Summarization

In this paper, we describe a method for automatic creation of a knowledge source for text generation using information ex- traction over the Internet. We present a prototype system called …...

AbstractAmong the three main applications using multilinguality, i.e., information retrieval, summarization and text generation, the first one could be considered to be the core and the other two its supporting …...

This paper introduces a set of guidelines for annotating time expressions with a canonicalized representation of the times they refer to. Applications that can benefit from such an annotated corpus …...

While sentence extraction as an approach to summarization has been shown to work in docu- ments of certain genres, because of the conver- sational nature of email communication where utterances …...

Discovering the significant relations embedded in documents would be very useful not only for infor- mation retrieval but also for question answering and summarization. Prior methods for relation discov- ery, …...

The work presented in this paper is the first step in a project which aims to cluster and sum- marise electronic discussions in the context of help-desk applications. The eventual …...

We propose an approach to summarization exploiting both lexical information and the output of an automatic anaphoric re- solver, and using Singular Value Decom- position (SVD) to identify the main …...

This paper presents a hybrid approach to question answering in the clinical domain that combines techniques from summarization and information retrieval. We tackle a frequently-occurring class of questions that takes …...

Aligning sentences belonging to compa- rable monolingual corpora has been sug- gested as a first step towards training text rewriting algorithms, for tasks such as summarization or paraphrasing. We present …...

The task of selecting and ordering infor- mation appears in multiple contexts in text generation and summarization. For in- stance, methods for title generation con- struct a headline by selecting …...

While speaking spontaneously, speakers often make errors such as self-correction or false starts which interfere with the successful application of natural language processing techniques like summarization and machine translation to …...

AbstractThis paper presents two corpora produced within the RPM2 project: a multi-document summarization corpus and a sentence compression corpus. Both corpora are in French. The first one is the only …...

Determining whether two terms in text have an ancestor relation (e.g. Toyota and car) or a sibling relation (e.g. Toyota and Honda) is an essential component of textual inference in …...

. In this study, our purpose was to make a short summary for sentences. For ex- ample, we aimed to make a short summary “terror” for sentences “A bomb went …...

AbstractWe describe a set of tools, resources, and experiments for opinion classification in business-related datasources in two languages. In particular we concentrate on SentiWordNet text interpretation to produce word, sentence, …...

AbstractAt present there is no publicly available data set to evaluate the performance of different summarization systems on the task of generating location-related extended image captions. In this paper we …...

ive Summarization of Highly Redundant Opinions Kavita Ganesan and ChengXiang Zhai and Jiawei Han Department of Computer Science University of Illinois at Urbana-Champaign {kganes2,czhai,hanj}@cs.uiuc.edu Abstract We present a novel graph-based …...

The ability to accurately determine temporal relations between events is an important task for several natural language processing applications such as Question Answering, Summarization, and Information Extraction. Since current supervised …...

In most summarization approaches, sentence ranking plays a vital role. Most previous work ex- plored different features and combined them into unified ranking methods. However, it would be imprecise to …...

Most existing learning to rank based summarization methods only used content relevance of sentences with respect to queries to rank or estimate sentences, while neglecting sentence relationships. In our work, …...

Citations are a valuable resource for characterizing scientific publications that has already been used in applications such as summarization and information retrieval. These applications could be even better served by …...

Information structure, i.e the way speakers construct sentences to present new information in the context of old, can capture rich linguistic information about the discourse structure of scientific documents. Information …...

We present a method which exploits auto- matically generated scientific discourse an- notations to create a content model for the summarisation of scientific articles. Full pa- pers are first automatically …...

AbstractThis paper introduces a new email dataset, consisting of both single and thread emails, manually annotated with summaries and keywords. A total of 349 emails and threads have been annotated. …...

AbstractIn this paper we first introduce the working context related to the understanding of an heterogeneous network of references contained in the Italian regulatory framework. We then present an extended …...

Statistical language modeling (LM) that purports to quantify the acceptability of a given piece of text has long been an in- teresting yet challenging research area. In particular, language modeling …...

Despite the convexity of structured max- margin objectives (Taskar et al., 2004; Tsochantaridis et al., 2004), the many ways to optimize them are not equally ef- fective in practice. We …...

A microblog repost tree provides strong clues on how an event described therein develops. To help social media users capture the main clues of events on mi- croblogging sites, we …...

AbstractSummarization aims to represent source documents by a shortened passage. Existing methods focus on the extraction of key information, but often neglect coherence. Hence the generated summaries suffer from a …...

