Search Results for author:
Found 97 papers, 49 papers with code
Split and Rephrase
We propose a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences.
Stock Movement Prediction from Tweets and Historical Prices
Stock movement prediction is a challenging problem: the market is highly stochastic, and we make temporally-dependent predictions from chaotic data.
Ranked #2 on
Stock Market Prediction
on stocknet
(using extra training data)
Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization
We introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach.
Ranked #9 on
Text Summarization
on X-Sum
What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks
We 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?''.
Ranking Sentences for Extractive Summarization with Reinforcement Learning
In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective.
Ranked #13 on
Extractive Text Summarization
on CNN / Daily Mail
Neural Extractive Summarization with Side Information
Most extractive summarization methods focus on the main body of the document from which sentences need to be extracted.
Whodunnit? Crime Drama as a Case for Natural Language Understanding
In 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.
An Incremental Parser for Abstract Meaning Representation
We describe a transition-based parser for AMR that parses sentences left-to-right, in linear time.
Ranked #5 on
AMR Parsing
on LDC2015E86
Discourse Representation Structure Parsing
We introduce an open-domain neural semantic parser which generates formal meaning representations in the style of Discourse Representation Theory (DRT; Kamp and Reyle 1993).
Multilingual Clustering of Streaming News
Clustering news across languages enables efficient media monitoring by aggregating articles from multilingual sources into coherent stories.
Structural Neural Encoders for AMR-to-text Generation
AMR-to-text generation is a problem recently introduced to the NLP community, in which the goal is to generate sentences from Abstract Meaning Representation (AMR) graphs.
Ranked #2 on
Graph-to-Sequence
on LDC2015E86:
The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python
Large Language Models (LLMs) have successfully been applied to code generation tasks, raising the question of how well these models understand programming.
Cross-lingual Abstract Meaning Representation Parsing
Abstract Meaning Representation (AMR) annotation efforts have mostly focused on English.
Jointly Extracting and Compressing Documents with Summary State Representations
We present a new neural model for text summarization that first extracts sentences from a document and then compresses them.
A Root of a Problem: Optimizing Single-Root Dependency Parsing
We describe two approaches to single-root dependency parsing that yield significant speed ups in such parsing.
Privacy-preserving Neural Representations of Text
This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection.
Compositional Languages Emerge in a Neural Iterated Learning Model
The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary.
Abstractive Summarization Guided by Latent Hierarchical Document Structure
Sequential abstractive neural summarizers often do not use the underlying structure in the input article or dependencies between the input sentences.
Large Language Models Relearn Removed Concepts
This demonstrates that models exhibit polysemantic capacities and can blend old and new concepts in individual neurons.
Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents
We argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers.
Ranked #1 on
Text Summarization
on GovReport
Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation
With the help of these strategies, we are able to train a model with fewer parameters while maintaining the model capacity.
LeanReasoner: Boosting Complex Logical Reasoning with Lean
Large language models (LLMs) often struggle with complex logical reasoning due to logical inconsistencies and the inherent difficulty of such reasoning.
Machine Reading of Historical Events
Machine reading is an ambitious goal in NLP that subsumes a wide range of text understanding capabilities.
Document Modeling with External Attention for Sentence Extraction
Document modeling is essential to a variety of natural language understanding tasks.
Learning Typed Entailment Graphs with Global Soft Constraints
We instead propose a scalable method that learns globally consistent similarity scores based on new soft constraints that consider both the structures across typed entailment graphs and inside each graph.
Detecting and Mitigating Hallucinations in Multilingual Summarisation
With the existing faithful metrics focusing on English, even measuring the extent of this phenomenon in cross-lingual settings is hard.
Are Large Language Models Temporally Grounded?
Instead, we provide LLMs with textual narratives and probe them with respect to their common-sense knowledge of the structure and duration of events, their ability to order events along a timeline, and self-consistency within their temporal model (e. g., temporal relations such as after and before are mutually exclusive for any pair of events).
Duality of Link Prediction and Entailment Graph Induction
The new entailment score outperforms prior state-of-the-art results on a standard entialment dataset and the new link prediction scores show improvements over the raw link prediction scores.
Co-training an Unsupervised Constituency Parser with Weak Supervision
We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence.
Ranked #5 on
Constituency Grammar Induction
on PTB Diagnostic ECG Database
(using extra training data)
Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs
In this paper, we introduce the new task of open-domain contextual link prediction which has access to both the textual context and the KG structure to perform link prediction.
Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
We describe a simple and effective method (Spectral Attribute removaL; SAL) to remove private or guarded information from neural representations.
Obfuscation for Privacy-preserving Syntactic Parsing
We introduce an idea for a privacy-preserving transformation on natural language data, inspired by homomorphic encryption.
Learning to Match Mathematical Statements with Proofs
The task is designed to improve the processing of research-level mathematical texts.
BERT is not The Count: Learning to Match Mathematical Statements with Proofs
While the first decoding method matches a proof to a statement without being aware of other statements or proofs, the second method treats the task as a global matching problem.
Knowledge Base Question Answering for Space Debris Queries
In this work we present a system, developed for the European Space Agency (ESA), that can answer complex natural language queries, to support engineers in accessing the information contained in a KB that models the orbital space debris environment.
The Role of Reentrancies in Abstract Meaning Representation Parsing
Abstract Meaning Representation (AMR) parsing aims at converting sentences into AMR representations.
Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
We present CEMA: Causal Explanations in Multi-Agent systems; a framework for creating causal natural language explanations of an agent's decisions in dynamic sequential multi-agent systems to build more trustworthy autonomous agents.
PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India
This paper introduces PMIndiaSum, a multilingual and massively parallel summarization corpus focused on languages in India.
Sentence-Incremental Neural Coreference Resolution
We propose a sentence-incremental neural coreference resolution system which incrementally builds clusters after marking mention boundaries in a shift-reduce method.
A Joint Matrix Factorization Analysis of Multilingual Representations
Using this tool, we study to what extent and how morphosyntactic features are reflected in the representations learned by multilingual pre-trained models.
Unlexicalized Transition-based Discontinuous Constituency Parsing
Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head (ii) bilexical statistics are crucial to solve ambiguities.
Discontinuous Constituency Parsing with a Stack-Free Transition System and a Dynamic Oracle
We introduce a novel transition system for discontinuous constituency parsing.
Semantic Role Labeling with Iterative Structure Refinement
Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on expressive sentence encoders (e. g., multi-layer LSTMs) but tend to model only local (if any) interactions between individual argument labeling decisions.
On the Trade-off between Redundancy and Local Coherence in Summarization
Extractive summarization systems are known to produce poorly coherent and, if not accounted for, highly redundant text.
AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite
We present the Granular AMR Parsing Evaluation Suite (GrAPES), a challenge set for Abstract Meaning Representation (AMR) parsing with accompanying evaluation metrics.
Canonical Correlation Inference for Mapping Abstract Scenes to Text
We describe a technique for structured prediction, based on canonical correlation analysis.
Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing
One of the limitations of semantic parsing approaches to open-domain question answering is the lexicosyntactic gap between natural language questions and knowledge base entries -- there are many ways to ask a question, all with the same answer.
Encoding Prior Knowledge with Eigenword Embeddings
Canonical correlation analysis (CCA) is a method for reducing the dimension of data represented using two views.
Optimizing Spectral Learning for Parsing
We describe a search algorithm for optimizing the number of latent states when estimating latent-variable PCFGs with spectral methods.
Parsing Linear Context-Free Rewriting Systems with Fast Matrix Multiplication
Our result provides another proof for the best known result for parsing mildly context sensitive formalisms such as combinatory categorial grammars, head grammars, linear indexed grammars, and tree adjoining grammars, which can be parsed in time $O(n^{4. 76})$.
Low-Rank Approximation of Weighted Tree Automata
We describe a technique to minimize weighted tree automata (WTA), a powerful formalisms that subsumes probabilistic context-free grammars (PCFGs) and latent-variable PCFGs.
Diversity in Spectral Learning for Natural Language Parsing
We describe an approach to create a diverse set of predictions with spectral learning of latent-variable PCFGs (L-PCFGs).
The Visualization of Change in Word Meaning over Time using Temporal Word Embeddings
We describe a visualization tool that can be used to view the change in meaning of words over time.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Abstract Meaning Representation for Paraphrase Detection
Abstract Meaning Representation (AMR) parsing aims at abstracting away from the syntactic realization of a sentence, and denote only its meaning in a canonical form.
Local String Transduction as Sequence Labeling
We show that the general problem of string transduction can be reduced to the problem of sequence labeling.
Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs
We describe an approach to speed-up inference with latent variable PCFGs, which have been shown to be highly effective for natural language parsing.
Empirical Risk Minimization with Approximations of Probabilistic Grammars
Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures.
Online Adaptor Grammars with Hybrid Inference
Adaptor grammars are a flexible, powerful formalism for defining nonparametric, unsupervised models of grammar productions.
