A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering

By Di Wang, Eric Nyberg. 2015

353 citations recorded by the source corpus.

In this paper, we present an approach that address the answer sentence selection problem for question answering. The proposed method uses a stacked bidirectional Long-Short Term Memory (BLSTM) network to sequentially read words from question and answer sentences, and then outputs their relevance scores. Unlike prior work, this approach does not require any syntactic parsing or external knowledge resources such as WordNet which may not be available in some domains or languages. The full system is based on a combination of the stacked BLSTM relevance model and keywords matching. The results of our experiments on a public benchmark dataset from TREC show that our system outperforms previous work which requires syntactic features and external knowledge resources.

Subfields: Artificial Intelligence, Natural Language Processing, Model Architectures

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 Natural Language Processing

In Model Architectures

Citations in the corpus

Coarse-to-Fine Question Answering for Long Documents (2016, background): “Recently, neural networks models (Wang and Nyberg, 2015; Severyn and Moschitti, 2015; dos Santos et al., 2016) answer sentence selection as latent and generates answer strings instead of selecting text spans.”
Towards Universal Paraphrastic Sentence Embeddings (2015, background): “LSTMs have recently been shown to produce state-of-the-art results in a variety of sequence processing tasks (Chen et al., 2015a; Filippova et al., 2015; Xu et al., 2015c; Belinkov & Glass, 2015; Wang & Nyberg, 2015).”
Recurrent Neural Networks for Classifying Relations in Clinical Notes (2017, neutral): “In general domain NLP, a growing number of studies have successfully used recurrent neural networks (RNNs) combined with word embedding [22] on tasks including language modeling [23], text classification [24–27], question answering [25,26,28,29], machine translation [25,30–32], named entity recognit”
Attentive Pooling Networks (2016, methodology): “Different neural network architectures have been recently proposed to perform matching of semantically related text segments (Yu et al., 2014; Hu et al., 2014; dos Santos et al., 2015; Wang & Nyberg, 2015; Severyn & Moschitti, 2015; Tan et al., 2015).”
Semi-supervised Question Retrieval with Gated Convolutions (2015, background): “has also involved the use of neural network architectures (Severyn and Moschitti, 2015; Wang and Nyberg, 2015; Shen et al., 2015; Feng et al., 2015; Tan et al., 2015).”
Steering Output Style and Topic in Neural Response Generation (2017, methodology): “RNN-based ranking methods are among the most effective methods for retrieving relevant responses (Wang and Nyberg, 2015, 2016).”
De-identification of patient notes with recurrent neural networks (2016, background): “…text classiﬁcation (Socher et al., 2013; Kim, 2014; Blunsom et al., 2014; Lee and Dernoncourt, 2016), question answering (We-ston et al., 2015; Wang and Nyberg, 2015), machine translation (Bahdanau et al., 2014; Tamura et al., 2014; Sundermeyer et al., 2014), as well as named entity…”
Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications (2019, methodology): “Various neural network models are employed to represent questions (Severyn and Moschitti, 2015; Wang and Nyberg, 2015).”
DeepStory: Video Story QA by Deep Embedded Memory Networks (2017, background): “, 2014], long short-term memory [Wang et al., 2015] and attention based deep models [Tan et al.”
LSTM-based Deep Learning Models for non-factoid answer selection (2015, methodology): “Instead of generating QA representation independently, we leverage a simple attention model for the answer vector generation based on questions.”
AUEB at BioASQ 7: Document and Snippet Retrieval (2019, methodology): “[28] use a stacked bilstm that reads the”
Discriminative Information Retrieval for Question Answering Sentence Selection (2017, background): “Extensive research has explored employing syntactic/semantic features (Yih et al., 2013; Wang and Manning, 2010; Heilman and Smith, 2010; Yao et al., 2013a) and recently using neural networks (Yu et al., 2014; Severyn and Mos-chitti, 2015; Wang and Nyberg, 2015; Yin et al., 2016).”
Neural information retrieval: at the end of the early years (2017, methodology): “Wang and Nyberg (2015) use a stacked bidirectional LSTM to sequentially read words from both question and answer sentences, calculating relevance scores for answer sentence selection through mean pooling across all time steps.”
Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning (2017, methodology): “Currently, the problem of community-based question answering has attracted considerable attention (Ji et al. 2012; Qiu and Huang 2015; Shen et al. 2015; Wang and Nyberg 2015; Dong et al. 2015; Fang et al. 2016).”
Denoising Bodies to Titles: Retrieving Similar Questions with Recurrent Convolutional Models (2015, background): “Recent work on answer selection on community QA forums, similar to our task of question retrieval, has also involved the use of neural network architectures (Severyn and Moschitti, 2015; Wang and Nyberg, 2015; Shen et al., 2015; Feng et al., 2015; Tan et al., 2015).”
SelQA: A New Benchmark for Selection-Based Question Answering (2016, background): “Several corpora have been created for these tasks [1, 2, 3], allowing researchers to build effective question answering systems [4, 5, 6] with the aim of improving reading comprehension through understanding and reasoning of natural language.”
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models (2017, background): “Recently, end-to-end approaches to predicting the match of short text pairs have been proposed, by utilising neural networks, such as convolutional neural network (CNN) [9, 37] or long short-term memory neural network (LSTM) [40].”