Search Results for author:
Found 173 papers, 58 papers with code
Online Neural Coreference Resolution with Rollback
Humans process natural language online, whether reading a document or participating in multiparty dialogue.
Craft an Iron Sword: Dynamically Generating Interactive Game Characters by Prompting Large Language Models Tuned on Code
In this work, we demonstrate that use of a few example conversational prompts can power a conversational agent to generate both natural language and novel code.
Guided K-best Selection for Semantic Parsing Annotation
Collecting data for conversational semantic parsing is a time-consuming and demanding process.
Improved Induction of Narrative Chains via Cross-Document Relations
The standard approach for inducing narrative chains considers statistics gathered per individual document.
Zero and Few-shot Semantic Parsing with Ambiguous Inputs
We attempt to address this shortcoming by introducing AmP, a framework, dataset, and challenge for parsing with linguistic ambiguity.
InteractiveIE: Towards Assessing the Strength of Human-AI Collaboration in Improving the Performance of Information Extraction
Learning template based information extraction from documents is a crucial yet difficult task.
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
Incorporating language-specific (LS) modules is a proven method to boost performance in multilingual machine translation.
"According to ..." Prompting Language Models Improves Quoting from Pre-Training Data
Large Language Models (LLMs) may hallucinate and generate fake information, despite pre-training on factual data.
NevIR: Negation in Neural Information Retrieval
Although the Information Retrieval (IR) community has adopted LMs as the backbone of modern IR architectures, there has been little to no research in understanding how negation impacts neural IR.
Did You Mean...? Confidence-based Trade-offs in Semantic Parsing
We then examine how confidence scores can help optimize the trade-off between usability and safety.
Data Portraits: Recording Foundation Model Training Data
Foundation models are trained on increasingly immense and opaque datasets.
Can GPT-3 Perform Statutory Reasoning?
Statutory reasoning is the task of reasoning with facts and statutes, which are rules written in natural language by a legislature.
Ontologically Faithful Generation of Non-Player Character Dialogues
We introduce a language generation task grounded in a popular video game environment.
Defending Against Misinformation Attacks in Open-Domain Question Answering
Recent work in open-domain question answering (ODQA) has shown that adversarial poisoning of the search collection can cause large drops in accuracy for production systems.
When Do Decompositions Help for Machine Reading?
Answering complex questions often requires multi-step reasoning in order to obtain the final answer.
Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning
Visual Question Answering (VQA) models often perform poorly on out-of-distribution data and struggle on domain generalization.
Localization vs. Semantics: How Can Language Benefit Visual Representation Learning?
In this work, we investigate how language can help with visual representation learning from a probing perspective.
Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA
Natural language is ambiguous.
Calibrated Interpretation: Confidence Estimation in Semantic Parsing
Sequence generation models are increasingly being used to translate language into executable programs, i. e. to perform executable semantic parsing.
Automatic Document Selection for Efficient Encoder Pretraining
Building pretrained language models is considered expensive and data-intensive, but must we increase dataset size to achieve better performance?
An Empirical Study on Finding Spans
We present an empirical study on methods for span finding, the selection of consecutive tokens in text for some downstream tasks.
Iterative Document-level Information Extraction via Imitation Learning
We present a novel iterative extraction model, IterX, for extracting complex relations, or templates (i. e., N-tuples representing a mapping from named slots to spans of text) within a document.
Ambiguous Images With Human Judgments for Robust Visual Event Classification
However, humans are frequently presented with visual data that they cannot classify with 100% certainty, and models trained on standard vision benchmarks achieve low performance when evaluated on this data.
Dynamic Generation of Grounded Logical Explanations in a Neuro-Symbolic Expert System
We propose an approach for systematic reasoning that produces human interpretable proof trees grounded in a factbase.
Multilingual Coreference Resolution in Multiparty Dialogue
Existing multiparty dialogue datasets for coreference resolution are nascent, and many challenges are still unaddressed.
Zero-shot Cross-lingual Transfer is Under-specified Optimization
Pretrained multilingual encoders enable zero-shot cross-lingual transfer, but often produce unreliable models that exhibit high performance variance on the target language.
BenchCLAMP: A Benchmark for Evaluating Language Models on Semantic Parsing
We introduce BenchCLAMP, a Benchmark to evaluate Constrained LAnguage Model Parsing, which produces semantic outputs based on the analysis of input text through constrained decoding of a prompted or fine-tuned language model.
Pretrained Models for Multilingual Federated Learning
Since the advent of Federated Learning (FL), research has applied these methods to natural language processing (NLP) tasks.
Asking the Right Questions in Low Resource Template Extraction
Information Extraction (IE) researchers are mapping tasks to Question Answering (QA) in order to leverage existing large QA resources, and thereby improve data efficiency.