Tasks such as knowledge extraction, text simplification and summarization have in common the fact that from a text fragment a smaller (not necessarily contiguous) portion is obtained by discarding part …...

AbstractSummarizing a document requires identifying the important parts of the document with an objective of providing a quick overview to a reader. However, a long article can span several topics …...

The pyramid method is a content analysis approach in automatic summarization evaluation for manual construction of a content model from reference summaries, and manual scoring of unseen summaries with the …...

AbstractSeq2seq learning has produced promising results on summarization. However, in many cases, system summaries still struggle to keep the meaning of the original intact. They may miss out important words …...

AbstractDespite the recent developments on neural summarization systems, the underlying logic behind the improvements from the systems and its corpus-dependency remains largely unexplored. Position of sentences in the original text, …...

AbstractWe address the task of assessing discourse coherence, an aspect of text quality that is essential for many NLP tasks, such as summarization and language assessment. We propose a hierarchical …...

AbstractHow can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not catch models …...

Identifying argument components has become an important area of research in argument mining. When argument components are identified, they can not only be used for stance classification but also can …...

AbstractPodcasts are a large and growing repository of spoken audio. As an audio format, podcasts are more varied in style and production type than broadcast news, contain more genres than …...

AbstractAutomatic definition extraction from texts is an important task that has numerous applications in several natural language processing fields such as summarization, analysis of scientific texts, automatic taxonomy generation, ontology …...

AbstractThe performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of …...

AbstractWe present FELIX – a flexible text-editing approach for generation, designed to derive maximum benefit from the ideas of decoding with bi-directional contexts and self-supervised pretraining. In contrast to conventional …...

AbstractIdentifying the key events in a document is critical to holistically understanding its important information. Although measuring the salience of events is highly contextual, most previous work has used a …...

AbstractIn this paper, we introduce a large-scale Indonesian summarization dataset. We harvest articles from Liputan6.com, an online news portal, and obtain 215,827 document–summary pairs. We leverage pre-trained language models to …...

AbstractCross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate -> summarize or …...

AbstractModeling content importance is an essential yet challenging task for summarization. Previous work is mostly based on statistical methods that estimate word-level salience, which does not consider semantics and larger …...

AbstractRST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate …...

AbstractTask-agnostic pretraining objectives like masked language models or corrupted span prediction are applicable to a wide range of NLP downstream tasks (Raffel et al.,2019), but are outperformed by task-specific pretraining …...

AbstractAtomic clauses are fundamental text units for understanding complex sentences. Identifying the atomic sentences within complex sentences is important for applications such as summarization, argument mining, discourse analysis, discourse parsing, …...

Argumentation is an important tool within hu- man interaction, not only in law and politics but also for discussing issues, expressing and exchanging opinions and coming to decisions in our …...

AbstractA new metric BaryScore to evaluate text generation based on deep contextualized embeddings (e.g., BERT, Roberta, ELMo) is introduced. This metric is motivated by a new framework relying on optimal …...

AbstractRecent work learns contextual representations of source code by reconstructing tokens from their context. For downstream semantic understanding tasks like code clone detection, these representations should ideally capture program functionality. …...

AbstractNatural language generation (NLG) tasks on pro-drop languages are known to suffer from zero pronoun (ZP) problems, and the problems remain challenging due to the scarcity of ZP-annotated NLG corpora. …...

Natural language inference (NLI) is formu- lated as a unified framework for solving vari- ous NLP problems such as relation extraction, question answering, summarization, etc. It has been studied intensively …...

AbstractGenerating long and coherent text is an important and challenging task encompassing many application areas such as summarization, document level machine translation and story generation. Despite the success in modeling …...

AbstractProviding pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, …...

AbstractProfessional summaries are written with document-level information, such as the theme of the document, in mind. This is in contrast with most seq2seq decoders which simultaneously learn to focus on …...

AbstractTo assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and manual literature review. NLP systems can help to automate or assist in parts of this expensive …...

AbstractNarrative analysis is becoming increasingly important for a number of linguistic tasks including summarization, knowledge extraction, and question answering. We present a novel approach for narrative event representation using attention …...

Sequence-to-sequence models usually transfer all encoder outputs to the decoder for genera- tion. In this work, by contrast, we hypothesize that these encoder outputs can be compressed to shorten the …...

AbstractPrevious work indicates that discourse information benefits summarization. In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained neural …...

AbstractFine-tuning is the de facto way of leveraging large pretrained language models for downstream tasks. However, fine-tuning modifies all the language model parameters and therefore necessitates storing a full copy …...

