Using Semantic Roles to Improve Question Answering

By Dan Shen, Mirella Lapata. 2007

448 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

A Neural Network for Factoid Question Answering over Paragraphs (2014, methodology): “Many approaches to this problem rely on hand-crafted pattern matching and answer-type classification to narrow down the search space (Shen, 2007; Bilotti et al., 2010; Wang, 2006).”
End-to-end learning of semantic role labeling using recurrent neural networks (2015, neutral): “, 2009) and questionanswering (Dan and Lapata, 2007; Surdeanu et al., 2003; Moschitti et al., 2003).”
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs (2015, methodology): “Representative examples include methods based on deeper semantic analysis (Shen and Lapata, 2007; Moldovan et al., 2007), tree edit-distance (Punyakanok et al.”
Question Answering as Global Reasoning Over Semantic Abstractions (2018, background): “Shen and Lapata (2007) have partly addressed the latter challenge with an inference framework that formulates the task as a bipartite matching problem over the assignment of semantic roles, and managed to slightly improve QA.”
FrameNet+: Fast Paraphrastic Tripling of FrameNet (2015, background): “Frame semantic analysis can improve natural language understanding (Fillmore and Baker, 2001), and has been applied to tasks like question answering (Shen and Lapata, 2007) and recognizing textual”
SemEval-2016 Task 3: Community Question Answering (2019, methodology): “Building on the success of SemEval–2015 Task 3 “Answer Selection in Community Question Answer-ing” 1 (Nakov et al., 2015), we run an extension in 2016, which covers a full task on Community Question Answering (CQA) and which is, therefore, closer to the real application needs.”
Question Answering Using Enhanced Lexical Semantic Models (2013, methodology): “Representative examples include methods based on deeper semantic analysis (Shen and Lapata, 2007; Moldovan et al., 2007) and on tree edit-distance (Punyakanok et al., 2004; Heilman and Smith, 2010) and quasi-synchronous grammar (Wang et al., 2007) that match the dependency parse trees of questions…”
Deep Semantic Role Labeling with Self-Attention (2017, background): “ntic representation thus beneﬁting many NLP applications, such as Information Extraction (Bastianelli et al. 2013), Question Answering (Surdeanu et al. 2003; Moschitti, Morarescu, and Harabagiu 2003; Dan and Lapata 2007), Machine Translation (Knight and Luk 1994; Uefﬁng, Haffari, and Sarkar 2007; Wu”
Semi-Supervised Semantic Role Labeling (2009, background): “, 2003) to question answering (Shen and Lapata, 2007), paraphrase identification (Padó and Erk, 2005), and the modeling of textual entailment relations (Tatu and Moldovan, 2005).”
Frame-Semantic Parsing (2014, unknown): “Causative_of relation Excludes relation”
Modelling input texts: from Tree Kernels to Deep Learning (2015, unknown): “, [99, 141, 156].”
Semantic Role Labeling (2010, unknown): “However, a discussion of previous work that has successfully exploited SRL—for example, for question answering (Moschitti et al. 2007; Shen and Lapata 2007; Surdeanu, Ciaramita, and Zaragoza 2008), for sentiment analysis (Johansson and Moschitti 2010), and for cross-document coreference resolution…”
A survey on question answering technology from an information retrieval perspective (2011, background): “A more complete semantic labelling of the full question and candidate answer sentence can improve performance as shown in [130].”
Erratum: “ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs” (2016, methodology): “Representative examples include methods based on deeper semantic analysis (Shen and Lapata, 2007; Moldovan et al., 2007), tree edit-distance (Punyakanok et al., 2004; Heilman and Smith, 2010) and quasi-synchronous grammars (Wang et al., 2007) that match the dependency parse trees of the two…”
Rank learning for factoid question answering with linguistic and semantic constraints (2010, methodology): “[20] D. Shen and M. Lapata.”
High Accuracy Rule-based Question Classification using Question Syntax and Semantics (2016, methodology): “Previous work that has made use of parse trees includes that by Silva et al. (2011), who used Collin’s Rules (Collins, 1999) to extract headwords and work by Shen and Lapata (2007) who made use of FrameNet (Baker et al., 1998).”
Syntactic and Semantic Kernels for Short Text Pair Categorization (2009, background): “Recently, work such as (Shen and Lapata, 2007; Sur-deanu et al., 2008; Moschitti et al., 2007; Mos-chitti and Quarteroni, 2008; Chali and Joty, 2008), uses PAS to consider such dependencies but only the latter three researches attempt to completely exploit PAS with Shallow Semantic Tree Kernels…”
Simple BERT Models for Relation Extraction and Semantic Role Labeling (2019, background): “Both capabilities are useful in several downstream tasks such as question answering (Shen and Lapata, 2007) and open information extraction (Fader et al., 2011).”
A Joint Sequential and Relational Model for Frame-Semantic Parsing (2017, background): “It has been considered a valuable resource for Natural Language Processing and useful for studying tasks such as information extraction, machine translation, and question answering (Surdeanu et al., 2003; Shen and Lapata, 2007; Liu and Gildea, 2010).”