Search Results for author:
Found 176 papers, 78 papers with code
Evaluating Machine Reading Systems through Comprehension Tests
The evaluation architecture is completely multilingual: test documents, questions, and their answers are identical in all the supported languages.
Detecting Subevent Structure for Event Coreference Resolution
First, we introduce a multiclass logistic regression model that can detect subevent relations in addition to full coreference.
A Corpus of Participant Roles in Contentious Discussions
In this paper, we present a new corpus for social roles in online contentious discussions.
Supervised Within-Document Event Coreference using Information Propagation
Event coreference is an important task for full text analysis.
What a Nasty day: Exploring Mood-Weather Relationship from Twitter
While it has long been believed in psychology that weather somehow influences human's mood, the debates have been going on for decades about how they are correlated.
Retrofitting Word Vectors to Semantic Lexicons
Vector space word representations are learned from distributional information of words in large corpora.
The NLP Engine: A Universal Turing Machine for NLP
It is commonly accepted that machine translation is a more complex task than part of speech tagging.
Visualizing and Understanding Neural Models in NLP
While neural networks have been successfully applied to many NLP tasks the resulting vector-based models are very difficult to interpret.
Reflections on Sentiment/Opinion Analysis
In this paper, we described possible directions for deeper understanding, helping bridge the gap between psychology / cognitive science and computational approaches in sentiment/opinion analysis literature.
TabMCQ: A Dataset of General Knowledge Tables and Multiple-choice Questions
We describe two new related resources that facilitate modelling of general knowledge reasoning in 4th grade science exams.
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing.
Ranked #7 on
Named Entity Recognition (NER)
on CoNLL++
Unsupervised Ranking Model for Entity Coreference Resolution
Coreference resolution is one of the first stages in deep language understanding and its importance has been well recognized in the natural language processing community.
Harnessing Deep Neural Networks with Logic Rules
Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models.
Ranked #65 on
Sentiment Analysis
on SST-2 Binary classification
Edit Categories and Editor Role Identification in Wikipedia
In this work, we introduced a corpus for categorizing edit types in Wikipedia.
Dropout with Expectation-linear Regularization
Algorithmically, we show that our proposed measure of the inference gap can be used to regularize the standard dropout training objective, resulting in an \emph{explicit} control of the gap.
Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks
Curriculum Learning emphasizes the order of training instances in a computational learning setup.
Neural Probabilistic Model for Non-projective MST Parsing
In this paper, we propose a probabilistic parsing model, which defines a proper conditional probability distribution over non-projective dependency trees for a given sentence, using neural representations as inputs.
Calibrating Energy-based Generative Adversarial Networks
In this paper, we propose to equip Generative Adversarial Networks with the ability to produce direct energy estimates for samples. Specifically, we propose a flexible adversarial training framework, and prove this framework not only ensures the generator converges to the true data distribution, but also enables the discriminator to retain the density information at the global optimal.
Ranked #17 on
Conditional Image Generation
on CIFAR-10
(Inception score metric)
Experiment Segmentation in Scientific Discourse as Clause-level Structured Prediction using Recurrent Neural Networks
We propose a deep learning model for identifying structure within experiment narratives in scientific literature.
RACE: Large-scale ReAding Comprehension Dataset From Examinations
We present RACE, a new dataset for benchmark evaluation of methods in the reading comprehension task.
An Interpretable Knowledge Transfer Model for Knowledge Base Completion
Knowledge bases are important resources for a variety of natural language processing tasks but suffer from incompleteness.
Ontology-Aware Token Embeddings for Prepositional Phrase Attachment
Type-level word embeddings use the same set of parameters to represent all instances of a word regardless of its context, ignoring the inherent lexical ambiguity in language.
Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML
Reward augmented maximum likelihood (RAML), a simple and effective learning framework to directly optimize towards the reward function in structured prediction tasks, has led to a number of impressive empirical successes.
Controllable Invariance through Adversarial Feature Learning
Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning.
CharManteau: Character Embedding Models For Portmanteau Creation
Portmanteaus are a word formation phenomenon where two words are combined to form a new word.
Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models
Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose.
Detecting and Explaining Causes From Text For a Time Series Event
Our quantitative and human analysis show empirical evidence that our method successfully extracts meaningful causality relationships between time series with textual features and generates appropriate explanation between them.
Finding Structure in Figurative Language: Metaphor Detection with Topic-based Frames
In this paper, we present a novel and highly effective method for induction and application of metaphor frame templates as a step toward detecting metaphor in extended discourse.
Event Detection Using Frame-Semantic Parser
Recent methods for Event Detection focus on Deep Learning for automatic feature generation and feature ranking.
Embedded Semantic Lexicon Induction with Joint Global and Local Optimization
Creating annotated frame lexicons such as PropBank and FrameNet is expensive and labor intensive.
Identifying Semantic Edit Intentions from Revisions in Wikipedia
Most studies on human editing focus merely on syntactic revision operations, failing to capture the intentions behind revision changes, which are essential for facilitating the single and collaborative writing process.
Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models
Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose.
Huntsville, hospitals, and hockey teams: Names can reveal your location
Geolocation is the task of identifying a social media user{'}s primary location, and in natural language processing, there is a growing literature on to what extent automated analysis of social media posts can help.
STCP: Simplified-Traditional Chinese Conversion and Proofreading
This paper aims to provide an effective tool for conversion between Simplified Chinese and Traditional Chinese.
Large-scale Cloze Test Dataset Created by Teachers
Cloze tests are widely adopted in language exams to evaluate students' language proficiency.
SPINE: SParse Interpretable Neural Embeddings
We propose a novel variant of denoising k-sparse autoencoders that generates highly efficient and interpretable distributed word representations (word embeddings), beginning with existing word representations from state-of-the-art methods like GloVe and word2vec.
Large-scale Cloze Test Dataset Designed by Teachers
Cloze test is widely adopted in language exams to evaluate students' language proficiency.
A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications
In the first task, we show that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline.
From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction
In this work, we study the credit assignment problem in reward augmented maximum likelihood (RAML) learning, and establish a theoretical equivalence between the token-level counterpart of RAML and the entropy regularized reinforcement learning.
Stack-Pointer Networks for Dependency Parsing
Combining pointer networks~\citep{vinyals2015pointer} with an internal stack, the proposed model first reads and encodes the whole sentence, then builds the dependency tree top-down (from root-to-leaf) in a depth-first fashion.
Ranked #14 on
Dependency Parsing
on Penn Treebank
AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it.
Graph-Based Decoding for Event Sequencing and Coreference Resolution
In this paper, we study two types of relation: Event Coreference and Event Sequencing.
Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data
This paper examines the problem of generating natural language descriptions of chess games.
Graph Based Decoding for Event Sequencing and Coreference Resolution
In this paper, we study two types of relation: Event Coreference and Event Sequencing.
Automatic Event Salience Identification
Our analyses demonstrate that our neural model captures interesting connections between salience and discourse unit relations (e. g., scripts and frame structures).
Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
Mixture of Softmaxes (MoS) has been shown to be effective at addressing the expressiveness limitation of Softmax-based models.
Ranked #18 on
Machine Translation
on WMT2014 English-French
Measuring Density and Similarity of Task Relevant Information in Neural Representations
Neural models achieve state-of-the-art performance due to their ability to extract salient features useful to downstream tasks.
The Profiling Machine: Active Generalization over Knowledge
The human mind is a powerful multifunctional knowledge storage and management system that performs generalization, type inference, anomaly detection, stereotyping, and other tasks.
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
Different languages might have different word orders.
Neural Machine Translation with Adequacy-Oriented Learning
Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation.
Ranked #35 on
Machine Translation
on WMT2014 English-German
MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations.
EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference
Quantitative reasoning is a higher-order reasoning skill that any intelligent natural language understanding system can reasonably be expected to handle.
An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via sentiment labels.
MaCow: Masked Convolutional Generative Flow
Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations.
Ranked #3 on
Image Generation
on CelebA 256x256
The ARIEL-CMU Systems for LoReHLT18
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
Unsupervised Data Augmentation for Consistency Training
In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning.
Ranked #1 on
Sentiment Analysis
on Amazon Review Full
Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances
Emotion is intrinsic to humans and consequently emotion understanding is a key part of human-like artificial intelligence (AI).
