Papers by Yoshihiko Suhara
OpinionDigest: A Simple Framework for Opinion Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Abstractive opinion summarization framework outperforms competitors' summarizing frameworks . extractive approaches produce well-formed text, but selecting the most popular opinions is challenging . |
| Approach: | They propose an abstractive opinion summarization framework that trains a Transformer model to reconstruct reviews from extracted opinions. |
| Outcome: | The proposed framework outperforms baselines on Yelp and shows promising customization capabilities. |
Convex Aggregation for Opinion Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in text autoencoders have significantly improved the quality of the latent space, allowing models to generate consistent text from aggregated latent vectors. |
| Approach: | They develop a framework which searches input-output word overlap for latent vector aggregation. |
| Outcome: | The proposed framework improves the quality of the latent space and establishes state-of-the-art performance on two opinion summarization benchmarks. |
Extractive Opinion Summarization in Quantized Transformer Spaces (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing work on opinion summarization focuses on aggregating opinions among reviews . et al., 2018; see etal., 2019; liu eto, 2019) demonstrate the potential of opinion summaries. |
| Approach: | They propose an unsupervised system for extractive opinion summarization based on vector-quantized variables and an extraction algorithm. |
| Outcome: | The proposed method is validated by human studies showing that judges prefer it over baselines. |
Comparative Opinion Summarization via Collaborative Decoding (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing opinion summarization methods are insufficient to help users compare multiple choices. |
| Approach: | They propose a comparative opinion summarization task that generates two contrastive summaries and one common summary from two different candidate sets of reviews. |
| Outcome: | The proposed framework produces higher-quality contrastive and common summaries than state-of-the-art models. |
HappyDB: A Corpus of 100,000 Crowdsourced Happy Moments (L18-1)
Copied to clipboard
Akari Asai, Sara Evensen, Behzad Golshan, Alon Halevy, Vivian Li, Andrei Lopatenko, Daniela Stepanov, Yoshihiko Suhara, Wang-Chiew Tan, Yinzhan Xu
| Challenge: | Recent research has focused on developing technologies that help users incorporate the findings of the science of happiness into their daily lives. |
| Approach: | They crowd-sourced HappyDB, a corpus of 100,000 happy moments, and applied several state-of-the-art analysis techniques to analyze HappyDB. |
| Outcome: | The proposed technology can understand how people express their happy moments in text and analyze them using state-of-the-art techniques. |
Open Information Extraction from Question-Answer Pairs (N19-1)
Copied to clipboard
| Challenge: | Existing work on OpenIE extracts structured data from sentences . a system for extracting tuples from question-answer pairs solves this problem . |
| Approach: | They propose a system for extracting tuples from question-answer pairs . they use distributed representations of a question and an answer to generate knowledge facts . |
| Outcome: | The proposed system extracts meaningful structured tuples from question-answer pairs . it can find new and interesting facts to extend knowledge bases, the authors show . |