Proceedings of the 2nd Workshop on New Frontiers in Summarization

15 papers
Answering Naturally: Factoid to Full length Answer Generation (D19-54)

Copied to clipboard

Challenge: Factoid question answering systems extract answers for a question from passages, which are usually short spans of text . but, these spans would result in an unnatural reading experience in a conversational system . a pointer generator based full-length answer generator can be used with most QA systems .
Approach: They propose a pointer generator based full-length answer generator which can be used with most QA systems.
Outcome: The proposed system generates full length answer without relying on passage from which it was extracted.
Summary Level Training of Sentence Rewriting for Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing models rely on sentence-level rewards or suboptimal labels to achieve summary-level ROUGE scores.
Approach: They propose a model that extracts salient sentences from a document and paraphrases them to generate a summary.
Outcome: The proposed model improves on CNN/Daily Mail and New York Times datasets.
Abstractive Timeline Summarization (D19-54)

Copied to clipboard

Challenge: Prior approaches to TLS focus on extractive methods, which generate extractive timelines . a study with human judges shows that our abstractive system also produces output that is easy to read and understand.
Approach: They propose an abstractive timeline summarization system that is unsupervised . their system outperforms extractive systems in terms of ROUGE scores .
Outcome: The proposed system outperforms extractive systems in terms of ROUGE scores . it produces output that is easy to read and understand, the authors say .
Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization (D19-54)

Copied to clipboard

Challenge: Existing methods for summarizing documents rely on hand-crafted features or additional annotated data.
Approach: They propose a method that makes use of two types of sentence embeddings . the method uses universal embeddable and domain-specific embeddible features .
Outcome: The proposed method achieves competitive results on two types of summary, consisting of 665 bytes and 100 words.
Unsupervised Aspect-Based Multi-Document Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing methods for opinion summarization are expensive and do not deal with contradictory statements.
Approach: They propose an unsupervised abstractive summarization neural system that generates short summaries of reviews in a vector space.
Outcome: The proposed system can generate short summaries of user-generated reviews in a short paragraph, while nobody reads all reviews.
BillSum: A Corpus for Automatic Summarization of US Legislation (D19-54)

Copied to clipboard

Challenge: In the US Congress, over 10,000 bills are introduced each year, with state legislatures introducing tens of thousands of bills.
Approach: They introduce the first dataset for summarizing US Congressional and California state bills . they demonstrate that models built on Congressional bills can be used to summarize California billa .
Outcome: The proposed summarization methods can be applied to states without human-written summaries.
An Editorial Network for Enhanced Document Summarization (D19-54)

Copied to clipboard

Challenge: Existing extractive and abstractive summarization methods are less fluent, coherent and readable, whereas extractive methods are sensitive to vocabulary size, making them more difficult to train and generalize.
Approach: They propose an approach which uses a combination of extractive and abstractive methods to combine a given sequence of sentences into a short version.
Outcome: The proposed method is compared with state-of-the-art methods using extractive-only or abstractive- only baselines.
Towards Annotating and Creating Summary Highlights at Sub-sentence Level (D19-54)

Copied to clipboard

Challenge: Creating summary highlights at the sub-sentence level is desirable because sub-entrances are more concise than whole sentences.
Approach: They propose to annotate summary-worthy sub-sentences and teach classifiers to do the same . they frame task as selecting important sentences and identifying a single most informative textual unit from each sentence.
Outcome: The proposed method reduces the complexity involved in sentence compression by reducing the number of words and phrases deleted.
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing work on abstractive dialogue summarizations has focused on news summarizing but there is no such comprehensive dataset.
Approach: They propose to use a chat-dialogues corpus with abstractive dialogue summaries to generate a short version of text that covers the main points succinctly.
Outcome: The proposed dataset achieves higher ROUGE scores than the model-generated summaries of news, compared with human evaluators' judgement.
A Closer Look at Data Bias in Neural Extractive Summarization Models (D19-54)

Copied to clipboard

Challenge: In this paper, we examine the generalization behaviour of summarization models . we propose several properties of datasets that matter for generalization .
Approach: They propose several properties of datasets which matter for generalization of summarization models.
Outcome: The proposed approach improves the state-of-the-art model by rethinking the model design process on a typical dataset.
Global Voices: Crossing Borders in Automatic News Summarization (D19-54)

Copied to clipboard

Challenge: a crowd-sourced dataset is needed to evaluate cross-lingual summarization methods . human-written summarizing is expensive and difficult to design for humans .
Approach: They construct a multilingual dataset for evaluating cross-lingual summarization methods . they use social-network descriptions of news articles to extract evaluation data .
Outcome: The proposed dataset compares a translate-then-summarize approach with baselines in 15 languages.
Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations (D19-54)

Copied to clipboard

Challenge: Determinantal point processes (DPP) is one of the best performing techniques for extractive summarization.
Approach: They propose to combine determinantal point processes with surface indicators for effective identification of summary-worthy sentences.
Outcome: The determinantal point processes (DPP) framework is one of the best performing in summarization competitions.
Analyzing Sentence Fusion in Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Abstractive summarization systems struggle to combine information from multiple sources, resulting in poor grammar and incorrect facts.
Approach: They analyze the outputs of five abstractive summarization systems and examine their grammatical accuracy and faithfulness.
Outcome: The proposed summarization systems are able to combine information from multiple sources, but they often fail to remain faithful to the original document.
Summarizing Relationships for Interactive Concept Map Browsers (D19-54)

Copied to clipboard

Challenge: Concept maps are visual summaries, structured as directed graphs . initial attempts to generate static summary models focused on static summarization . however, in interactive settings, users will need to dynamically query relationships .
Approach: They propose a model which returns a labeled summary of a query concept for display in a visual interface.
Outcome: The proposed model can summarize relationships between two query concepts in a visual network . it is based on a new dataset, and is trained on the dataset .
Exploiting Discourse-Level Segmentation for Extractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing approaches to extract summarize text are based on sentences as the elementary unit, but semantic segments containing supplementary information or descriptive details are often nonessential in the generated summaries.
Approach: They propose to exploit discourse-level segmentation as a finer-grained means to more precisely pinpoint the core content in a document.
Outcome: The proposed method improves extractive summarization performance on CNN/Daily Mail dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations