Results for "Mirella Lapata"

total 61took 0.07s
Language to Logical Form with Neural AttentionJan 06 2016Jun 06 2016Semantic parsing aims at mapping natural language to machine interpretable meaning representations. Traditional approaches rely on high-quality lexicons, manually-built templates, and linguistic features which are either domain- or representation-specific. ... More
Sentence Simplification with Deep Reinforcement LearningMar 31 2017Jul 16 2017Sentence simplification aims to make sentences easier to read and understand. Most recent approaches draw on insights from machine translation to learn simplification rewrites from monolingual corpora of complex and simple sentences. We address the simplification ... More
Hierarchical Transformers for Multi-Document SummarizationMay 30 2019In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner. We represent cross-document relationships ... More
Sentence Centrality Revisited for Unsupervised SummarizationJun 08 2019Single document summarization has enjoyed renewed interests in recent years thanks to the popularity of neural network models and the availability of large-scale datasets. In this paper we develop an unsupervised approach arguing that it is unrealistic ... More
Neural Summarization by Extracting Sentences and WordsMar 23 2016Jul 01 2016Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document ... More
Categorization in the Wild: Generalizing Cognitive Models to Naturalistic Data across LanguagesFeb 23 2019Categories such as animal or furniture are acquired at an early age and play an important role in processing, organizing, and communicating world knowledge. Categories exist across cultures: they allow to efficiently represent the complexity of the world, ... More
Text Summarization with Pretrained EncodersAug 22 2019Sep 05 2019Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how BERT can be usefully ... More
Text Summarization with Pretrained EncodersAug 22 2019Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how BERT can be usefully ... More
Coarse-to-Fine Decoding for Neural Semantic ParsingMay 12 2018Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Given an input utterance, ... More
Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly SupervisedAug 27 2018We present a neural framework for opinion summarization from online product reviews which is knowledge-lean and only requires light supervision (e.g., in the form of product domain labels and user-provided ratings). Our method combines two weakly supervised ... More
Neural Semantic Role Labeling with Dependency Path EmbeddingsMay 24 2016Jul 18 2016This paper introduces a novel model for semantic role labeling that makes use of neural sequence modeling techniques. Our approach is motivated by the observation that complex syntactic structures and related phenomena, such as nested subordinations and ... More
Weakly-supervised Neural Semantic Parsing with a Generative RankerAug 23 2018Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural parser-ranker ... More
Sentence Compression as Tree TransductionJan 15 2014This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. ... More
Bootstrapping Generators from Noisy DataApr 17 2018Mar 18 2019A core step in statistical data-to-text generation concerns learning correspondences between structured data representations (e.g., facts in a database) and associated texts. In this paper we aim to bootstrap generators from large scale datasets where ... More
Bootstrapping Generators from Noisy DataApr 17 2018Apr 18 2018A core step in statistical data-to-text generation concerns learning correspondences between structured data representations (e.g., facts in a database) and associated texts. In this paper we aim to bootstrap generators from large scale datasets where ... More
Dependency Parsing as Head SelectionJun 03 2016Jun 20 2016Conventional dependency parsers rely on a statistical model and a transition system or graph algorithm to enforce tree-structured outputs during training and inference. In this work we formalize dependency parsing as the problem of selecting the head ... More
Building a Neural Semantic Parser from a Domain OntologyDec 25 2018Semantic parsing is the task of converting natural language utterances into machine interpretable meaning representations which can be executed against a real-world environment such as a database. Scaling semantic parsing to arbitrary domains faces two ... More
Long Short-Term Memory-Networks for Machine ReadingJan 25 2016Sep 20 2016In this paper we address the question of how to render sequence-level networks better at handling structured input. We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning with memory ... More
Top-down Tree Long Short-Term Memory NetworksOct 31 2015Apr 03 2016Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have been successfully applied to a variety of sequence modeling tasks. In this paper we develop Tree Long Short-Term Memory (TreeLSTM), ... More
Generating Summaries with Topic Templates and Structured Convolutional DecodersJun 11 2019Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential ... More
Unsupervised Visual Sense Disambiguation for Verbs using Multimodal EmbeddingsMar 30 2016We introduce a new task, visual sense disambiguation for verbs: given an image and a verb, assign the correct sense of the verb, i.e., the one that describes the action depicted in the image. Just as textual word sense disambiguation is useful for a wide ... More
Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract ProgramsSep 09 2019Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained on utterance-denotation ... More
Dependency Parsing as Head SelectionJun 03 2016Dec 22 2016Conventional graph-based dependency parsers guarantee a tree structure both during training and inference. Instead, we formalize dependency parsing as the problem of independently selecting the head of each word in a sentence. Our model which we call ... More
Dependency Parsing as Head SelectionJun 03 2016Dec 02 2016Conventional graph-based dependency parsers guarantee a tree structure both during training and inference. Instead, we formalize dependency parsing as the problem of independently selecting the head of each word in a sentence. Our model which we call ... More
A Generative Parser with a Discriminative Recognition AlgorithmAug 01 2017Aug 17 2017Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models. We propose a framework for ... More
Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme SummarizationAug 27 2018We introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach. The idea is to create a short, one-sentence news summary answering the question "What ... More
Whodunnit? Crime Drama as a Case for Natural Language UnderstandingOct 31 2017In this paper we argue that crime drama exemplified in television programs such as CSI:Crime Scene Investigation is an ideal testbed for approximating real-world natural language understanding and the complex inferences associated with it. We propose ... More
Ranking Sentences for Extractive Summarization with Reinforcement LearningFeb 23 2018Apr 16 2018Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training ... More
Neural Extractive Summarization with Side InformationApr 14 2017Sep 10 2017Most extractive summarization methods focus on the main body of the document from which sentences need to be extracted. However, the gist of the document may lie in side information, such as the title and image captions which are often available for newswire ... More
Learning Structured Natural Language Representations for Semantic ParsingApr 27 2017Jun 14 2017We introduce a neural semantic parser that converts natural language utterances to intermediate representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains. The semantic ... More
Learning to Paraphrase for Question AnsweringAug 20 2017Question answering (QA) systems are sensitive to the many different ways natural language expresses the same information need. In this paper we turn to paraphrases as a means of capturing this knowledge and present a general framework which learns felicitous ... More
Learning an Executable Neural Semantic ParserNov 14 2017Aug 12 2018This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser generates tree-structured ... More
Universal Semantic ParsingFeb 10 2017Aug 28 2017Universal Dependencies (UD) offer a uniform cross-lingual syntactic representation, with the aim of advancing multilingual applications. Recent work shows that semantic parsing can be accomplished by transforming syntactic dependencies to logical forms. ... More
Autofolding for Source Code SummarizationMar 18 2014Feb 06 2016Developers spend much of their time reading and browsing source code, raising new opportunities for summarization methods. Indeed, modern code editors provide code folding, which allows one to selectively hide blocks of code. However this is impractical ... More
Text Generation from Knowledge Graphs with Graph TransformersApr 04 2019May 18 2019Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we address the problem ... More
Text Generation from Knowledge Graphs with Graph TransformersApr 04 2019Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we address the problem ... More
Weakly Supervised Domain DetectionJul 26 2019In this paper we introduce domain detection as a new natural language processing task. We argue that the ability to detect textual segments which are domain-heavy, i.e., sentences or phrases which are representative of and provide evidence for a given ... More
Multiple Instance Learning Networks for Fine-Grained Sentiment AnalysisNov 27 2017Jan 26 2018We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL). Our neural model is trained on document sentiment labels, and learns to predict the sentiment of text segments, i.e. sentences or elementary ... More
Learning Structured Text RepresentationsMay 25 2017Feb 03 2018In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural bias, we propose ... More
Cross-lingual Annotation Projection for Semantic RolesJan 15 2014This article considers the task of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We propose a general framework that is based on annotation projection, phrased as a graph optimization problem. It is relatively ... More
Informative and Controllable Opinion SummarizationSep 05 2019Opinion summarization is the task of automatically generating summaries for a set of opinions about a specific target (e.g., a movie or a product). Since the number of input documents can be prohibitively large, neural network-based methods sacrifice ... More
Movie Plot Analysis via Turning Point IdentificationAug 27 2019According to screenwriting theory, turning points (e.g., change of plans, major setback, climax) are crucial narrative moments within a screenplay: they define the plot structure, determine its progression and segment the screenplay into thematic units ... More
Data-to-Text Generation with Content Selection and PlanningSep 03 2018Apr 12 2019Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture ... More
