Noriki Nishida


pdf bib
Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations
Yi-Pei Chen | Noriki Nishida | Hideki Nakayama | Yuji Matsumoto
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Enhancing user engagement through personalization in conversational agents has gained significance, especially with the advent of large language models that generate fluent responses. Personalized dialogue generation, however, is multifaceted and varies in its definition – ranging from instilling a persona in the agent to capturing users’ explicit and implicit cues. This paper seeks to systemically survey the recent landscape of personalized dialogue generation, including the datasets employed, methodologies developed, and evaluation metrics applied. Covering 22 datasets, we highlight benchmark datasets and newer ones enriched with additional features. We further analyze 17 seminal works from top conferences between 2021-2023 and identify five distinct types of problems. We also shed light on recent progress by LLMs in personalized dialogue generation. Our evaluation section offers a comprehensive summary of assessment facets and metrics utilized in these works. In conclusion, we discuss prevailing challenges and envision prospect directions for future research in personalized dialogue generation.


pdf bib
RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs Summarization
Hisashi Kamezawa | Noriki Nishida | Nobuyuki Shimizu | Takashi Miyazaki | Hideki Nakayama
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

A release note is a technical document that describes the latest changes to a software product and is crucial in open source software development. However, it still remains challenging to generate release notes automatically. In this paper, we present a new dataset called RNSum, which contains approximately 82,000 English release notes and the associated commit messages derived from the online repositories in GitHub. Then, we propose classwise extractive-then-abstractive/abstractive summarization approaches to this task, which can employ a modern transformer-based seq2seq network like BART and can be applied to various repositories without specific constraints. The experimental results on the RNSum dataset show that the proposed methods can generate less noisy release notes at higher coverage than the baselines. We also observe that there is a significant gap in the coverage of essential information when compared to human references. Our dataset and the code are publicly available.

pdf bib
Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation
Noriki Nishida | Yuji Matsumoto
Transactions of the Association for Computational Linguistics, Volume 10

Discourse parsing has been studied for decades. However, it still remains challenging to utilize discourse parsing for real-world applications because the parsing accuracy degrades significantly on out-of-domain text. In this paper, we report and discuss the effectiveness and limitations of bootstrapping methods for adapting modern BERT-based discourse dependency parsers to out-of-domain text without relying on additional human supervision. Specifically, we investigate self-training, co-training, tri-training, and asymmetric tri-training of graph-based and transition-based discourse dependency parsing models, as well as confidence measures and sample selection criteria in two adaptation scenarios: monologue adaptation between scientific disciplines and dialogue genre adaptation. We also release COVID-19 Discourse Dependency Treebank (COVID19-DTB), a new manually annotated resource for discourse dependency parsing of biomedical paper abstracts. The experimental results show that bootstrapping is significantly and consistently effective for unsupervised domain adaptation of discourse dependency parsing, but the low coverage of accurately predicted pseudo labels is a bottleneck for further improvement. We show that active learning can mitigate this limitation.

pdf bib
Neural Networks in a Product of Hyperbolic Spaces
Jun Takeuchi | Noriki Nishida | Hideki Nakayama
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop

Machine learning in hyperbolic spaces has attracted much attention in natural language processing and many other fields. In particular, Hyperbolic Neural Networks (HNNs) have improved a wide variety of tasks, from machine translation to knowledge graph embedding. Although some studies have reported the effectiveness of embedding into the product of multiple hyperbolic spaces, HNNs have mainly been constructed in a single hyperbolic space, and their extension to product spaces has not been sufficiently studied. Therefore, we propose a novel method to extend a given HNN in a single space to a product of hyperbolic spaces. We apply our method to Hyperbolic Graph Convolutional Networks (HGCNs), extending several HNNs. Our model improved the graph node classification accuracy especially on datasets with tree-like structures. The results suggest that neural networks in a product of hyperbolic spaces can be more effective than in a single space in representing structural data.


pdf bib
Unsupervised Discourse Constituency Parsing Using Viterbi EM
Noriki Nishida | Hideki Nakayama
Transactions of the Association for Computational Linguistics, Volume 8

In this paper, we introduce an unsupervised discourse constituency parsing algorithm. We use Viterbi EM with a margin-based criterion to train a span-based discourse parser in an unsupervised manner. We also propose initialization methods for Viterbi training of discourse constituents based on our prior knowledge of text structures. Experimental results demonstrate that our unsupervised parser achieves comparable or even superior performance to fully supervised parsers. We also investigate discourse constituents that are learned by our method.

pdf bib
A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses
Hisashi Kamezawa | Noriki Nishida | Nobuyuki Shimizu | Takashi Miyazaki | Hideki Nakayama
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In real-world dialogue, first-person visual information about where the other speakers are and what they are paying attention to is crucial to understand their intentions. Non-verbal responses also play an important role in social interactions. In this paper, we propose a visually-grounded first-person dialogue (VFD) dataset with verbal and non-verbal responses. The VFD dataset provides manually annotated (1) first-person images of agents, (2) utterances of human speakers, (3) eye-gaze locations of the speakers, and (4) the agents’ verbal and non-verbal responses. We present experimental results obtained using the proposed VFD dataset and recent neural network models (e.g., BERT, ResNet). The results demonstrate that first-person vision helps neural network models correctly understand human intentions, and the production of non-verbal responses is a challenging task like that of verbal responses. Our dataset is publicly available.


pdf bib
Coherence Modeling Improves Implicit Discourse Relation Recognition
Noriki Nishida | Hideki Nakayama
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue

The research described in this paper examines how to learn linguistic knowledge associated with discourse relations from unlabeled corpora. We introduce an unsupervised learning method on text coherence that could produce numerical representations that improve implicit discourse relation recognition in a semi-supervised manner. We also empirically examine two variants of coherence modeling: order-oriented and topic-oriented negative sampling, showing that, of the two, topic-oriented negative sampling tends to be more effective.


pdf bib
Word Ordering as Unsupervised Learning Towards Syntactically Plausible Word Representations
Noriki Nishida | Hideki Nakayama
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

The research question we explore in this study is how to obtain syntactically plausible word representations without using human annotations. Our underlying hypothesis is that word ordering tests, or linearizations, is suitable for learning syntactic knowledge about words. To verify this hypothesis, we develop a differentiable model called Word Ordering Network (WON) that explicitly learns to recover correct word order while implicitly acquiring word embeddings representing syntactic knowledge. We evaluate the word embeddings produced by the proposed method on downstream syntax-related tasks such as part-of-speech tagging and dependency parsing. The experimental results demonstrate that the WON consistently outperforms both order-insensitive and order-sensitive baselines on these tasks.


pdf bib
Generating Video Description using Sequence-to-sequence Model with Temporal Attention
Natsuda Laokulrat | Sang Phan | Noriki Nishida | Raphael Shu | Yo Ehara | Naoaki Okazaki | Yusuke Miyao | Hideki Nakayama
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Automatic video description generation has recently been getting attention after rapid advancement in image caption generation. Automatically generating description for a video is more challenging than for an image due to its temporal dynamics of frames. Most of the work relied on Recurrent Neural Network (RNN) and recently attentional mechanisms have also been applied to make the model learn to focus on some frames of the video while generating each word in a describing sentence. In this paper, we focus on a sequence-to-sequence approach with temporal attention mechanism. We analyze and compare the results from different attention model configuration. By applying the temporal attention mechanism to the system, we can achieve a METEOR score of 0.310 on Microsoft Video Description dataset, which outperformed the state-of-the-art system so far.