When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
Rejecting class imbalance as the sole culprit, we reveal that the trend is closely associated with an effect we call source signal dilution, where strong lexical cues for the new symbol become diluted as the training dataset grows.
The Curious Case of Control
Given the advanced fluency of large generative language models, we ask whether model outputs are consistent with these heuristics, and to what degree different models are consistent with each other.
Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation
We introduce a novel setup for low-resource task-oriented semantic parsing which incorporates several constraints that may arise in real-world scenarios: (1) lack of similar datasets/models from a related domain, (2) inability to sample useful logical forms directly from a grammar, and (3) privacy requirements for unlabeled natural utterances.
Visual Commonsense in Pretrained Unimodal and Multimodal Models
Our commonsense knowledge about objects includes their typical visual attributes; we know that bananas are typically yellow or green, and not purple.
Ranked #1 on
Visual Commonsense Tests
on ViComTe-color
One-Shot Learning from a Demonstration with Hierarchical Latent Language
Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration.
The NLP Task Effectiveness of Long-Range Transformers
Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity.
Few-Shot Semantic Parsing with Language Models Trained On Code
Intuitively, such models can more easily output canonical utterances as they are closer to the natural language used for pre-training.
Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images
Our experiments show CCO substantially boosts the performance of neural symbolic methods on real images.
Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English.
BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems.
Ranked #1 on
Machine Translation
on IWSLT2014 German-English
Guided Generation of Cause and Effect
We present a conditional text generation framework that posits sentential expressions of possible causes and effects.
Factoring Statutory Reasoning as Language Understanding Challenges
Statutory reasoning is the task of determining whether a legal statute, stated in natural language, applies to the text description of a case.
Constrained Language Models Yield Few-Shot Semantic Parsers
We explore the use of large pretrained language models as few-shot semantic parsers.
Human Schema Curation via Causal Association Rule Mining
Event schemas are structured knowledge sources defining typical real-world scenarios (e. g., going to an airport).
Moving on from OntoNotes: Coreference Resolution Model Transfer
Academic neural models for coreference resolution (coref) are typically trained on a single dataset, OntoNotes, and model improvements are benchmarked on that same dataset.
Adapting Coreference Resolution Models through Active Learning
Active learning mitigates this problem by sampling a small subset of data for annotators to label.
Joint Universal Syntactic and Semantic Parsing
While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other.
InFillmore: Frame-Guided Language Generation with Bidirectional Context
We propose a structured extension to bidirectional-context conditional language generation, or "infilling," inspired by Frame Semantic theory (Fillmore, 1976).
Gradual Fine-Tuning for Low-Resource Domain Adaptation
Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain.
LOME: Large Ontology Multilingual Extraction
We present LOME, a system for performing multilingual information extraction.
Joint Modeling of Arguments for Event Understanding
We recognize the task of event argument linking in documents as similar to that of intent slot resolution in dialogue, providing a Transformer-based model that extends from a recently proposed solution to resolve references to slots.
Temporal Reasoning in Natural Language Inference
We introduce five new natural language inference (NLI) datasets focused on temporal reasoning.
CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence Models
Copy mechanisms are employed in sequence to sequence models (seq2seq) to generate reproductions of words from the input to the output.
COD3S: Diverse Generation with Discrete Semantic Signatures
We present COD3S, a novel method for generating semantically diverse sentences using neural sequence-to-sequence (seq2seq) models.
Which *BERT? A Survey Organizing Contextualized Encoders
Pretrained contextualized text encoders are now a staple of the NLP community.
Script Induction as Association Rule Mining
We show that the count-based Script Induction models of Chambers and Jurafsky (2008) and Jans et al. (2012) can be unified in a general framework of narrative chain likelihood maximization.
Iterative Paraphrastic Augmentation with Discriminative Span Alignment
We introduce a novel paraphrastic augmentation strategy based on sentence-level lexically constrained paraphrasing and discriminative span alignment.
A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering
Legislation can be viewed as a body of prescriptive rules expressed in natural language.
Incremental Neural Coreference Resolution in Constant Memory
We investigate modeling coreference resolution under a fixed memory constraint by extending an incremental clustering algorithm to utilize contextualized encoders and neural components.
Complementing Lexical Retrieval with Semantic Residual Embedding
This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model.
Probing Neural Language Models for Human Tacit Assumptions
Our prompts are based on human responses in a psychological study of conceptual associations.
Hierarchical Entity Typing via Multi-level Learning to Rank
We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction.
Causal Inference of Script Knowledge
When does a sequence of events define an everyday scenario and how can this knowledge be induced from text?
Reading the Manual: Event Extraction as Definition Comprehension
We ask whether text understanding has progressed to where we may extract event information through incremental refinement of bleached statements derived from annotation manuals.
