Learning Continuous Word Embedding with Metadata for Question Retrieval in Community Question Answering

By Guangyou Zhou, Tingting He, Jun Zhao, Po Hu. 2015

181 citations recorded by the source corpus.

Community question answering (cQA) has become an important issue due to the popularity of cQA archives on the web. This paper is concerned with the problem of question retrieval. Question retrieval in cQA archives aims to find the existing questions that are semantically equivalent or relevant to the queried questions. However, the lexical gap problem brings about new challenge for question retrieval in cQA. In this paper, we propose to learn continuous word embeddings with metadata of category information within cQA pages for question retrieval. To deal with the variable size of word embedding vectors, we employ the framework of fisher kernel to aggregated them into the fixedlength vectors. Experimental results on large-scale real world cQA data set show that our approach can significantly outperform state-of-the-art translation models and topic-based models for question re-

Subfields: Artificial Intelligence, Information Systems, Information Retrieval & Search, Question Answering & Reading Comprehension

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Information Retrieval & Search

In Question Answering & Reading Comprehension

Citations in the corpus

Relevance-based Word Embedding (2017, methodology): “[47] introduced an embeddingbased method for question retrieval in the context of community question answering.”
Semi-supervised Question Retrieval with Gated Convolutions (2015, methodology): “For instance, Zhou et al. (2015) learn word embeddings using category-based metadata information for questions.”
Sanity Check: A Strong Alignment and Information Retrieval Baseline for Question Answering (2018, unknown): “rmation retrieval (IR) systems [e.g., 23] have served as the standard baseline for QA tasks [19 ,26 inter alia]. However, the lack of lexical overlap in many QA datasets between questions and answers [1, 9, 33], makes standard IR approaches that rely on strict lexical matching less applicable. Sever”
Neural information retrieval: at the end of the early years (2017, methodology): “Similarly for word2vec, Mitra et al. (2016) simply adopt CBOW, while others adopt Skip-gram (De Vine et al. 2014; Manotumruksa et al. 2016; Vulic and Moens 2015; Yang et al. 2016b; Ye et al. 2016; Zhou et al. 2015).”
Retrieving Textual Evidence for Knowledge Graph Facts (2019, methodology): “Different aggregation strategies including Fisher Vectors are also used to build document vectors [4,25].”
The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings (2018, background): “This one change, shifting from global to local context, has resulted in a punctuated increase in their accuracy on a wide range of tasks, from the analogy tests we detail to word classification (Taddy 2015b), question-answering (Zhou et al. 2015), and automated translation (Johnson et al. 2017).”
Denoising Bodies to Titles: Retrieving Similar Questions with Recurrent Convolutional Models (2015, methodology): “The task of automatically retrieving similar questions to a given user's question has recently attracted significant attention and has become a testbed for various representation learning approaches (Zhou et al., 2015; dos Santos et al., 2015).”
Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning (2017, methodology): “Zhou et al. (Zhou et al. 2015a) introduce the metadata powered word embedding method for question retrieval in CQA.”
Embedding-based Query Language Models (2016, methodology): “[31] recently proposed an embeddingbased method for question retrieval in the community question answering systems.”