Unsupervised Sentence Enhancement for Automatic Summarization (original) (raw)
Related papers
Abstractive Summarization Improved by WordNet-based Extractive Sentences
arXiv (Cornell University), 2018
Recently, the seq2seq abstractive summarization models have achieved good results on the CNN/Daily Mail dataset. Still, how to improve abstractive methods with extractive methods is a good research direction, since extractive methods have their potentials of exploiting various efficient features for extracting important sentences in one text. In this paper, in order to improve the semantic relevance of abstractive summaries, we adopt the WordNet based sentence ranking algorithm to extract the sentences which are most semantically to one text. Then, we design a dual attentional seq2seq framework to generate summaries with consideration of the extracted information. At the same time, we combine pointer-generator and coverage mechanisms to solve the problems of out-of-vocabulary (OOV) words and duplicate words which exist in the abstractive models. Experiments on the CNN/Daily Mail dataset show that our models achieve competitive performance with the state-of-theart ROUGE scores. Human evaluations also show that the summaries generated by our models have high semantic relevance to the original text.
Event-centric summary generation
2004
The Natural Language Processing Group at Microsoft Research participated in Task 2 of the Document Understanding Conference for the first time in 2004. Our primary interest is two-fold: 1) to explore an event-centric approach to summarization, 2) to explore a generation approach to summary realization.
2004
Automatic summaries of text generated through sentence or word extraction has been evaluated by comparing them with manual summaries generated by humans by using numerical evaluation measures based on precision or accuracy. Although sentence extraction has previously been evaluated based only on precision of a single sentence, sentence concatenations in the summaries should be evaluated as well. We have evaluated the appropriateness of sentence concatenations in summaries by using evaluation measures used for evaluating word concatenations in summaries through word extraction. We determined that measures considering sentence concatenation much better reflect the human judgment rather than those based only on the precision of a single sentence.
A Neural Attention Model for Abstractive Sentence Summarization
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015
Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary conditioned on the input sentence. While the model is structurally simple, it can easily be trained end-to-end and scales to a large amount of training data. The model shows significant performance gains on the DUC-2004 shared task compared with several strong baselines.
RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization
2021
Existing summarization systems mostly generate summaries purely relying on the content of the source document. However, even for humans, we usually need some references or exemplars to help us fully understand the source document and write summaries in a particular format. But how to find the high-quality exemplars and incorporate them into summarization systems is still challenging and worth exploring. In this paper, we propose RetrievalSum, a novel retrieval enhanced abstractive summarization framework consisting of a dense Retriever and a Summarizer. At first, several closely related exemplars are retrieved as supplementary input to help the generation model understand the text more comprehensively. Furthermore, retrieved exemplars can also play a role in guiding the model to capture the writing style of a specific corpus. We validate our method on a wide range of summarization datasets across multiple domains and two backbone models: BERT and BART. Results show that our framewor...
Corpus-trained text generation for summarization
2002
Abstract We explore how machine learning can be employed to learn rulesets for the traditional modules of content planning and surface realization. Our approach takes advantage of semantically annotated corpora to induce preferences for content planning and constraints on realizations of these plans. We applied this methodology to an annotated corpus of indicative summaries to derive constraint rules that can assist in generating summaries for new, unseen material.
Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation
2020
Summarizing texts is not a straightforward task. Before even considering text summarization, one should determine what kind of summary is expected. How much should the information be compressed? Is it relevant to reformulate or should the summary stick to the original phrasing? State-of-the-art on automatic text summarization mostly revolves around news articles. We suggest that considering a wider variety of tasks would lead to an improvement in the field, in terms of generalization and robustness. We explore meeting summarization: generating reports from automatic transcriptions. Our work consists in segmenting and aligning transcriptions with respect to reports, to get a suitable dataset for neural summarization. Using a bootstrapping approach, we provide pre-alignments that are corrected by human annotators, making a validation set against which we evaluate automatic models. This consistently reduces annotators’ efforts by providing iteratively better pre-alignment and maximizes...
What Have We Achieved on Text Summarization?
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Deep learning has led to significant improvement in text summarization with various methods investigated and improved ROUGE scores reported over the years. However, gaps still exist between summaries produced by automatic summarizers and human professionals. Aiming to gain more understanding of summarization systems with respect to their strengths and limits on a fine-grained syntactic and semantic level, we consult the Multidimensional Quality Metric 1 (MQM) and quantify 8 major sources of errors on 10 representative summarization models manually. Primarily, we find that 1) under similar settings, extractive summarizers are in general better than their abstractive counterparts thanks to strength in faithfulness and factual-consistency; 2) milestone techniques such as copy, coverage and hybrid extractive/abstractive methods do bring specific improvements but also demonstrate limitations; 3) pre-training techniques, and in particular sequence-to-sequence pre-training, are highly effective for improving text summarization, with BART giving the best results.
Unsupervised Semantic Abstractive Summarization
Proceedings of ACL 2018, Student Research Workshop
Automatic abstractive summary generation remains a significant open problem for natural language processing. In this work, we develop a novel pipeline for Semantic Abstractive Summarization (SAS). SAS, as introduced by Liu et al. (2015) first generates an AMR graph of an input story, through which it extracts a summary graph and finally, creates summary sentences from this summary graph. Compared to earlier approaches, we develop a more comprehensive method to generate the story AMR graph using state-ofthe-art co-reference resolution and Meta Nodes. Which we then use in a novel unsupervised algorithm based on how humans summarize a piece of text to extract the summary sub-graph. Our algorithm outperforms the state of the art SAS method by 1.7% F1 score in node prediction.
Generating Multi-Sentence Abstractive Summaries of Interleaved Texts
2019
In multi-participant postings, as in online chat conversations, several conversations or topic threads may take place concurrently. This leads to difficulties for readers reviewing the postings in not only following discussions but also in quickly identifying their essence. A two-step process, disentanglement of interleaved posts followed by summarization of each thread, addresses the issue, but disentanglement errors are propagated to the summarization step, degrading the overall performance. To address this, we propose an end-to-end trainable encoder-decoder network for summarizing interleaved posts. The interleaved posts are encoded hierarchically, i.e., word-to-word (words in a post) followed by post-to-post (posts in a channel). The decoder also generates summaries hierarchically, thread-to-thread (generate thread representations) followed by word-to-word (i.e., generate summary words). Additionally, we propose a hierarchical attention mechanism for interleaved text. Overall, o...