Sentence Compression Beyond Word Deletion

By Trevor Cohn, Mirella Lapata. 2008

187 citations recorded by the source corpus.

In this paper we generalise the sentence compression task. Rather than simply shorten a sentence by deleting words or constituents, as in previous work, we rewrite it using additional operations such as substitution, reordering, and insertion. We present a new corpus that is suited to our task and a discriminative tree-to-tree transduction model that can naturally account for structural and lexical mismatches. The model incorporates a novel grammar extraction method, uses a language model for coherent output, and can be easily tuned to a wide range of compression specific loss functions.

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

Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond (2016, methodology): “, 2000), compression using weighted tree-transformation rules (Cohn and Lapata, 2008) and quasi-synchronous grammar approaches (Woodsend et al.”
A Neural Attention Model for Abstractive Sentence Summarization (2015, background): “More recently, Cohn and Lapata (2008) give a compression method which allows for more arbitrary transformations.”
Abstractive Sentence Summarization with Attentive Recurrent Neural Networks (2016, background): “More recently Cohn and Lapata (2008) and later Woodsend et al. (2010) proposed systems which made heavy use of the syntactic features of the sentence-summary pairs.”
TreeTalk: Composition and Compression of Trees for Image Descriptions (2014, background): “Much work has considered deletion-only edits like ours (Knight and Marcu, 2000; Turner and Charniak, 2005; Cohn and Lapata, 2007; Filippova and Altun, 2013), while recent ones explore more complex edits, such as substitutions, insertions and reordering (Cohn and Lapata, 2008).”
Controlling Output Length in Neural Encoder-Decoders (2016, background): “There are also several studies of abstractive sentence summarization using syntactic transduction (Cohn and Lapata, 2008; Napoles et al., 2011) or taking a phrase-based statistical machine translation approach (Banko et al.”
Sentence Compression by Deletion with LSTMs (2015, methodology): “A more complex translation model is also conceivable and may signiﬁcantly advance work on compression by paraphrasing, of which there have not been many examples yet (Cohn & Lapata, 2008).”
Benchmarking Large Language Models for News Summarization (2023, background): “Many automatic metrics have been proposed (Lin, 2004; Zhang* et al., 2020; Sellam et al., 2020; Durmus et al., 2020; Maynez et al., 2020; Deutsch and Roth, 2021) but they do not always correlate with human evaluation of summarization systems (Fab-bri et al., 2020; Durmus et al., 2022).”
Generalizing Image Captions for Image-Text Parallel Corpus (2013, background): “, Cohn and Lapata (2008), Cordeiro et al.”
Towards Understanding Neural Machine Translation with Word Importance (2019, background): “• Deletion perturbation removes the selected words from the input sentence, and it can be regarded as a specific instantiation of sentence compression (Cohn and Lapata, 2008).”
Unsupervised Sentence Compression using Denoising Auto-Encoders (2018, background): “Past models for sentence compression have tended to rely heavily on strong linguistic priors such as syntactic rules or heuristics (Dorr et al., 2003; Cohn and Lapata, 2008).”
Split and Rephrase (2017, background): “Sentence compression rewrites an input sentence into a shorter paraphrase (Knight and Marcu, 2000; Cohn and Lapata, 2008; Filippova and Strube, 2008; Pitler, 2010; Filippova et al., 2015; Toutanova et al., 2016).”
A Survey of Paraphrasing and Textual Entailment Methods (2009, background): “Sentence compression (Knight & Marcu, 2002; McDonald, 2006; Cohn & Lapata, 2008; Clarke & Lapata, 2008; Cohn & Lapata, 2009; Galanis & Androutsopoulos, 2010), often also a processing stage of text summarization, can be seen as a special case of sentence paraphrasing, as suggested by 3Culicover…”
Title Generation with Quasi-Synchronous Grammar (2010, background): “An alternative abstractive or “bottom-up” approach involves identifying high-interest words and phrases in the source text, and combining them into new sentences guided by a language model (Banko et al., 2000; Soricut and Marcu, 2007).”
Unsupervised Sentence Enhancement for Automatic Summarization (2014, background): “A relatively large body of work exists in sentence compression (Knight and Marcu, 2000; McDon-ald, 2006; Galley and McKeown, 2007; Cohn and Lapata, 2008; Clarke and Lapata, 2008, inter alia), and sentence fusion (Barzilay and McK-eown, 2005; Marsi and Krahmer, 2005; Filippova and Strube, 2008;…”
Global Encoding for Abstractive Summarization (2018, methodology): “Researchers developed many statistical methods and linguistic-rule-based methods to study automatic summarization (Banko et al., 2000; Dorr et al., 2003; Zajic et al., 2004; Cohn and Lapata, 2008).”
A New Annotated Portuguese/Spanish Corpus for the Multi-Sentence Compression Task (2018, methodology): “Cohn and Lapata (2008) and Toutanova et al. (2016) describe two manually created ab-stractive compression corpora that are publicly available.”
UvA-DARE (Digital Academic Repository) A Dataset and Evaluation Metrics for Abstractive Compression of Sentences and Short Paragraphs (unknown): “…programing approach for deletion-based compression (Clarke and Lapata, 2008), (2) T3, a tree transducer-based model for abstractive compression (Cohn and Lapata, 2008), (3) Seq2seq, a neural network model for deletion-based compression (Filippova et al., 2015), and (4) NAMAS, a neural model…”
Soylent: a word processor with a crowd inside (2010, background): “Shortn’s approach, which can rewrite or cut parts of sentences, is an example of sentence compression, an area of active recent research [5, 12] that suffers from a lack of training data [4].”
Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention (2019, methodology): “There are various methods exploring the effective way to model the monolingual ASSUM process including statistical models (Banko et al., 2000; Cohn and Lapata, 2008) or neural models (Rush et al., 2015; Chopra et al., 2016; Nallapati et al., 2016).”