AbstractMany NLG tasks such as summarization, dialogue response, or open domain question answering, focus primarily on a source text in order to generate a target response. This standard approach falls …...

AbstractAlthough coherence modeling has come a long way in developing novel models, their evaluation on downstream applications for which they are purportedly developed has largely been neglected. With the advancements …...

AbstractTransformer models have achieved state-of-the-art results in a wide range of NLP tasks including summarization. Training and inference using large transformer models can be computationally expensive. Previous work has focused …...

AbstractScientific literature serves as a high-quality corpus, supporting a lot of Natural Language Processing (NLP) research. However, existing datasets are centered around the English language, which restricts the development of …...

AbstractFast and reliable evaluation metrics are key to R&D progress. While traditional natural language generation metrics are fast, they are not very reliable. Conversely, new metrics based on large pretrained …...

AbstractOne of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text. In this study, we reinterpret the decoder overconfidence-regularizing …...

AbstractCurrent pre-trained models applied for summarization are prone to factual inconsistencies that misrepresent the source text. Evaluating the factual consistency of summaries is thus necessary to develop better models. However, …...

AbstractTraditionally, Text Simplification is treated as a monolingual translation task where sentences between source texts and their simplified counterparts are aligned for training. However, especially for longer input documents, summarizing …...

AbstractSummarization of legal case judgement documents is a challenging problem in Legal NLP. However, not much analyses exist on how different families of summarization models (e.g., extractive vs. abstractive) perform …...

AbstractSummaries, keyphrases, and titles are different ways of concisely capturing the content of a document. While most previous work has released the datasets of keyphrases and summarization separately, in this …...

AbstractConditional neural text generation models generate high-quality outputs, but often concentrate around a mode when what we really want is a diverse set of options. We present a search algorithm …...

AbstractCurrent medical question answering systems have difficulty processing long, detailed and informally worded questions submitted by patients, called Consumer Health Questions (CHQs). To address this issue, we introduce a medical …...

AbstractSeveral popular Transformer based language models have been found to be successful for text-driven brain encoding. However, existing literature leverages only pretrained text Transformer models and has not explored the …...

AbstractIn this paper, we explore the challenging problem of performing a generative task in a target language when labeled data is only available in English, using summarization as a case …...

AbstractThis paper aims for a potential architectural improvement for multilingual learning and asks: Can different tasks from different languages be modeled in a monolithic framework, i.e. without any task/language-specific module? …...

AbstractTeacher-forcing is widely used in training sequence generation models to improve sampling efficiency and to stabilize training. However, teacher-forcing is vulnerable to the exposure bias problem. Previous works have attempted …...

AbstractA document can be summarized in a number of ways. Reference-based evaluation of summarization has been criticized for its inflexibility. The more sufficient the number of abstracts, the more accurate …...

AbstractNLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild. We introduce SCROLLS, …...

AbstractModel-based, reference-free evaluation metricshave been proposed as a fast and cost-effectiveapproach to evaluate Natural Language Generation(NLG) systems. Despite promising recentresults, we find evidence that reference-freeevaluation metrics of summarization and dialoggeneration …...

AbstractSummarization datasets are often assembled either by scraping naturally occurring public-domain summaries—which are nearly always in difficult-to-work-with technical domains—or by using approximate heuristics to extract them from everyday text—which frequently …...

AbstractWe introduce Textstar, a graph-based summarization and keyphrase extraction system that builds a document graph using only lemmatization and POS tagging. The document graph aggregates connections between lemma and sentence …...

AbstractMany language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to further progress, but ensembling …...

AbstractMany text generation applications require the generated text to be factually consistent with input information. Automatic evaluation of factual consistency is challenging. Previous work has developed various metrics that often …...

AbstractInformation extraction (IE) and summarization are closely related, both tasked with presenting a subset of the information contained in a natural language text. However, while IE extracts structural representations, summarization …...

AbstractOne of the major problems with text simplification is the lack of high-quality data. The sources of simplification datasets are limited to Wikipedia and Newsela, restricting further development of this …...

AbstractLarge language models (LLMs) and generative AI have emerged as the most important areas in the field of natural language processing (NLP). LLMs are considered to be a key component …...

AbstractIn this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating …...

AbstractWith the ubiquitous use of online meeting platforms and robust automatic speech recognition systems, meeting transcripts have emerged as a promising domain for natural language tasks. Most recent works on …...

AbstractThe integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic …...

AbstractDespite their unprecedented success, even the largest language models make mistakes. Similar to how humans learn and improve using feedback, previous work proposed providing language models with natural language feedback …...

AbstractSpoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker …...