Search Results for author:
Found 195 papers, 119 papers with code
Using Word Embedding to Reveal Monetary Policy Explanation Changes
Documents have been an essential tool of communication for governments to announce their policy operations.
Think Before You Speak: Learning to Generate Implicit Knowledge for Response Generation by Self-Talk
We further investigate can such models identify when to generate implicit background knowledge and when it is not necessary.
NewsEdits: A News Article Revision Dataset and a Novel Document-Level Reasoning Challenge
News article revision histories provide clues to narrative and factual evolution in news articles.
ER-TEST Evaluating Explanation Regularization Methods for NLP Models
For the latter, explanation regularization (ER) aims to improve NLM generalization by pushing the machine rationales to align with human rationales.
Knowledge-Augmented Methods for Natural Language Processing
Knowledge in natural language processing (NLP) has been a rising trend especially after the advent of large scale pre-trained models.
Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp.
Modality-specific Distillation
In this paper, we propose modality-specific distillation (MSD) to effectively transfer knowledge from a teacher on multimodal datasets.
Diverging Preferences: When do Annotators Disagree and do Models Know?
We find that the majority of disagreements are in opposition with standard reward modeling approaches, which are designed with the assumption that annotator disagreement is noise.
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions.
Rethinking Backdoor Detection Evaluation for Language Models
Backdoor detection methods aim to detect whether a released model contains a backdoor, so that practitioners can avoid such vulnerabilities.
Symbolic Working Memory Enhances Language Models for Complex Rule Application
Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially when rules are presented non-sequentially.
Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
We introduce Lifelong ICL, a problem setting that challenges long-context language models (LMs) to learn a sequence of language tasks through in-context learning (ICL).
Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models.
CAVE: Controllable Authorship Verification Explanations
Authorship Verification (AV) (do two documents have the same author?)
Demystifying Language Model Forgetting with Low-rank Example Associations
Leveraging the low-rank nature of the associations, we predict forgetting of upstream examples when fine-tuning on unseen tasks with matrix completion over the empirical associations.
WildChat: 1M ChatGPT Interaction Logs in the Wild
In addition to timestamped chat transcripts, we enrich the dataset with demographic data, including state, country, and hashed IP addresses, alongside request headers.
CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting
As the utilization of large language models (LLMs) has proliferated world-wide, it is crucial for them to have adequate knowledge and fair representation for diverse global cultures.
Logits of API-Protected LLMs Leak Proprietary Information
Large language model (LLM) providers often hide the architectural details and parameters of their proprietary models by restricting public access to a limited API.
WinoViz: Probing Visual Properties of Objects Under Different States
We present WinoViz, a text-only evaluation dataset, consisting of 1, 380 examples that probe the reasoning abilities of language models regarding variant visual properties of objects under different contexts or states.
Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
Our analysis of GPT-series models over a rule subset reveals significant gaps in LLMs' logic understanding compared to human performance, especially in compositional and structural complex rules with certain bias patterns.
Self-Discover: Large Language Models Self-Compose Reasoning Structures
We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods.
Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification
Finally, we use this model to filter out inconsistent model-generated rationales in self-consistency decoding, resulting in a 6% accuracy improvement on average across three MCQ datasets.
What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement
We propose a partially interpretable forecasting model based on the observation that changes in pre-softmax logit scores of pretraining examples resemble that of online learned examples, which performs decently on BART but fails on T5 models.
Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty
As natural language becomes the default interface for human-AI interaction, there is a need for LMs to appropriately communicate uncertainties in downstream applications.
Wireless Communications in Cavity: A Reconfigurable Boundary Modulation based Approach
This paper explores the potential wireless communication applications of Reconfigurable Intelligent Surfaces (RIS) in reverberant wave propagation environments.
In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
To effectively use large language models (LLMs) for real-world queries, it is imperative that they generalize to the long-tail distribution, i. e. rare examples where models exhibit low confidence.
Tailoring Self-Rationalizers with Multi-Reward Distillation
Results on five difficult question-answering datasets StrategyQA, QuaRel, OpenBookQA, NumerSense and QASC show that not only does MaRio improve task accuracy, but it also improves the self-rationalization quality of small LMs across the aforementioned axes better than a supervised fine-tuning (SFT) baseline.
Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance
Instead, our approach BOSS (BOotStrapping your own Skills) learns to accomplish new tasks by performing "skill bootstrapping," where an agent with a set of primitive skills interacts with the environment to practice new skills without receiving reward feedback for tasks outside of the initial skill set.
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence.
DOMINO: A Dual-System for Multi-step Visual Language Reasoning
By fine-tuning the System-2 module (LLaMA-2 70B) on only a small amount of data on multi-step reasoning, the accuracy of our method is further improved and surpasses the best fully-supervised end-to-end approach by 5. 7% and a pipeline approach with FlanPaLM (540B) by 7. 5% on a challenging dataset with human-authored questions.
