Modeling Local Coherence: An Entity-Based Approach

By Regina Barzilay, Mirella Lapata. 2005

881 citations recorded by the source corpus.

This article proposes a novel framework for representing and measuring local coherence. Central to this approach is the entity-grid representation of discourse, which captures patterns of entity distribution in a text. The algorithm introduced in the article automatically abstracts a text into a set of entity transition sequences and records distributional, syntactic, and referential information about discourse entities. We re-conceptualize coherence assessment as a learning task and show that our entity-based representation is well-suited for ranking-based generation and text classification tasks. Using the proposed representation, we achieve good performance on text ordering, summary coherence evaluation, and readability assessment.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning (2017, methodology): “t al. (2015). Outside the context of representation learning, there has been a good deal of work in NLP on discourse coherence, and on the particular tasks of sentence ordering and coherence scoring. Barzilay and Lapata (2008) provide thorough coverage of this work. 3 Discourse Inspired Objectives I”
Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators (2019, background): “• Entity Grid: Cervone et al. (2018); Barzilay and Lapata (2008) show that entities and DA transitions across turns can be strong features for assessing dialog coherence.”
Learning to Extract Coherent Summary via Deep Reinforcement Learning (2018, methodology): “One of the most popular methods is the entity grid model (Barzilay and Lapata 2008) The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)”
Learning Semantic Correspondences with Less Supervision (2009, methodology): “More sophisticated models of coherence could also be employed here (Barzilay and Lapata, 2008).”
A Hierarchical Neural Autoencoder for Paragraphs and Documents (2015, methodology): “, input documents in our tasks) are coherent (Barzilay and Lapata, 2008), we compare generated outputs with input documents in terms of how much original text order is preserved.”
Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints (2016, neutral): “Other work has used structure primarily to reorder summaries and ensure coherence (Barzilay et al., 2001; Barzilay and Lapata, 2008; Louis and Nenkova, 2012; Christensen et al., 2013) or to represent content for sentence fusion or abstraction (Thadani and McKeown, 2013; Pighin et al.”
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization (2019, methodology): “Finally, we use the entity-grid representation by Barzilay and Lapata (2008) and their coreference resolution rules to capture the entity distribution across summary sentences.”
Document Context Language Models (2015, methodology): “Therefore, we have the same computation procedure on perplexity for the models with and without contextual information.”
Mining Discourse Markers for Unsupervised Sentence Representation Learning (2019, background): “In the same vein, Logeswaran et al. (2016) propose to predict if two sentences are consecutive, even though such local coherence can be straightforwardly predicted with relatively shallow features (Barzilay and Lapata, 2008).”
A Model of Coherence Based on Distributed Sentence Representation (2014, methodology): “Entity grid models represent each sentence as a column of a grid of features and apply machine learning methods (e.g., SVM) to identify the coherent transitions based on entity features (for details of entity models see (Barzilay and Lapata, 2008)).”
What Context Features Can Transformer Language Models Use? (2021, background): “, 2016) and discourse representations in feature-based models (Barzilay and Lapata, 2008).”
Detecting Information-Dense Texts in Multiple News Domains (2014, background): “Prior work has shown that such features capture aspects of text readability and coherence (Barzilay and Lapata 2008; Lin, Ng, and Kan 2011), but no prior work has tested the extent to which such features correlate with writing style.”
Unsupervised Learning of Narrative Event Chains (2008, background): “, 1995) and other entity-based models of coherence (Barzilay and Lapata, 2005) in which an entity is in focus through a sequence of sentences.”
Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts (2019, background): “Evaluation has been among the most discussed topics of the natural language generation (NLG) research area (Lapata and Barzilay, 2005; Belz and Reiter, 2006; Reiter and Belz, 2006; Barzilay and Lapata, 2008; Reiter and Belz, 2009; Reiter, 2011; Novikova et al., 2017).”
IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP (2020, methodology): “For the second task, we propose a related but more complex task of thread message ordering, based on the sentence ordering task of Barzilay and Lapata (2008) to assess text relatedness.”
Recent automatic text summarization techniques: a survey (2016, background): “Other quality evaluation paradigms are local coherence (Barzilay and Lapata 2005), centering theory (Grosz et al.”
Cohere: A Toolkit for Local Coherence (2016, methodology): “Results for previous grid experiments (Barzilay and Lapata, 2008) were obtained from supervised training, whereby the parameters are trained on this same Earthquakes and Accidents corpus, then tested on a heldout section of the same dataset.”
Revisiting the Predictability of Language: Response Completion in Social Media (2012, background): “(Similar intuition has been explored in the context of text coherency (Barzilay and Lapata, 2005).)”
Automatic Evaluation of Linguistic Quality in Multi-Document Summarization (2010, methodology): “In addition, we investigate some models of gram-maticality (Chae and Nenkova, 2009) and coherence (Graesser et al., 2004; Soricut and Marcu, 2006; Barzilay and Lapata, 2008) from prior work (Sections 3.6 to 3.9).”