Papers by Hiroshi Kanayama
Incorporating Syntax and Lexical Knowledge to Multilingual Sentiment Classification on Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | generative approach to multilingual sentiment classification is based on syntactic and lexical knowledge and requires retraining and tuning. |
| Approach: | They propose to use a sentiment extractor supported by syntactic and lexical resources to enhance multilingual sentiment classification without retraining LLMs. |
| Outcome: | The proposed approach reduces the multilingual sentiment classification error by 33 points and performs well even for nongenerative tasks such as topic classification and sentiment polarity judgment. |
How Universal are Universal Dependencies? Exploiting Syntax for Multilingual Clause-level Sentiment Detection (2020.lrec-1)
Copied to clipboard
| Challenge: | a new method for clause-level sentiment detection is proposed for multilingual use cases. |
| Approach: | They propose a pipeline method that makes the most of syntactic structures based on Universal Dependencies. |
| Outcome: | The proposed method achieves high precision in sentiment detection for 17 languages . it avoids machine-learning approaches that may cause obstacles to its use cases . |
Think Like You Execute: Verifiable Chain of Thought from Program Traces (2026.acl-industry)
Copied to clipboard
Shailja Thakur, Vaibhav Saxena, Rohan Kulkarni, Shivdeep Singh, Parameswaran Selvam, Hiroshi Kanayama, Hima Patel
| Challenge: | Current synthetic Chain-of-Thought (CoT) training data often consists of plausible-sounding explanations generated by teacher models, not verifiable accounts of actual program behavior. |
| Approach: | They propose to ground CoT generation directly in program execution traces to improve reasoning capabilities. |
| Outcome: | The proposed pipeline improves performance on live code benchmarks and on cruxEval-output and cruxeval-input. |
Universal Dependencies Version 2 for Japanese (L18-1)
Copied to clipboard
Masayuki Asahara, Hiroshi Kanayama, Takaaki Tanaka, Yusuke Miyao, Sumire Uematsu, Shinsuke Mori, Yuji Matsumoto, Mai Omura, Yugo Murawaki
| Challenge: | UD Japanese resources are built on automatic conversion from several treebanks. |
| Approach: | They propose to port the word delimitation, POS, and syntactic relations of existing treebanks to UD Japanese . they discuss the issues of the UD scheme found through porting of the Japanese language . |
| Outcome: | The proposed UD Japanese resources are based on automatic conversion from treebanks. |
Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models acquire general knowledge from pretraining but pretraining data contain undesirable social biases which can be perpetuated or even amplified by LLMs. |
| Approach: | They propose an efficient yet effective annotation pipeline to investigate social biases in pretraining data. |
| Outcome: | The proposed pipeline investigates social biases in the pretraining corpus using protected attribute detection and regard classification. |
Interactive Construction of User-Centric Dictionary for Text Analytics (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for interactive dictionary construction are limited to a small number of terms, but we propose a method that can be used to create flexible dictionaries with precise granularity. |
| Approach: | They propose a method to construct a term dictionary for text analytics through an interactive process between a human and a machine. |
| Outcome: | The proposed method outperforms baseline methods and works even with a small number of interactions. |
A Simple-Yet-Efficient Instruction Augmentation Method for Zero-Shot Sentiment Classification (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have used labeled sentiment instances to instruction tune LLMs, improving zero-shot sentiment classification performance. |
| Approach: | They propose a simple-yet-efficient method which does not rely on actual labeled sentiment instances. |
| Outcome: | The proposed method outperforms LLMs tuned with more complex instruction tuning methods by 5.1 points and increases scores by 30 points. |
Scalable Cross-lingual Treebank Synthesis for Improved Production Dependency Parsers (2020.coling-industry)
Copied to clipboard
| Challenge: | scalable Universal Dependency (UD) treebank synthesis techniques are used to improve production-grade parsers. |
| Approach: | They propose a data augmentation technique that uses synthetic treebanks to improve production-grade parsers. |
| Outcome: | The proposed technique improves LAS performance on seven languages by up to two points on production models trained on original UD treebanks. |
PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation (2023.findings-eacl)
Copied to clipboard
Ishan Jindal, Alexandre Rademaker, Khoi-Nguyen Tran, Huaiyu Zhu, Hiroshi Kanayama, Marina Danilevsky, Yunyao Li
| Challenge: | Existing evaluation scripts for semantic role labeling do not consider error propagation . existing evaluation script does not consider argument independent of predicate sense . |
| Approach: | They propose a more strict SRL evaluation metric PriMeSRL to address these issues . they propose to use a metric that measures the quality of the underlying SRL models . |
| Outcome: | The proposed metric reduces quality evaluation of all SoTA SRL models and penalizes failures. |
A Simple Yet Effective Corpus Construction Method for Chinese Sentence Compression (2022.lrec-1)
Copied to clipboard
| Challenge: | Deletion-based sentence compression has made significant progress in the english language . however, there is a lack of large-scale and high-quality parallel corpus for the Chinese language to train an efficient system. |
| Approach: | They propose to construct a Chinese corpus with 151k pairs of sentences and train extractive and generative neural compression models on the constructed corpus. |
| Outcome: | The proposed method generates high-quality compressed sentences on automatic and human evaluation metrics compared with baselines. |
Sentence Identification with BOS and EOS Label Combinations (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for preprocessing sentences only use the end of the sentence (EOS) however, real-world texts often contain non-sentential units (NSUs) such as metadata, sentence fragments, etc. |
| Approach: | They propose a task of sentence identification where the goal is to identify SUs while excluding NSUs in a given text. |
| Outcome: | The proposed method outperforms baselines which only use EOS labels on the sentence identification task. |
Incorporating Syntactic Knowledge into Pre-trained Language Model using Optimization for Overcoming Catastrophic Forgetting (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models lack syntactic knowledge for many tasks that handle complex or long sentences. |
| Approach: | They propose to use pre-trained language models to incorporate syntactic knowledge into a model by adding additional syntatic knowledge to the model. |
| Outcome: | The proposed model can be easily applied to downstream tasks that require syntactic knowledge. |