Question similarity in community question answering: A systematic exploration of preprocessing methods and models

Florian Kunneman, Thiago Castro Ferreira, Emiel Krahmer, Antal Van Den Bosch

Onderzoeksoutput: Hoofdstuk in boek/boekdeelBijdrage aan conferentie proceedingsWetenschappelijkpeer review

Samenvatting

Community Question Answering forums are popular among Internet users, and a basic problem they encounter is trying to find out if their question has already been posed before. To address this issue, NLP researchers have developed methods to automatically detect question-similarity, which was one of the shared tasks in SemEval. The best performing systems for this task made use of Syntactic Tree Kernels or the SoftCosine metric. However, it remains unclear why these methods seem to work, whether their performance can be improved by better preprocessing methods and what kinds of errors they (and other methods) make. In this paper, we therefore systematically combine and compare these two approaches with the more traditional BM25 and translation-based models. Moreover, we analyze the impact of preprocessing steps (lowercasing, suppression of punctuation and stop words removal) and word meaning similarity based on different distributions (word translation probability, Word2Vec, fastText and ELMo) on the performance of the task. We conduct an error analysis to gain insight into the differences in performance between the system set-ups. The implementation is made publicly available.1

Originele taal-2Engels
TitelInternational Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings
RedacteurenGalia Angelova, Ruslan Mitkov, Ivelina Nikolova, Irina Temnikova, Irina Temnikova
Pagina's593-601
Aantal pagina's9
ISBN van elektronische versie9789544520557
DOI's
StatusGepubliceerd - 01 jan 2019

Publicatie series

NaamInternational Conference Recent Advances in Natural Language Processing, RANLP
Volume2019-September
ISSN van geprinte versie1313-8502

Vingerafdruk

Duik in de onderzoeksthema's van 'Question similarity in community question answering: A systematic exploration of preprocessing methods and models'. Samen vormen ze een unieke vingerafdruk.

Citeer dit