Ranked #6 on
Emotion Recognition in Conversation
on EC
Let's Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms
Modeling what makes a request persuasive - eliciting the desired response from a reader - is critical to the study of propaganda, behavioral economics, and advertising.
Word Embedding-Based Automatic MT Evaluation Metric using Word Position Information
We designate this metric as Word Embedding-Based automatic MT evaluation using Word Position Information (WE{\_}WPI).
Iterative Search for Weakly Supervised Semantic Parsing
Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer.
An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing
In this paper, we investigate the aspect of structured output modeling for the state-of-the-art graph-based neural dependency parser (Dozat and Manning, 2017).
Exploring Numeracy in Word Embeddings
In this work, we show that existing embedding models are inadequate at constructing representations that capture salient aspects of mathematical meaning for numbers, which is important for language understanding.
Toward Comprehensive Understanding of a Sentiment Based on Human Motives
In sentiment detection, the natural language processing community has focused on determining holders, facets, and valences, but has paid little attention to the reasons for sentiment decisions.
A Cascade Model for Proposition Extraction in Argumentation
Propositions are the basic units of an argument and the primary building blocks of most argument mining systems.
Domain Adaptation of SRL Systems for Biological Processes
Domain adaptation remains one of the most challenging aspects in the wide-spread use of Semantic Role Labeling (SRL) systems.
Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization
We find that while position exhibits substantial bias in news articles, this is not the case, for example, with academic papers and meeting minutes.
Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs
In order to produce a coherent flow of text, we explore two forms of intersentential relations in a paragraph: one is a human-created linguistical relation that forms a structure (e. g., discourse tree) and the other is a relation from latent representation learned from the sentences themselves.
(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas
Stylistic variation in text needs to be studied with different aspects including the writer's personal traits, interpersonal relations, rhetoric, and more.
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens.
Ranked #3 on
Machine Translation
on WMT2016 English-Romanian
Nested Named Entity Recognition via Second-best Sequence Learning and Decoding
When an entity name contains other names within it, the identification of all combinations of names can become difficult and expensive.
Ranked #2 on
Nested Mention Recognition
on ACE 2005
Definition Frames: Using Definitions for Hybrid Concept Representations
Advances in word representations have shown tremendous improvements in downstream NLP tasks, but lack semantic interpretability.
Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
While classifiers trained on either original or manipulated data alone are sensitive to spurious features (e. g., mentions of genre), models trained on the combined data are less sensitive to this signal.
Do Sentence Interactions Matter? Leveraging Sentence Level Representations for Fake News Classification
The rising growth of fake news and misleading information through online media outlets demands an automatic method for detecting such news articles.
Style is NOT a single variable: Case Studies for Cross-Style Language Understanding
This paper provides the benchmark corpus (xSLUE) that combines existing datasets and collects a new one for sentence-level cross-style language understanding and evaluation.
Decompressing Knowledge Graph Representations for Link Prediction
Specifically, embeddings of entities and relationships are first decompressed to a more expressive and robust space by decompressing functions, then knowledge graph embedding models are trained in this new feature space.
Ranked #26 on
Link Prediction
on FB15k-237
Self-training with Noisy Student improves ImageNet classification
During the learning of the student, we inject noise such as dropout, stochastic depth, and data augmentation via RandAugment to the student so that the student generalizes better than the teacher.
Ranked #16 on
Image Classification
on ImageNet ReaL
(using extra training data)
Decoupling Global and Local Representations via Invertible Generative Flows
In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting, by embedding a generative flow in the VAE framework to model the decoder.
SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
We introduce SCDE, a dataset to evaluate the performance of computational models through sentence prediction.
Ranked #3 on
Question Answering
on SCDE
Machine-Aided Annotation for Fine-Grained Proposition Types in Argumentation
We introduce a corpus of the 2016 U. S. presidential debates and commentary, containing 4, 648 argumentative propositions annotated with fine-grained proposition types.
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?
Although neural models have achieved impressive results on several NLP benchmarks, little is understood about the mechanisms they use to perform language tasks.
What-if I ask you to explain: Explaining the effects of perturbations in procedural text
We address the task of explaining the effects of perturbations in procedural text, an important test of process comprehension.
Measuring Forecasting Skill from Text
We present a number of linguistic metrics which are computed over text associated with people's predictions about the future including: uncertainty, readability, and emotion.