Confidence Modeling for Neural Semantic ParsingMay 11 2018In this work we focus on confidence modeling for neural semantic parsers which are built upon sequence-to-sequence models. We outline three major causes of uncertainty, and design various metrics to quantify these factors. These metrics are then used ... More
Data-to-text Generation with Entity ModelingJun 07 2019Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning to select content ... More
What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural NetworksJul 19 2019We introduce 'extreme summarization', a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question ``What is the article about?''. We argue that extreme summarization, by nature, is not amenable ... More
Neural Latent Extractive Document SummarizationAug 22 2018Aug 28 2018Extractive summarization models require sentence-level labels, which are usually created heuristically (e.g., with rule-based methods) given that most summarization datasets only have document-summary pairs. Since these labels might be suboptimal, we ... More
Image Pivoting for Learning Multilingual Multimodal RepresentationsJul 24 2017In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding. Our model learns a common ... More
Autofolding for Source Code SummarizationMar 18 2014Mar 06 2017Developers spend much of their time reading and browsing source code, raising new opportunities for summarization methods. Indeed, modern code editors provide code folding, which allows one to selectively hide blocks of code. However this is impractical ... More
The speed of Arnold diffusionFeb 06 2013A detailed numerical study is presented of the slow diffusion (Arnold diffusion) taking place around resonance crossings in nearly integrable Hamiltonian systems of three degrees of freedom in the so-called `Nekhoroshev regime'. The aim is to construct ... More
Chaotic Spiral GalaxiesAug 30 2011We study the role of asymptotic curves in supporting the spiral structure of a N-body model simulating a barred spiral galaxy. Chaotic orbits with initial conditions on the unstable asymptotic curves of the main unstable periodic orbits follow the shape ... More
Building CX peanut-shaped disk galaxy profiles. The relative importance of the 3D families of periodic orbits bifurcating at the vertical 2:1 resonanceApr 17 2018We present and discuss the orbital content of a rather unusual rotating barred galaxy model, in which the three-dimensional (3D) family, bifurcating from x1 at the 2:1 vertical resonance with the known "frown-smile" side-on morphology, is unstable. Our ... More
Global and Local diffusion in the Standard MapJul 17 2018We study the global and the local transport and diffusion in the case of the standard map, by calculating the diffusion exponent $\mu$. In the global case we find that the mean diffusion exponent for the whole phase space is either $\mu=1$, denoting normal ... More
A Note on Generic ProjectionsOct 10 2002Let $X \subseteq {\bf P}^N ={\bf P}^{2n}_K$ be a subvariety of dimension $n$ and $P \in {\bf P}^N$ a generic point. If the tangent variety Tan$ X$ is equal to ${\bf P}^N$ then for generic points $x$, $y$ of $X$ the projective tangent spaces $t_xX$ and ... More
Periodic Orbits and Escapes in Dynamical SystemsMar 05 2012We study the periodic orbits and the escapes in two different dynamical systems, namely (1) a classical system of two coupled oscillators, and (2) the Manko-Novikov metric (1992) which is a perturbation of the Kerr metric (a general relativistic system). ... More
Analytical forms of chaotic spiral armsMar 30 2016We develop an analytical theory of chaotic spiral arms in galaxies. This is based on the Moser theory of invariant manifolds around unstable periodic orbits. We apply this theory to the chaotic spiral arms, that start from the neighborhood of the Lagrangian ... More
Characteristic times in the standard mapOct 26 2018We study and compare three characteristic times of the standard map, the Lyapunov time t_L, the Poincare recurrence time t_r and the stickiness (or escape) time t_{st}. The Lyapunov time is the inverse of the Lyapunov characteristic number LCN and in ... More
A randomized most powerful test to detect a cheater's action. Applicaton to identification of listeriosis in LombardyApr 01 2014Nov 08 2014This article presents a new randomized non-parametric test based on a sample of independent but not identically distributed variables; this test detects if a cheater replaces one of the distributions of the sample with a convex-dominating one. The presented ... More
A generalization of Kantorovich operators for convex compact subsetsMay 22 2016In this paper we introduce and study a new sequence of positive linear operators acting on function spaces defined on a convex compact subset. Their construction depends on a given Markov operator, a positive real number and a sequence of probability ... More
Computational Anatomy for Multi-Organ Analysis in Medical Imaging: A ReviewDec 20 2018The medical image analysis field has traditionally been focused on the development of organ-, and disease-specific methods. Recently, the interest in the development of more 20 comprehensive computational anatomical models has grown, leading to the creation ... More
A quick guide for student-driven community genome annotationMay 09 2018Oct 16 2018High quality gene models are necessary to expand the molecular and genetic tools available for a target organism, but these are available for only a handful of model organisms that have undergone extensive curation and experimental validation over the ... More