose new constraints that can take into account the difference between function words and content words.Experimental results on French-to-English and Japanese-to-English alignment tasks show statistically significant gains over the previous posterior regularization baseline.We also observed gains in Japanese-to-English translation tasks, which prove the effectiveness of our methods under grammatically different language pairs.

Recent office documents follow an XML archive format, so they consist of multiple XML files. XML files in office documents include information about page structures and styles such as font, color and position. But, existing text-based search engines do not focus on structure and style of documents. By utilizing them, we can achieve similarity search for office documents based on structures and styles. We propose SOS, a similarity search method based on structures and styles of office documents. To compute a similarity value between office documents, we have to compute similarity values between multiple pairs of XML files in the documents. We also propose LAX+, which is an algorithm to calculate a similarity value for a pair of XML files, by extending existing XML leaf node clustering algorithm. In our experiments, we use docx, xlsx and pptx files and evaluate SOS and LAX+ by precision and recall.