Papers by Natthawut Kertkeidkachorn
Visual and Memory–Augmented Soccer Commentary Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing datasets produce incomplete commentary that lacks semantic richness and does not convey full visual information present in standard video clips. |
| Approach: | They propose a method that transforms incomplete annotations into MatchText, a semantically complete and structurally standardized dataset. |
| Outcome: | The proposed model outperforms baselines on constructed soccer commentary datasets. |
Enhancing Financial Table and Text Question Answering with Tabular Graph and Numerical Reasoning (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing models that learn tabular structures in financial documents do not understand tables and numbers. |
| Approach: | They propose to infuse explicit tabular structures through a graph neural network to improve model's performance in question answering. |
| Outcome: | The proposed model outperforms the baseline model in low-resource settings while outperforming the graph module. |
Text Generation Model Enhanced with Semantic Information in Aspect Category Sentiment Analysis (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for ACSA fail to model relations of target words and opinion words in a sentence including multiple aspects. |
| Approach: | They propose to incorporate AMR into a text generation model to model relations of target words and opinion words in a sentence including multiple aspects. |
| Outcome: | The proposed method outperforms state-of-the-art methods on three datasets. |
One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing sentence embedding methods lack the ability to capture the implicit semantics of sentences. |
| Approach: | They propose a sentence embedding method that assigns two embeddables to each sentence . one represents the explicit semantics and the other represents the implicit semantics . results show DualCSE can effectively encode both explicit and implicit meanings - they argue . |
| Outcome: | The proposed method can effectively encode both explicit and implicit meanings and improve the performance of the downstream task. |
Sentiment Analysis using the Relationship between Users and Products (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on modelling user and product aspects without considering the relationship between users and products. |
| Approach: | They propose a model that incorporates the relationship between users and products into the model. |
| Outcome: | The proposed model improves on three well-known benchmarks for sentiment classification with the user and product information. |
Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Shortcut reasoning is an irrational process of inference, which degrades the robustness of an NLP model. |
| Approach: | They propose a method to quantify the severity of shortcut reasoning by leveraging out-of-distribution data. |
| Outcome: | The proposed method quantifies the severity of the discovered shortcut reasoning using out-of-distribution data. |
DBQR-QA: A Question Answering Dataset on a Hybrid of Database Querying and Reasoning (2024.findings-acl)
Copied to clipboard
| Challenge: | Question answering (QA) is a fundamental task in the field of Natural Language Processing (NLP). |
| Approach: | They propose a database querying and reasoning dataset for question answering that is designed to accommodate sequential questions and multi-hop queries. |
| Outcome: | The proposed dataset better mirrors the dynamics of real-world information retrieval and analysis with a particular focus on the financial reports of US companies. |