paper-with-me

홈 › Papers

Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices

2022-01-16 · ACL ARR January 2022 1 · Anonymous

It is of great value to answer product questions based on heterogeneous information sources available on web product pages, e.g., semi-structured attributes, text descriptions, user-provided contents, etc. However, these sources have different structures and writing styles, which poses challenges for (1) evidence ranking, (2) source selection, and (3) answer generation. In this paper, we build a benchmark with annotations for both evidence selection and answer generation covering 6 information sources. Based on this benchmark, we conduct a comprehensive study and present a set of best practices. We show that all sources are important and contribute to answering questions. Handling all sources within one single model can produce comparable confidence scores across sources and combining multiple sources for training always helps, even for sources with totally different structures. We further propose a novel data augmentation method to iteratively create training samples for answer generation, which achieves close-to-human performance with only a few thousandannotations. Finally, we perform an in-depth error analysis of model predictions and highlight the challenges for future research.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Answer GenerationData AugmentationEvidence Selection

Similar Papers 제목 키워드 기반

Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices

2022-05-01 · ECNLP (ACL) 2022 5 · Xiaoyu Shen, Gianni Barlacchi, Marco del Tredici, Weiwei Cheng 외

It is of great value to answer product questions based on heterogeneous information sources available on web product pages, e.g., semi-structured attributes, text descriptions, user-provided contents, etc. However, these…

Answer GenerationData AugmentationEvidence Selection

Answering Product-related Questions with Heterogeneous Information

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Wenxuan Zhang, Qian Yu, Wai Lam

Providing instant response for product-related questions in E-commerce question answering platforms can greatly improve users{'} online shopping experience. However, existing product question answering (PQA) methods only…

AttributeQuestion Answering

Contextually Aware E-Commerce Product Question Answering using RAG

2025-08-04 · Praveen Tangarajan, Anand A. Rajasekar, Manish Rathi, Vinay Rao Dandin 외 arxiv

E-commerce product pages contain a mix of structured specifications, unstructured reviews, and contextual elements like personalized offers or regional variants. Although informative, this volume can lead to cognitive ov…

Question Answering

CompMix: A Benchmark for Heterogeneous Question Answering

2023-06-21 · Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum

Fact-centric question answering (QA) often requires access to multiple, heterogeneous, information sources. By jointly considering several sources like a knowledge base (KB), a text collection, and tables from the web, Q…

Question Answering

Natural Answer Generation with Heterogeneous Memory

2018-06-01 · NAACL 2018 6 · Yao Fu, Yansong Feng

Memory augmented encoder-decoder framework has achieved promising progress for natural language generation tasks. Such frameworks enable a decoder to retrieve from a memory during generation. However, less research has b…

Answer GenerationDecoderQuestion AnsweringSentence+1