323 citations · 495 across the 19 of their papers we have counts for
14 papers · 1 filter
Summarizing Community-based Question-Answer Pairs
Ting-Yao Hsu, Yoshi Suhara, Xiaolan Wang
Community-based Question Answering (CQA), which allows users to acquire their desired information, has increasingly become an essential component of online services in various doma…
Noisy Pairing and Partial Supervision for Stylized Opinion Summarization
Hayate Iso, Xiaolan Wang, Yoshi Suhara
Opinion summarization research has primarily focused on generating summaries reflecting important opinions from customer reviews without paying much attention to the writing style.…
Beyond Opinion Mining: Summarizing Opinions of Customer Reviews
Reinald Kim Amplayo, Arthur Bražinskas, Yoshi Suhara +2
Customer reviews are vital for making purchasing decisions in the Information Age. Such reviews can be automatically summarized to provide the user with an overview of opinions. In…
Comparative Opinion Summarization via Collaborative Decoding
Hayate Iso, Xiaolan Wang, Stefanos Angelidis +1
Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and…
Convex Aggregation for Opinion Summarization
Hayate Iso, Xiaolan Wang, Yoshihiko Suhara +2
Recent advances in text autoencoders have significantly improved the quality of the latent space, which enables models to generate grammatical and consistent text from aggregated l…
Extractive Opinion Summarization in Quantized Transformer Spaces
Stefanos Angelidis, Reinald Kim Amplayo, Yoshihiko Suhara +2
We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector-Quantized Variational Autoencoders, which we repurp…
Constructing Explainable Opinion Graphs from Review
Nofar Carmeli, Xiaolan Wang, Yoshihiko Suhara +4
The Web is a major resource of both factual and subjective information. While there are significant efforts to organize factual information into knowledge bases, there is much less…
OpinionDigest: A Simple Framework for Opinion Summarization
Yoshihiko Suhara, Xiaolan Wang, Stefanos Angelidis +1
We present OpinionDigest, an abstractive opinion summarization framework, which does not rely on gold-standard summaries for training. The framework uses an Aspect-based Sentiment…
Enhancing Review Comprehension with Domain-Specific Commonsense
Aaron Traylor, Chen Chen, Behzad Golshan +6
Review comprehension has played an increasingly important role in improving the quality of online services and products and commonsense knowledge can further enhance review compreh…
Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization
Wataru Hirota, Yoshihiko Suhara, Behzad Golshan +1
We present Emu, a system that semantically enhances multilingual sentence embeddings. Our framework fine-tunes pre-trained multilingual sentence embeddings using two main component…
Happiness Entailment: Automating Suggestions for Well-Being
Sara Evensen, Yoshihiko Suhara, Alon Halevy +3
Understanding what makes people happy is a central topic in psychology. Prior work has mostly focused on developing self-reporting assessment tools for individuals and relies on ex…
Open Information Extraction from Question-Answer Pairs
Nikita Bhutani, Yoshihiko Suhara, Wang-Chiew Tan +2
Open Information Extraction (OpenIE) extracts meaningful structured tuples from free-form text. Most previous work on OpenIE considers extracting data from one sentence at a time.…
HappyDB: A Corpus of 100,000 Crowdsourced Happy Moments
Akari Asai, Sara Evensen, Behzad Golshan +7
The science of happiness is an area of positive psychology concerned with understanding what behaviors make people happy in a sustainable fashion. Recently, there has been interest…
A Lightweight Front-end Tool for Interactive Entity Population
Hidekazu Oiwa, Yoshihiko Suhara, Jiyu Komiya +1
Entity population, a task of collecting entities that belong to a particular category, has attracted attention from vertical domains. There is still a high demand for creating enti…