A Two-Step Approach for Implicit Event Argument Detection
It remains a challenge to detect implicit arguments, calling for more future work of document-level modeling for this task.
Explaining The Efficacy of Counterfactually Augmented Data
In attempts to produce ML models less reliant on spurious patterns in NLP datasets, researchers have recently proposed curating counterfactually augmented data (CAD) via a human-in-the-loop process in which given some documents and their (initial) labels, humans must revise the text to make a counterfactual label applicable.
GenAug: Data Augmentation for Finetuning Text Generators
We also examine the relationship between the amount of augmentation and the quality of the generated text.
Detecting Attackable Sentences in Arguments
Finding attackable sentences in an argument is the first step toward successful refutation in argumentation.
Extracting Implicitly Asserted Propositions in Argumentation
Our study may inform future research on argument mining and the semantics of these rhetorical devices in argumentation.
BERTering RAMS: What and How Much does BERT Already Know About Event Arguments? -- A Study on the RAMS Dataset
Next, we find that linear combinations of these heads, estimated with approx 11% of available total event argument detection supervision, can push performance well-higher for some roles - highest two being Victim (68. 29% Accuracy) and Artifact(58. 82% Accuracy).
Plan ahead: Self-Supervised Text Planning for Paragraph Completion Task
To address that, we propose a self-supervised text planner SSPlanner that predicts what to say first (content prediction), then guides the pretrained language model (surface realization) using the predicted content.
Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretability
Any prediction from a model is made by a combination of learning history and test stimuli.
EIGEN: Event Influence GENeration using Pre-trained Language Models
Reasoning about events and tracking their influences is fundamental to understanding processes.
A Dataset for Tracking Entities in Open Domain Procedural Text
Our solution is a new task formulation where given just a procedural text as input, the task is to generate a set of state change tuples(entity, at-tribute, before-state, after-state)for each step, where the entity, attribute, and state values must be predicted from an open vocabulary.
An Empirical Exploration of Local Ordering Pre-training for Structured Prediction
Recently, pre-training contextualized encoders with language model (LM) objectives has been shown an effective semi-supervised method for structured prediction.
Event-Related Bias Removal for Real-time Disaster Events
Furthermore, the classification of information in real-time systems requires training on out-of-domain data, as we do not have any data from a new emerging crisis.
Incorporating a Local Translation Mechanism into Non-autoregressive Translation
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs.
Ranked #2 on
Machine Translation
on WMT2016 English-Romanian
Exploring Neural Entity Representations for Semantic Information
Neural methods for embedding entities are typically extrinsically evaluated on downstream tasks and, more recently, intrinsically using probing tasks.
On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT
In particular, we demonstrate through a simple consistency probe that the ability to correctly retrieve hypernyms in cloze tasks, as used in prior work, does not correspond to systematic knowledge in BERT.
Measuring and Improving Consistency in Pretrained Language Models
In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge?
NoiseQA: Challenge Set Evaluation for User-Centric Question Answering
When Question-Answering (QA) systems are deployed in the real world, users query them through a variety of interfaces, such as speaking to voice assistants, typing questions into a search engine, or even translating questions to languages supported by the QA system.
SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers
We introduce SelfExplain, a novel self-explaining model that explains a text classifier's predictions using phrase-based concepts.
CURIE: An Iterative Querying Approach for Reasoning About Situations
Recently, models have been shown to predict the effects of unexpected situations, e. g., would cloudy skies help or hinder plant growth?
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer
Many of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e. g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence.
NAREOR: The Narrative Reordering Problem
In this paper, we propose and investigate the task of Narrative Reordering (NAREOR) which involves rewriting a given story in a different narrative order while preserving its plot.
A Survey of Data Augmentation Approaches for NLP
In this paper, we present a comprehensive and unifying survey of data augmentation for NLP by summarizing the literature in a structured manner.
Could you give me a hint? Generating inference graphs for defeasible reasoning
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence.
Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes
While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those relations.
More Identifiable yet Equally Performant Transformers for Text Classification
In this work, we provide deeper theoretical analysis and empirical observations on the identifiability of attention weights.
Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation
Multiple different responses are often plausible for a given open domain dialog context.
Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction
Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-to-sequence models with attention.
Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding
This paper provides the benchmark corpus (XSLUE) that combines existing datasets and collects a new one for sentence-level cross-style language understanding and evaluation.
Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis
To overcome these challenges, in this paper, we propose a dual graph convolutional networks (DualGCN) model that considers the complementarity of syntax structures and semantic correlations simultaneously.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation
We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination.
Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models
We investigate the use of multimodal information contained in images as an effective method for enhancing the commonsense of Transformer models for text generation.
Knowledge-Enhanced Evidence Retrieval for Counterargument Generation
Finding counterevidence to statements is key to many tasks, including counterargument generation.
Investigating Robustness of Dialog Models to Popular Figurative Language Constructs
Humans often employ figurative language use in communication, including during interactions with dialog systems.
Interpreting Deep Learning Models in Natural Language Processing: A Review
Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks.
Think about it! Improving defeasible reasoning by first modeling the question scenario
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence.
Template Filling for Controllable Commonsense Reasoning
To enable better controllability, we propose to study the commonsense reasoning as a template filling task (TemplateCSR) -- where the language models fills reasoning templates with the given constraints as control factors.
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge
In this work, we present NewsClaims, a new benchmark for attribute-aware claim detection in the news domain.
Counterfactual Data Augmentation improves Factuality of Abstractive Summarization
Abstractive summarization systems based on pretrained language models often generate coherent but factually inconsistent sentences.
PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically
Through automatic and human evaluation, as well as qualitative analysis, we show that PANCETTA generates novel, phonetically difficult, fluent, and semantically meaningful tongue twisters.
PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation
To this end, we propose PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation.
CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models
We motivate and introduce CHARD: Clinical Health-Aware Reasoning across Dimensions, to investigate the capability of text generation models to act as implicit clinical knowledge bases and generate free-flow textual explanations about various health-related conditions across several dimensions.
A Survey of Active Learning for Natural Language Processing
In this work, we provide a survey of active learning (AL) for its applications in natural language processing (NLP).
EvEntS ReaLM: Event Reasoning of Entity States via Language Models
This paper investigates models of event implications.
Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation
We present PeerSum, a novel dataset for generating meta-reviews of scientific papers.
Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training
To address this challenge, we adopt an error estimator to adaptively decide the partial selection ratio according to the current model's capability.
Factuality Challenges in the Era of Large Language Models
The emergence of tools based on Large Language Models (LLMs), such as OpenAI's ChatGPT, Microsoft's Bing Chat, and Google's Bard, has garnered immense public attention.
Sim-GPT: Text Similarity via GPT Annotated Data
Due to the lack of a large collection of high-quality labeled sentence pairs with textual similarity scores, existing approaches for Semantic Textual Similarity (STS) mostly rely on unsupervised techniques or training signals that are only partially correlated with textual similarity, e. g., NLI-based datasets.
Exploring Multi-Document Information Consolidation for Scientific Sentiment Summarization
Modern natural language generation systems with LLMs exhibit the capability to generate a plausible summary of multiple documents; however, it is uncertain if models truly possess the ability of information consolidation to generate summaries, especially on those source documents with opinionated information.
Overview and Insights from the Shared Tasks at Scholarly Document Processing 2020: CL-SciSumm, LaySumm and LongSumm
We present the results of three Shared Tasks held at the Scholarly Document Processing Workshop at EMNLP2020: CL-SciSumm, LaySumm and LongSumm.
Overview of the First Workshop on Scholarly Document Processing (SDP)
To reach to the broader NLP and AI/ML community, pool distributed efforts and enable shared access to published research, we held the 1st Workshop on Scholarly Document Processing at EMNLP 2020 as a virtual event.
One Document, Many Revisions: A Dataset for Classification and Description of Edit Intents
Document authoring involves a lengthy revision process, marked by individual edits that are frequently linked to comments.
BERTering RAMS: What and How Much does BERT Already Know About Event Arguments? - A Study on the RAMS Dataset
Next, we find that linear combinations of these heads, estimated with approx.
Comparing Span Extraction Methods for Semantic Role Labeling
In this work, we empirically compare span extraction methods for the task of semantic role labeling (SRL).
On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling
Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervised SRL training data are not abundant.
Think about it! Improving defeasible reasoning by first modeling the question scenario.
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence.
