In Japanese, the natural minimal phrase of a sentence is the “bunsetsu” and it serves as a natural boundary of a sentence for native speakers rather than words, and thus grammatical analysis in Japanese linguistics commonly operates on the basis of bunsetsu units.In contrast, because Japanese does not have delimiters between words, there are two major categories of word definition, namely, Short Unit Words (SUWs) and Long Unit Words (LUWs).Though a SUW dictionary is available, LUW is not.Hence, this study focuses on providing deep learning-based (or LLM-based) bunsetsu and Long Unit Words analyzer for the Heian period (AD 794-1185) and evaluating its performances.We model the parser as transformer-based joint sequential labels model, which combine bunsetsu BI tag, LUW BI tag, and LUW Part-of-Speech (POS) tag for each SUW token.We train our models on corpora of each period including contemporary and historical Japanese.The results range from 0.976 to 0.996 in f1 value for both bunsetsu and LUW reconstruction indicating that our models achieve comparable performance with models for a contemporary Japanese corpus.Through the statistical analysis and diachronic case study, the estimation of bunsetsu could be influenced by the grammaticalization of morphemes.

This paper explains the participation of team Hitachi to SemEval-2023 Task 3 “Detecting the genre, the framing, and the persuasion techniques in online news in a multi-lingual setup.” Based on the multilingual, multi-task nature of the task and the low-resource setting, we investigated different cross-lingual and multi-task strategies for training the pretrained language models. Through extensive experiments, we found that (a) cross-lingual/multi-task training, and (b) collecting an external balanced dataset, can benefit the genre and framing detection. We constructed ensemble models from the results and achieved the highest macro-averaged F1 scores in Italian and Russian genre categorization subtasks.

This paper describes our participation in SemEval-2023 Task 4, ValueEval: Identification of Human Values behind Arguments. The aim of this task is to identify whether or not an input text supports each of the 20 pre-defined human values. Previous work on human value detection has shown the effectiveness of a sequence classification approach using BERT. However, little is known about what type of task formulation is suitable for the task. To this end, this paper explores various task formulations, including sequence classification, question answering, and question answering with chain-of-thought prompting and evaluates their performances on the shared task dataset. Experiments show that a zero-shot approach is not as effective as other methods, and there is no one approach that is optimal in every scenario. Our analysis also reveals that utilizing the descriptions of human values can help to improve performance.

Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts. Although simpler and computationally efficient pretraining objectives, e.g., predicting the first character of a masked token, have recently shown comparable results to MLM, no objectives with a masking scheme actually outperform it in downstream tasks. Motivated by the assumption that their lack of complexity plays a vital role in the degradation, we validate whether more complex masked objectives can achieve better results and investigate how much complexity they should have to perform comparably to MLM. Our results using GLUE, SQuAD, and Universal Dependencies benchmarks demonstrate that more complicated objectives tend to show better downstream results with at least half of the MLM complexity needed to perform comparably to MLM. Finally, we discuss how we should pretrain a model using a masked objective from the task complexity perspective.

One of the challenges in text generation is to control text generation as intended by the user. Previous studies proposed specifying the keywords that should be included in the generated text. However, this approach is insufficient to generate text that reflect the user’s intent. For example, placing an important keyword at the beginning of the text would help attract the reader’s attention; however, existing methods do not enable such flexible control. In this paper, we tackle a novel task of controlling not only keywords but also the position of each keyword in the text generation. To this end, we propose a task-independent method that uses special tokens to control the relative position of keywords. Experimental results on summarization and story generation tasks show that the proposed method can control keywords and their positions. The experimental results also demonstrate that controlling the keyword positions can generate summary texts that are closer to the user’s intent than baseline.

In this paper, we describe our system for SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding. The task aims at detecting idiomaticity in an input sequence (Subtask A) and modeling representation of sentences that contain potential idiomatic multiword expressions (MWEs) (Subtask B) in three languages. We focus on the zero-shot setting of Subtask A and propose two span-based idiomaticity classification methods: MWE span-based classification and idiomatic MWE span prediction-based classification. We use several cross-lingual pre-trained language models (InfoXLM, XLM-R, and others) as our backbone network. Our best-performing system, fine-tuned with the span-based idiomaticity classification, ranked fifth in the zero-shot setting of Subtask A and exhibited a macro F1 score of 0.7466.

This paper describes our participation in SemEval-2022 Task 10, a structured sentiment analysis. In this task, we have to parse opinions considering both structure- and context-dependent subjective aspects, which is different from typical dependency parsing. Some of the major parser types have recently been used for semantic and syntactic parsing, while it is still unknown which type can capture structured sentiments well due to their subjective aspects. To this end, we compared two different types of state-of-the-art parser, namely graph-based and seq2seq-based. Our in-depth analyses suggest that, even though graph-based parser generally outperforms the seq2seq-based one, with strong pre-trained language models both parsers can essentially output acceptable and reasonable predictions. The analyses highlight that the difficulty derived from subjective aspects in structured sentiment analysis remains an essential challenge.

Mining an argument structure from text is an important step for tasks such as argument search and summarization. While studies on argument(ation) mining have proposed promising neural network models, they usually suffer from a shortage of training data. To address this issue, we expand the training data with various auxiliary argument mining corpora and propose an end-to-end cross-corpus training method called Multi-Task Argument Mining (MT-AM). To evaluate our approach, we conducted experiments for the main argument mining tasks on several well-established argument mining corpora. The results demonstrate that MT-AM generally outperformed the models trained on a single corpus. Also, the smaller the target corpus was, the better the MT-AM performed. Our extensive analyses suggest that the improvement of MT-AM depends on several factors of transferability among auxiliary and target corpora.