Multi-Sentence Argument Linking
We present a novel document-level model for finding argument spans that fill an event's roles, connecting related ideas in sentence-level semantic role labeling and coreference resolution.
Interactive Refinement of Cross-Lingual Word Embeddings
Cross-lingual word embeddings transfer knowledge between languages: models trained on high-resource languages can predict in low-resource languages.
Bag-of-Words Transfer: Non-Contextual Techniques for Multi-Task Learning
Many architectures for multi-task learning (MTL) have been proposed to take advantage of transfer among tasks, often involving complex models and training procedures.
Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering
Producing diverse paraphrases of a sentence is a challenging task.
Universal Decompositional Semantic Parsing
We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional semantic attribute scores.
Exact and/or Fast Nearest Neighbors
Prior methods for retrieval of nearest neighbors in high dimensions are fast and approximate--providing probabilistic guarantees of returning the correct answer--or slow and exact performing an exhaustive search.
Data Structures and Algorithms
The Universal Decompositional Semantics Dataset and Decomp Toolkit
We present the Universal Decompositional Semantics (UDS) dataset (v1. 0), which is bundled with the Decomp toolkit (v0. 1).
Uncertain Natural Language Inference
We introduce Uncertain Natural Language Inference (UNLI), a refinement of Natural Language Inference (NLI) that shifts away from categorical labels, targeting instead the direct prediction of subjective probability assessments.
Broad-Coverage Semantic Parsing as Transduction
We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations.
Ranked #2 on
UCCA Parsing
on SemEval 2019 Task 1
A Discriminative Neural Model for Cross-Lingual Word Alignment
We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model.
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference
Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases.
Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
In contrast to standard approaches to NLI, our methods predict the probability of a premise given a hypothesis and NLI label, discouraging models from ignoring the premise.
Learning to Rank for Plausible Plausibility
Researchers illustrate improvements in contextual encoding strategies via resultant performance on a battery of shared Natural Language Understanding (NLU) tasks.
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting
Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in generation tasks such as machine translation or monolingual text rewriting.
AMR Parsing as Sequence-to-Graph Transduction
Our experimental results outperform all previously reported SMATCH scores, on both AMR 2. 0 (76. 3% F1 on LDC2017T10) and AMR 1. 0 (70. 2% F1 on LDC2014T12).
Ranked #1 on
AMR Parsing
on LDC2014T12:
What do you learn from context? Probing for sentence structure in contextualized word representations
The jiant toolkit for general-purpose text understanding models
Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling
Work on the problem of contextualized word representation—the development of reusable neural network components for sentence understanding—has recently seen a surge of progress centered on the unsupervised pretraining task of language modeling with methods like ELMo (Peters et al., 2018).
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
Our results show that pretraining on language modeling performs the best on average across our probing tasks, supporting its widespread use for pretraining state-of-the-art NLP models, and CCG supertagging and NLI pretraining perform comparably.
Fine-Grained Temporal Relation Extraction
We present a novel semantic framework for modeling temporal relations and event durations that maps pairs of events to real-valued scales.
Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
We present a novel semantic framework for modeling linguistic expressions of generalization---generic, habitual, and episodic statements---as combinations of simple, real-valued referential properties of predicates and their arguments.
ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation
We present ParaBank, a large-scale English paraphrase dataset that surpasses prior work in both quantity and quality.
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pretrained on variants of language modeling.
Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages
Multilingual topic models can reveal patterns in cross-lingual document collections.
ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension
We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning.
Cross-lingual Decompositional Semantic Parsing
We introduce the task of cross-lingual decompositional semantic parsing: mapping content provided in a source language into a decompositional semantic analysis based on a target language.
Predicting the Argumenthood of English Prepositional Phrases
Distinguishing between arguments and adjuncts of a verb is a longstanding, nontrivial problem.
Lexicosyntactic Inference in Neural Models
We use this dataset, which we make publicly available, to probe the behavior of current state-of-the-art neural systems, showing that these systems make certain systematic errors that are clearly visible through the lens of factuality prediction.
Efficient Online Scalar Annotation with Bounded Support
We describe a novel method for efficiently eliciting scalar annotations for dataset construction and system quality estimation by human judgments.
Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction
Cross-lingual information extraction (CLIE) is an important and challenging task, especially in low resource scenarios.
Hypothesis Only Baselines in Natural Language Inference
We propose a hypothesis only baseline for diagnosing Natural Language Inference (NLI).
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference
We propose a process for investigating the extent to which sentence representations arising from neural machine translation (NMT) systems encode distinct semantic phenomena.
Gender Bias in Coreference Resolution
We present an empirical study of gender bias in coreference resolution systems.
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation
We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning.