Wide-Coverage Neural A* Parsing for Minimalist Grammars
Minimalist Grammars (Stabler, 1997) are a computationally oriented, and rigorous formalisation of many aspects of Chomsky{'}s (1995) Minimalist Program.
Discourse Representation Parsing for Sentences and Documents
We introduce a novel semantic parsing task based on Discourse Representation Theory (DRT; Kamp and Reyle 1993).
Partners in Crime: Multi-view Sequential Inference for Movie Understanding
Multi-view learning algorithms are powerful representation learning tools, often exploited in the context of multimodal problems.
Experimenting with Power Divergences for Language Modeling
In this paper, we experiment with several families (alpha, beta and gamma) of power divergences, generalized from the KL divergence, for learning language models with an objective different than standard MLE.
Discourse Representation Structure Parsing with Recurrent Neural Networks and the Transformer Model
Our best system achieves a score of 84. 8{\%} F1 in the DRS parsing shared task.
Ranked #2 on
DRS Parsing
on PMB-2.2.0
Bottom-Up Unranked Tree-to-Graph Transducers for Translation into Semantic Graphs
We propose a formal model for translating unranked syntactic trees, such as dependency trees, into semantic graphs.
Multi-Step Inference for Reasoning Over Paragraphs
Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives.
Learning Dialog Policies from Weak Demonstrations
Deep reinforcement learning is a promising approach to training a dialog manager, but current methods struggle with the large state and action spaces of multi-domain dialog systems.
Dscorer: A Fast Evaluation Metric for Discourse Representation Structure Parsing
Discourse representation structures (DRSs) are scoped semantic representations for texts of arbitrary length.
Nonparametric Learning of Two-Layer ReLU Residual Units
We describe an algorithm that learns two-layer residual units using rectified linear unit (ReLU) activation: suppose the input $\mathbf{x}$ is from a distribution with support space $\mathbb{R}^d$ and the ground-truth generative model is a residual unit of this type, given by $\mathbf{y} = \boldsymbol{B}^\ast\left[\left(\boldsymbol{A}^\ast\mathbf{x}\right)^+ + \mathbf{x}\right]$, where ground-truth network parameters $\boldsymbol{A}^\ast \in \mathbb{R}^{d\times d}$ represent a full-rank matrix with nonnegative entries and $\boldsymbol{B}^\ast \in \mathbb{R}^{m\times d}$ is full-rank with $m \geq d$ and for $\boldsymbol{c} \in \mathbb{R}^d$, $[\boldsymbol{c}^{+}]_i = \max\{0, c_i\}$.
Reducing Quantity Hallucinations in Abstractive Summarization
It is well-known that abstractive summaries are subject to hallucination---including material that is not supported by the original text.
A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing
In contrast, we treat both alignment and segmentation as latent variables in our model and induce them as part of end-to-end training.
Ranked #22 on
AMR Parsing
on LDC2017T10
Narration Generation for Cartoon Videos
Research on text generation from multimodal inputs has largely focused on static images, and less on video data.
Unsupervised Extractive Summarization by Human Memory Simulation
We introduce a wide range of heuristics that leverage cognitive representations of content units and how these are retained or forgotten in human memory.
Extractive Summarization
Unsupervised Extractive Summarization
Text Generation from Discourse Representation Structures
We propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs).
English-to-Chinese Transliteration with Phonetic Auxiliary Task
Approaching named entities transliteration as a Neural Machine Translation (NMT) problem is common practice.
Universal Discourse Representation Structure Parsing
Abstract We consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages.
Understanding Domain Learning in Language Models Through Subpopulation Analysis
We investigate how different domains are encoded in modern neural network architectures.
Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains
Although large language models (LLMs) exhibit remarkable capacity to leverage in-context demonstrations, it is still unclear to what extent they can learn new concepts or facts from ground-truth labels.
Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation
Knowledge-to-text generators often struggle to faithfully generate descriptions for the input facts: they may produce hallucinations that contradict the input, or describe facts not present in the input.
Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?
Also, we show that we can improve the controllability of LLMs with keyword-based classifier-free guidance (CFG) while achieving lexical overlap comparable to strong fine-tuned baselines on arXiv and PubMed.
`Keep it Together': Enforcing Cohesion in Extractive Summaries by Simulating Human Memory
Extractive summaries are usually presented as lists of sentences with no expected cohesion between them.
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
In this paper, we investigate the interplay between attention heads and specialized "next-token" neurons in the Multilayer Perceptron that predict specific tokens.