This paper describes the first report on cross-lingual transfer for semantic dependency parsing. We present the insight that there are twodifferent kinds of cross-linguality, namely sur-face level and mantic level, and try to cap-ture both kinds of cross-linguality by combin-ing annotation projection and model transferof pre-trained language models. Our exper-iments showed that the performance of our graph-based semantic dependency parser almost achieved the approximated upper bound.

In this paper, we present our system for SemEval-2020 task 3, Predicting the (Graded) Effect of Context in Word Similarity. Due to the unsupervised nature of the task, we concentrated on inquiring about the similarity measures induced by different layers of different pre-trained Transformer-based language models, which can be good approximations of the human sense of word similarity. Interestingly, our experiments reveal a language-independent characteristic: the middle to upper layers of Transformer-based language models can induce good approximate similarity measures. Finally, our system was ranked 1st on the Slovenian part of Subtask1 and 2nd on the Croatian part of both Subtask1 and Subtask2.

This paper describes the winning system for SemEval-2020 task 7: Assessing Humor in Edited News Headlines. Our strategy is Stacking at Scale (SaS) with heterogeneous pre-trained language models (PLMs) such as BERT and GPT-2. SaS first performs fine-tuning on numbers of PLMs with various hyperparameters and then applies a powerful stacking ensemble on top of the fine-tuned PLMs. Our experimental results show that SaS outperforms a naive average ensemble, leveraging weaker PLMs as well as high-performing PLMs. Interestingly, the results show that SaS captured non-funny semantics. Consequently, the system was ranked 1st in all subtasks by significant margins compared with other systems.

Users of social networking services often share their emotions via multi-modal content, usually images paired with text embedded in them. SemEval-2020 task 8, Memotion Analysis, aims at automatically recognizing these emotions of so-called internet memes. In this paper, we propose a simple but effective Modality Ensemble that incorporates visual and textual deep-learning models, which are independently trained, rather than providing a single multi-modal joint network. To this end, we first fine-tune four pre-trained visual models (i.e., Inception-ResNet, PolyNet, SENet, and PNASNet) and four textual models (i.e., BERT, GPT-2, Transformer-XL, and XLNet). Then, we fuse their predictions with ensemble methods to effectively capture cross-modal correlations. The experiments performed on dev-set show that both visual and textual features aided each other, especially in subtask-C, and consequently, our system ranked 2nd on subtask-C.

This paper shows our system for SemEval-2020 task 10, Emphasis Selection for Written Text in Visual Media. Our strategy is two-fold. First, we propose fine-tuning many pre-trained language models, predicting an emphasis probability distribution over tokens. Then, we propose stacking a trainable distribution fusion DistFuse system to fuse the predictions of the fine-tuned models. Experimental results show tha DistFuse is comparable or better when compared with a naive average ensemble. As a result, we were ranked 2nd amongst 31 teams.

In this paper, we show our system for SemEval-2020 task 11, where we tackle propaganda span identification (SI) and technique classification (TC). We investigate heterogeneous pre-trained language models (PLMs) such as BERT, GPT-2, XLNet, XLM, RoBERTa, and XLM-RoBERTa for SI and TC fine-tuning, respectively. In large-scale experiments, we found that each of the language models has a characteristic property, and using an ensemble model with them is promising. Finally, the ensemble model was ranked 1st amongst 35 teams for SI and 3rd amongst 31 teams for TC.

In this paper, we present our participation in SemEval-2020 Task-12 Subtask-A (English Language) which focuses on offensive language identification from noisy labels. To this end, we developed a hybrid system with the BERT classifier trained with tweets selected using Statistical Sampling Algorithm (SA) and Post-Processed (PP) using an offensive wordlist. Our developed system achieved 34th position with Macro-averaged F1-score (Macro-F1) of 0.90913 over both offensive and non-offensive classes. We further show comprehensive results and error analysis to assist future research in offensive language identification with noisy labels.

State-of-the-art argument mining studies have advanced the techniques for predicting argument structures. However, the technology for capturing non-tree-structured arguments is still in its infancy. In this paper, we focus on non-tree argument mining with a neural model. We jointly predict proposition types and edges between propositions. Our proposed model incorporates (i) task-specific parameterization (TSP) that effectively encodes a sequence of propositions and (ii) a proposition-level biaffine attention (PLBA) that can predict a non-tree argument consisting of edges. Experimental results show that both TSP and PLBA boost edge prediction performance compared to baselines.

This paper presents our proposed parser for the shared task on Meaning Representation Parsing (MRP 2020) at CoNLL, where participant systems were required to parse five types of graphs in different languages. We propose to unify these tasks as a text-to-graph-notation transduction in which we convert an input text into a graph notation. To this end, we designed a novel Plain Graph Notation (PGN) that handles various graphs universally. Then, our parser predicts a PGN-based sequence by leveraging Transformers and biaffine attentions. Notably, our parser can handle any PGN-formatted graphs with fewer framework-specific modifications. As a result, ensemble versions of the parser tied for 1st place in both cross-framework and cross-lingual tracks.

This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task. In this shared task, the participating systems were asked to predict nodes, edges and their attributes for five frameworks, each with different order of “abstraction” from input tokens. We proposed a unified encoder-to-biaffine network for all five frameworks, which effectively incorporates a shared encoder to extract rich input features, decoder networks to generate anchorless nodes in UCCA and AMR, and biaffine networks to predict edges. Our system was ranked fifth with the macro-averaged MRP F1 score of 0.7604, and outperformed the baseline unified transition-based MRP. Furthermore, post-evaluation experiments showed that we can boost the performance of the proposed system by incorporating multi-task learning, whereas the baseline could not. These imply efficacy of incorporating the biaffine network to the shared architecture for MRP and that learning heterogeneous meaning representations at once can boost the system performance.