Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learning

Umakoshi, Masato; Murawaki, Yugo; Kurohashi, Sadao

doi:10.18653/v1/2021.findings-emnlp.165

Cited by 5 publications

(3 citation statements)

References 32 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Subject-object-verb constructions Furthermore, it is important to consider zero pronouns (Umakoshi et al, 2021) when comparing two sentences. Consider two sentences A and B with the same meaning, but only sentence A contains a zero pronoun.…”

Section: Scene Graphmentioning

confidence: 99%

JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models

Wada,

Kaneda,

Sugiura

2023

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

Image captioning studies heavily rely on automatic evaluation metrics such as BLEU and METEOR. However, such n-gram-based metrics have been shown to correlate poorly with human evaluation, leading to the proposal of alternative metrics such as SPICE for English; however, no equivalent metrics have been established for other languages. Therefore, in this study, we propose an automatic evaluation metric called JaSPICE, which evaluates Japanese captions based on scene graphs. The proposed method generates a scene graph from dependencies and the predicate-argument structure, and extends the graph using synonyms. We conducted experiments employing 10 image captioning models trained on STAIR Captions and PFN-PIC and constructed the Shichimi dataset, which contains 103,170 human evaluations. The results showed that our metric outperformed the baseline metrics for the correlation coefficient with the human evaluation.

show abstract

Section: Scene Graphmentioning

confidence: 99%

JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models

Wada,

Kaneda,

Sugiura

2023

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

show abstract

“…There has been extensive research on the application of ZAR to Japanese (Sasano and Kurohashi, 2011;Yamashiro et al, 2018;Umakoshi et al, 2021). Konno et al (2021) proposed a new pretraining task and a fine-tuning method for ZAR, assuming the importance of common-sense knowledge to understand the contextual connections around zero pronouns and antecedents.…”

Section: Zero Anaphora Resolutionmentioning

confidence: 99%

Dialogue Response Generation Using Completion of Omitted Predicate Arguments Based on Zero Anaphora Resolution

Ueyama,

Kano

2023

Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

Human conversation attempts to build common ground consisting of shared beliefs, knowledge, and perceptions that form the premise for understanding utterances. Recent deep learningbased dialogue systems use human dialogue data to train a mapping from a dialogue history to responses, but common ground not directly expressed in words makes it difficult to generate coherent responses by learning statistical patterns alone. We propose Dialogue Completion using Zero Anaphora Resolution (DCZAR), a framework that explicitly completes omitted information in the dialogue history and generates responses from the completed dialogue history. In this study, we conducted automatic and human evaluations by applying several pretraining methods and datasets in Japanese in various combinations. Experimental results show that the DCZAR framework contributes to the generation of more coherent and engaging responses.

show abstract

“…Our code and data are publicly available. 1 Furthermore, it is important to consider zero pronouns (Umakoshi et al, 2021) when comparing two sentences. Consider two sentences A and B with the same meaning, but only sentence A contains a zero pronoun.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

2023

View full text Add to dashboard Cite

Language models (LMs) have been argued to overlap substantially with human beings in grammaticality judgment tasks. But when humans systematically make errors in language processing, should we expect LMs to behave like cognitive models of language and mimic human behavior? We answer this question by investigating LMs' more subtle judgments associated with "language illusions" -sentences that are vague in meaning, implausible, or ungrammatical but receive unexpectedly high acceptability judgments by humans. We looked at three illusions: the comparative illusion (e.g. "More people have been to Russia than I have"), the depth-charge illusion (e.g. "No head injury is too trivial to be ignored"), and the negative polarity item (NPI) illusion (e.g. "The hunter who no villager believed to be trustworthy will ever shoot a bear"). We found that probabilities represented by LMs were more likely to align with human judgments of being "tricked" by the NPI illusion which examines a structural dependency, compared to the comparative and the depth-charge illusions which require sophisticated semantic understanding. No single LM or metric yielded results that are entirely consistent with human behavior. Ultimately, we show that LMs are limited both in their construal as cognitive models of human language processing and in their capacity to recognize nuanced but critical information in complicated language materials.

show abstract

Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learning

Cited by 5 publications

References 32 publications

JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models

JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models

Dialogue Response Generation Using Completion of Omitted Predicate Arguments Based on Zero Anaphora Resolution

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

Contact Info

Product

Resources

About