Question Answering Using Enhanced Lexical Semantic Models

By Wen-tau Yih, Ming-Wei Chang, Christopher Meek, Andrzej Pastusiak, A. Pastusiak. 2013

266 citations recorded by the source corpus.

Subfields: Information Retrieval & Search, Natural Language Processing

How researchers see this paper

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

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Know What You Don’t Know: Unanswerable Questions for SQuAD (2018, background): “Otherwise, simple heuristics (e.g., based on word overlap) could distinguish answerable and unanswerable questions (Yih et al., 2013).”
WikiQA: A Challenge Dataset for Open-Domain Question Answering (2015, methodology): “We implement several strong baselines to study model behaviors in the two datasets, including two previous state-of-the-art systems (Yih et al., 2013; Yu et al., 2014) on the QAS ENT dataset as well as simple lexical matching methods.”
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions (2016, background): “(This approach to combining vectors is simple and has worked well previously, e.g., (Yih et al. 2013)).”
Neural Variational Inference for Text Processing (2015, methodology): “As stated in (Yih et al., 2013) that the evaluation scripts used by previous work are noisy — 4 out of 72 questions in the test set are treated answered incorrectly.”
Deep Learning for Answer Sentence Selection (2014, methodology): “The table also includes three baseline models provided in [22].”
DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension (2019, methodology): “We report the performance of the baselines introduced in Section 5.1 and our proposed approaches (Yih et al., 2013) 41.7 42.0 Sliding Window (SW) (Richardson et al., 2013) 42.6 42.5 Distance-Based Sliding Window (DSW) (Richardson et al., 2013) 44.4 44.6 Stanford Attentive Reader (SAR) (Chen et al.,…”
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs (2015, methodology): “Instead of focusing on the high-level semantic representation, Yih et al. (2013) turn their attention to improving the shallow semantic component, lexical semantics, by performing semantic matching based on a latent word-alignment structure (cf. Chang et al. (2010)).”
Learning Answer-Entailing Structures for Machine Comprehension (2015, methodology): “…have ranged from various IR based approaches (Mittal and Mittal, 2011) that treat this as a problem of retrieval from existing knowledge bases and perform some shallow inference to NLP approaches that learn a similarity between the question and a set of candidate answers (Yih et al., 2013).”
Attentive Pooling Networks (2016, background): “Traditional work on answer selection have normally used feature engineering, linguistic tools, or external resources (Yih et al., 2013; Wang & Manning, 2010; Wang et al., 2007).”
Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016, neutral): “…0.4891 0.4924 Wgt Word Cnt (Yang et al., 2015) 0.5099 0.5132 PV (Le and Mikolov, 2014) 0.5110 0.5160 PV-Cnt (Yang et al., 2015) 0.5976 0.6058 LCLR (Yih et al., 2013) 0.5993 0.6086 CNN (Yu et al., 2014) 0.6190 0.6281 CNN-Cnt (Yang et al., 2015) 0.6520 0.6652 He et al. (2015) 0.6930 0.7090 This…”
Science Question Answering using Instructional Materials (2016, methodology): “Alignment is a common technique in many NLP applications such as MT (Blunsom and Cohn, 2006), RTE (Sammons et al., 2009; MacCartney et al., 2008; Yao et al., 2013; Sultan et al., 2014), QA (Berant et al., 2013; Yih et al., 2013; Yao and Van Durme, 2014; Sachan et al., 2015), etc.”
A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering (2015, methodology): “Yih et al. (2014) focused on answering single-relation factual questions by a semantic similarity model us-”
Erratum: “ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs” (2016, methodology): “A quotation of three sentences from (Yih et al., 2013) was not properly attributed.”
Statute Law Information Retrieval and Entailment (2019, background): “Extensive research has explored employing syntactic/semantic features [4, 5] and recently using neural networks [6].”
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).”
Answer Interaction in Non-factoid Question Answering Systems (2019, background): “Substantial work has been done in factoid QA [9, 22, 34, 37, 38], community QA [10, 24, 24, 25, 32, 33], and non-factoid QA [5, 11, 18, 35].”
Learning Grounded Meaning Representations with Autoencoders (2014, background): “Examples include information retrieval (Manning et al., 2008), search query expansions (Jones et al., 2006), document classiﬁcation (Se-bastiani, 2002), and question answering (Yih et al., 2013).”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “[161] use distributional models based on lexical semantics to match semantic relations of aligned words in QA pairs.”