Probabilistic Text Structuring: Experiments with Sentence Ordering

By Mirella Lapata. Annual Meeting of the Association for Computational Linguistics, 2003

330 citations recorded by the source corpus.

Ordering information is a critical task for natural language generation applications. In this paper we propose an approach to information ordering that is particularly suited for text-to-text generation. We describe a model that learns constraints on sentence order from a corpus of domain-specific texts and an algorithm that yields the most likely order among several alternatives. We evaluate the automatically generated orderings against authored texts from our corpus and against human subjects that are asked to mimic the model's task. We also assess the appropriateness of such a model for multidocument summarization.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/ec6c09bbf13a08e8fcc901e334e2aae20821727b

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

Citations in the corpus

Individual and Domain Adaptation in Sentence Planning for Dialogue (2007, methodology): “This work does not look at individual differences.”
Neural Net Models for Open-Domain Discourse Coherence (2016, methodology): “We therefore use Kendall’s Tau (Lapata, 2003; Lapata, 2006), a metric of rank correlation for evaluation.”
Automatic Text Summarization: Past, Present and Future (2013, background): “It tries to find a locally optimal order by learning ordering constraints for pairs of sentences [27].”
Modeling Local Coherence: An Entity-Based Approach (2005, background): “Text structuring algorithms (Lapata, 2003; Barzi-lay and Lee, 2004; Karamanis et al., 2004) are commonly evaluated by their performance at information-ordering.”
A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization (2006, methodology): “Even though we could not compare our experiment with the probabilistic approach (Lapata, 2003) directly due to the difference of the text corpora, the Kendall coefficient reported higher agreement than Lapata’s experiment (Kendall=0.48 with lemmatized nouns and Kendall=0.56 with verb-noun…”
Exploring Content Models for Multi-Document Summarization (2009, background): “In this task we assume a document collection D consisting of documents D 1 , . . . , D n describing the same (or closely related) narrative (Lapata, 2003). set of events.”
Automatic Evaluation of Linguistic Quality in Multi-Document Summarization (2010, background): “Word co-occurrence patterns across adjacent sentences provide a way of measuring local coherence that is not linguistically informed but which can be easily computed using large amounts of unan-notated text (Lapata, 2003; Soricut and Marcu, 2006).”
Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring? (2018, background): “Methods focused on training individual modules for content selection and linearization (Marcu, 1997; Lapata, 2003; Barzilay and Lapata, 2005), and trainable sentence planning for discourse structure and aggregation operations (Stent”
Story Comprehension for Predicting What Happens Next (2017, background): “ing topic drift within a domain (Barzilay and Lee, 2004; Fung and Ngai, 2006), co-occurrence of words (Lapata, 2003; Soricut and Marcu, 2006), syntactic patterns (Louis and Nenkova, 2012) and discourse relations (Pitler and Nenkova, 2008; Lin”
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation (2019, neutral): “Lapata (2003) devised a probabilistic model for sentence ordering which correlated well with human ordering.”
Neural Sentence Ordering (2016, background): “Lapata (2003) proposed a probabilistic model that assumes the probability of any given sentence is determined by its adjacent sentence and learns constraints on sentence order from a corpus of domain speciﬁc texts.”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, methodology): “Other metrics for measuring fluency [15, 123, 42], consistency [48, 86], readability [85], and informativeness [67] can also be used in evaluating the natural language output of CRS models.”
Graph-based Neural Multi-Document Summarization (2017, background): “Optionally, sentence reordering (Lapata, 2003; Barzilay et al., 2001) can follow to improve coherence of the summary.”
Sentence Ordering using Recurrent Neural Networks (2016, neutral): “Lapata (2006) discusses that this metric reliably correlates with human judgements.”
Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization (2004, methodology): “Furthermore, to provide some assessment of the quality of the predicted orderings themselves, we follow Lapata (2003) in employing Kendall’s τ , which is a measure of how much an ordering differs from the OSO— the underlying assumption is that most reasonable sentence orderings should be fairly…”
Evaluation of Text Generation: A Survey (2020, background): “• Readability and Fluency, associated with non-redundancy, are linguistic quality metrics used to measure how repetitive the generated summary is and how many spelling and grammar errors there are in the generated summary (Lapata, 2003).”