WebCPM: Interactive Web Search for Chinese Long-form Question Answering

05/11/2023
by   Yujia Qin, et al.
0

Long-form question answering (LFQA) aims at answering complex, open-ended questions with detailed, paragraph-length responses. The de facto paradigm of LFQA necessitates two procedures: information retrieval, which searches for relevant supporting facts, and information synthesis, which integrates these facts into a coherent answer. In this paper, we introduce WebCPM, the first Chinese LFQA dataset. One unique feature of WebCPM is that its information retrieval is based on interactive web search, which engages with a search engine in real time. Following WebGPT, we develop a web search interface. We recruit annotators to search for relevant information using our interface and then answer questions. Meanwhile, the web search behaviors of our annotators would be recorded. In total, we collect 5,500 high-quality question-answer pairs, together with 14,315 supporting facts and 121,330 web search actions. We fine-tune pre-trained language models to imitate human behaviors for web search and to generate answers based on the collected facts. Our LFQA pipeline, built on these fine-tuned models, generates answers that are no worse than human-written ones in 32.5 respectively.

READ FULL TEXT
12/17/2021

WebGPT: Browser-assisted question-answering with human feedback

We fine-tune GPT-3 to answer long-form questions using a text-based web-...
11/15/2022

Generative Long-form Question Answering: Relevance, Faithfulness and Succinctness

In this thesis, we investigated the relevance, faithfulness, and succinc...
05/05/2021

Rethinking Search: Making Experts out of Dilettantes

When experiencing an information need, users want to engage with an expe...
07/31/2023

Olio: A Semantic Search Interface for Data Repositories

Search and information retrieval systems are becoming more expressive in...
08/16/2019

Learning Representations and Agents for Information Retrieval

A goal shared by artificial intelligence and information retrieval is to...
09/10/2023

AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions

The development of large high-quality datasets and high-performing model...

Please sign up or login with your details

Forgot password? Click here to reset