Neural-Davidsonian Semantic Proto-role Labeling
We present a model for semantic proto-role labeling (SPRL) using an adapted bidirectional LSTM encoding strategy that we call "Neural-Davidsonian": predicate-argument structure is represented as pairs of hidden states corresponding to predicate and argument head tokens of the input sequence.
Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds
Fine-grained entity typing is the task of assigning fine-grained semantic types to entity mentions.
Cross-lingual Semantic Parsing
We introduce the task of cross-lingual semantic parsing: mapping content provided in a source language into a meaning representation based on a target language.
Neural models of factuality
We present two neural models for event factuality prediction, which yield significant performance gains over previous models on three event factuality datasets: FactBank, UW, and MEANTIME.
Selective Decoding for Cross-lingual Open Information Extraction
Cross-lingual open information extraction is the task of distilling facts from the source language into representations in the target language.
Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework
We propose to unify a variety of existing semantic classification tasks, such as semantic role labeling, anaphora resolution, and paraphrase detection, under the heading of Recognizing Textual Entailment (RTE).
CADET: Computer Assisted Discovery Extraction and Translation
It combines a multitude of analytics together with a flexible environment for customizing the workflow for different users.
Grammatical Error Correction with Neural Reinforcement Learning
We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC).
Error-repair Dependency Parsing for Ungrammatical Texts
We propose a new dependency parsing scheme which jointly parses a sentence and repairs grammatical errors by extending the non-directional transition-based formalism of Goldberg and Elhadad (2010) with three additional actions: SUBSTITUTE, DELETE, INSERT.
Pocket Knowledge Base Population
Existing Knowledge Base Population methods extract relations from a closed relational schema with limited coverage leading to sparse KBs.
Bayesian Modeling of Lexical Resources for Low-Resource Settings
Practically, this means that we may treat the lexical resources as observations under the proposed generative model.
Low Resource Named Entity Recognition
named-entity-recognition
+2
Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles
We study how different frame annotations complement one another when learning continuous lexical semantics.
Streaming Word Embeddings with the Space-Saving Algorithm
We develop a streaming (one-pass, bounded-memory) word embedding algorithm based on the canonical skip-gram with negative sampling algorithm implemented in word2vec.
Discriminative Information Retrieval for Question Answering Sentence Selection
We propose a framework for discriminative IR atop linguistic features, trained to improve the recall of answer candidate passage retrieval, the initial step in text-based question answering.
Social Bias in Elicited Natural Language Inferences
We analyze the Stanford Natural Language Inference (SNLI) corpus in an investigation of bias and stereotyping in NLP data.
Efficient, Compositional, Order-sensitive n-gram Embeddings
We propose ECO: a new way to generate embeddings for phrases that is Efficient, Compositional, and Order-sensitive.
Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis
The popular skip-gram model induces word embeddings by exploiting the signal from word-context coocurrence.
The Semantic Proto-Role Linking Model
We propose the semantic proto-role linking model, which jointly induces both predicate-specific semantic roles and predicate-general semantic proto-roles based on semantic proto-role property likelihood judgments.
MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models
Conventional pipeline solutions decompose the task as machine translation followed by information extraction (or vice versa).
Feature Generation for Robust Semantic Role Labeling
Hand-engineered feature sets are a well understood method for creating robust NLP models, but they require a lot of expertise and effort to create.
Ordinal Common-sense Inference
Humans have the capacity to draw common-sense inferences from natural language: various things that are likely but not certain to hold based on established discourse, and are rarely stated explicitly.
Computational linking theory
A linking theory explains how verbs' semantic arguments are mapped to their syntactic arguments---the inverse of the Semantic Role Labeling task from the shallow semantic parsing literature.
An Analysis of Lemmatization on Topic Models of Morphologically Rich Language
Topic models are typically represented by top-$m$ word lists for human interpretation.
Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network
Inspired by the findings from the Cmabrigde Uinervtisy effect, we propose a word recognition model based on a semi-character level recurrent neural network (scRNN).
A Critical Examination of RESCAL for Completion of Knowledge Bases with Transitive Relations
Link prediction in large knowledge graphs has received a lot of attention recently because of its importance for inferring missing relations and for completing and improving noisily extracted knowledge graphs.
Sublinear Partition Estimation
The output scores of a neural network classifier are converted to probabilities via normalizing over the scores of all competing categories.
Interactive Knowledge Base Population
Most work on building knowledge bases has focused on collecting entities and facts from as large a collection of documents as possible.
Statistical modality tagging from rule-based annotations and crowdsourcing
We explore training an automatic modality tagger.
Semantic Proto-Roles
We present the first large-scale, corpus based verification of Dowty{'}s seminal theory of proto-roles.
A Wikipedia-based Corpus for Contextualized Machine Translation
We describe a corpus for target-contextualized machine translation (MT), where the task is to improve the translation of source documents using language models built over presumably related documents in the target language.
