paper-with-me

홈 › Papers

Studio Ousia's Quiz Bowl Question Answering System

2018-03-23 · Ikuya Yamada, Ryuji Tamaki, Hiroyuki Shindo, Yoshiyasu Takefuji

In this chapter, we describe our question answering system, which was the winning system at the Human-Computer Question Answering (HCQA) Competition at the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS). The competition requires participants to address a factoid question answering task referred to as quiz bowl. To address this task, we use two novel neural network models and combine these models with conventional information retrieval models using a supervised machine learning model. Our system achieved the best performance among the systems submitted in the competition and won a match against six top human quiz experts by a wide margin.

📄 PDF Abstract BibTeX arXiv:1803.08652

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningInformation RetrievalQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

A novel interface for adversarial trivia question-writing

2024-03-12 · Jason Liu

A critical component when developing question-answering AIs is an adversarial dataset that challenges models to adapt to the complex syntax and reasoning underlying our natural language. Present techniques for procedural…

Question AnsweringSentence

Mitigating Noisy Inputs for Question Answering

2019-08-08 · Denis Peskov, Joe Barrow, Pedro Rodriguez, Graham Neubig 외

Natural language processing systems are often downstream of unreliable inputs: machine translation, optical character recognition, or speech recognition. For instance, virtual assistants can only answer your questions af…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationOptical Character Recognition+5

Efficient Passage Retrieval with Hashing for Open-domain Question Answering

2021-06-02 · ACL 2021 5 · Ikuya Yamada, Akari Asai, Hannaneh Hajishirzi

Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require …

Natural QuestionsOpen-Domain Question AnsweringPassage RetrievalQuestion Answering+3

Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering

2018-09-07 · TACL 2019 3 · Eric Wallace, Pedro Rodriguez, Shi Feng, Ikuya Yamada 외

Adversarial evaluation stress tests a model's understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose h…

DiversityInformation RetrievalQuestion AnsweringRetrieval

Improving Question Answering with Generation of NQ-like Questions

2022-10-12 · Saptarashmi Bandyopadhyay, Shraman Pal, Hao Zou, Abhranil Chandra 외

Question Answering (QA) systems require a large amount of annotated data which is costly and time-consuming to gather. Converting datasets of existing QA benchmarks are challenging due to different formats and complexiti…

Natural QuestionsQuestion Answering