Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions

By Michael Heilman, Noah A. Smith. 2010

275 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

ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, methodology): “Similar proof systems have used mutations in the form of tree-edit operations (Mehdad, 2009), transformations over syntactic parses (Heilman and Smith, 2010; Harmeling, 2009), knowledge-based transformations in the form of lexical mutations, entailment rules, rewrite rules, or their combinations (Ba”
WikiQA: A Challenge Dataset for Open-Domain Question Answering (2015, background): “Answer sentence selection is a crucial subtask of the open-domain question answering (QA) problem, with the goal of extracting answers from a set of pre-selected sentences (Heilman and Smith, 2010; Yao et al., 2013; Severyn and Moschitti, 2013).”
Semantic Parsing via Paraphrasing (2014, background): “Many existing paraphrase models introduce latent variables to describe the derivation of c from x , e.g., with transformations (Heilman and Smith, 2010; Stern and Dagan, 2011) or alignments (Haghighi et al., 2005; Das and Smith, 2009; Chang et al., 2010).”
Deep Learning for Answer Sentence Selection (2014, methodology): “More recently, Yao et al. [21] extended Heilman and Smith’s approach with the difference that they used dynamic programming to ﬁnd the optimal tree edit sequences.”
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs (2015, neutral): “, 2007), tree edit-distance (Punyakanok et al., 2004; Heilman and Smith, 2010) and quasi-synchronous grammars (Wang et al.”
Machine Comprehension with Syntax, Frames, and Semantics (2015, positive): “Our simple rule set is inspired by the rich history of QA research into modeling syntactic transformations between questions and answers (Moschitti et al., 2007; Wang et al., 2007; Heilman and Smith, 2010).”
Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016, methodology): “Previous approaches with probabilistic tree-edit techniques or tree kernels (Wang and Manning, 2010; Heilman and Smith, 2010; Yao et al., 2013) have been successful since tree structure information perModel MAP MRR”
Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets (2019, methodology): “While earlier models for these tasks relied on domain knowledge and lexical resources like WordNet (e.g MacCartney et al., 2008; Heilman and Smith, 2010), the release of the large-scale Stanford natural language inference dataset (SNLI; Bowman et al., 2015) shifted the focus to neural models which…”
Bilateral Multi-Perspective Matching for Natural Language Sentences (2017, background): “Early approaches focused on designing hand-craft features to capture n-gram overlapping, word re-ordering and syntactic alignments phenomena [ Heilman and Smith, 2010; Wang and Ittycheriah, 2015 ] .”
A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering (2015, methodology): “Later, tree kernel function together with a logistic regression model (Heilman and Smith, 2010) or Conditional Random Fields models (Wang and Manning, 2010; Yao et al., 2013) with extracted feature were adopted to learn the associations between question and answer.”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “[175] use quasi-synchronous grammar, Heilman & Smith [58] develop an improved Tree Edit Distance (TED) model, Wang & Manning [174] develop a probabilistic model to learn tree-edit operations on dependency parse trees, while Yao et al.”
Learning Semantic Textual Similarity with Structural Representations (2013, background): “(Wang et al., 2007; Wang and Manning, 2010; Heilman and Smith, 2010).”
Knowledge-Based Textual Inference via Parse-Tree Transformations (2015, background): “The discourse commitments derived by Hickl (2008) are quite similar to the kind of consequents we generate by applying our syntactic, lexical-syntactic, and co-reference substitution rules.”
Semantic Matching in Search (2014, background): “These include collaborative filtering [101, 1, 2, 102, 45, 149, 9, 44], image annotation [83, 76, 159], paraphrasing and textual entailment [62, 54, 139, 203, 55, 85, 165, 35], question answering [37, 126, 21, 205, 178, 130], cross-language information retrieval [64, 141, 140], short text conversati”
Answer Extraction as Sequence Tagging with Tree Edit Distance (2013, methodology): “Such relations have been used in prior approaches to this task (Wang et al., 2007; Wang and Manning, 2010), but not in conjunction with the model of Heilman and Smith (2010).”
Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks (2015, background): “Our model shows an improvement of about a signiﬁcant improvement over previous state-378 ) [36] .6029 .6852 Heilman and Smith (2010) [15] .6091 .6917 Wang and Manning (2010) [35] .5951 .6951 Yao et al. (2013) [37] .6307 .7477 Severyn & Moschitti (2013) [26] .6781 .7358 Yih et al. (2013) [33] .7092…”
Transforming Dependency Structures to Logical Forms for Semantic Parsing (2016, background): “, answer-sentence selection (Punyakanok et al., 2004; Heilman and Smith, 2010; Yao et al., 2013) and semantic parsing (Ge and Mooney, 2009; Poon, 2013; Parikh et al.”
SemEval-2016 Task 3: Community Question Answering (2019, methodology): “In a follow-up work, Zhou et al. (2015a) included long-short term memory (LSTM) units in their convolutional neural network to learn the classification sequence for the thread.”