How FaR Are Large Language Models From Agents with Theory-of-Mind?
We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenarios.
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
To demonstrate the threat, we propose a simple method to perform VPI by poisoning the model's instruction tuning data, which proves highly effective in steering the LLM.
Instruction-following Evaluation through Verbalizer Manipulation
We conduct a comprehensive evaluation of four major model families across nine datasets, employing twelve sets of verbalizers for each of them.
Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step
We release our corpus of chain-of-thought samples and code.
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
We present LLM-Blender, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language models (LLMs).
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
We present PlaSma, a novel two-pronged approach to endow small language models with procedural knowledge and (constrained) language planning capabilities.
Faith and Fate: Limits of Transformers on Compositionality
We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures.
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding.
How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench
We investigate the predictability of large language model (LLM) capabilities: given records of past experiments using different model families, numbers of parameters, tasks, and numbers of in-context examples, can we accurately predict LLM performance on new experiment configurations?
GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks.
Estimating Large Language Model Capabilities without Labeled Test Data
In this paper, we propose the task of ICL accuracy estimation, in which we predict the accuracy of an LLM when doing in-context learning on a new task given only unlabeled test data for that task.
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure prompting can often be limited.
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Existing metrics like task performance of the LM generating the rationales, or similarity between generated and gold rationales are not good indicators of their human utility.
SCOTT: Self-Consistent Chain-of-Thought Distillation
While CoT can yield dramatically improved performance, such gains are only observed for sufficiently large LMs.
Design of Reconfigurable Intelligent Surfaces for Wireless Communication: A Review
The prototype undergoes rigorous empirical evaluation, encompassing multi-hop RIS signal amplification, image reconstruction, and real-world indoor signal coverage experiments.
Exploring Distributional Shifts in Large Language Models for Code Analysis
We systematically study how three large language models with code capabilities - CodeT5, Codex, and ChatGPT - generalize to out-of-domain data.
PairReranker: Pairwise Reranking for Natural Language Generation
Pre-trained language models have been successful in natural language generation (NLG) tasks.
I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons
We propose a novel task, G4C, to study teacher-student natural language interactions in a goal-driven and grounded environment.
Dataless Knowledge Fusion by Merging Weights of Language Models
In this paper, we study the problem of merging individual models built on different training data sets to obtain a single model that performs well both across all data set domains and can generalize on out-of-domain data.
KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales
First, KNIFE finetunes a teacher LM (given task input and FTR) to predict the task output, transferring reasoning knowledge from the FTRs to the teacher's hidden states.
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
Logical reasoning of text is an important ability that requires understanding the information present in the text, their interconnections, and then reasoning through them to infer new conclusions.
Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models
In many task settings, text classification models are likely to encounter examples from novel classes on which they cannot predict correctly.
Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality
Human communication relies on common ground (CG), the mutual knowledge and beliefs shared by participants, to produce coherent and interesting conversations.
PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters.
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model.
MMGA: Multimodal Learning with Graph Alignment
In this paper, we propose MMGA (Multimodal learning with Graph Alignment), a novel multimodal pre-training framework to incorporate information from graph (social network), image and text modalities on social media to enhance user representation learning.
REV: Information-Theoretic Evaluation of Free-Text Rationales
More concretely, we propose a metric called REV (Rationale Evaluation with conditional V-information), to quantify the amount of new, label-relevant information in a rationale beyond the information already available in the input or the label.
On Grounded Planning for Embodied Tasks with Language Models
Language models (LMs) have demonstrated their capability in possessing commonsense knowledge of the physical world, a crucial aspect of performing tasks in everyday life.
Curriculum Learning for Data-Efficient Vision-Language Alignment
Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data.
Retweet-BERT: Political Leaning Detection Using Language Features and Information Diffusion on Social Networks
We introduce Retweet-BERT, a simple and scalable model to estimate the political leanings of Twitter users.
FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales
Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior.
NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge
News article revision histories provide clues to narrative and factual evolution in news articles.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Machine Translation Robustness to Natural Asemantic Variation
We find that existing MT models fail when presented with NAV data, but we demonstrate strategies to improve performance on NAV by fine-tuning them with human-generated variations.
ER-Test: Evaluating Explanation Regularization Methods for Language Models
to align with human rationales (Which input tokens would humans focus on?).
BITE: Textual Backdoor Attacks with Iterative Trigger Injection
We propose BITE, a backdoor attack that poisons the training data to establish strong correlations between the target label and a set of "trigger words".
RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning
Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in English natural language.
Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts
Recent works suggest that transformer models are capable of multi-tasking on diverse NLP tasks and adapting to new tasks efficiently.
Cross-lingual Lifelong Learning
The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual model that can withstand the changes in multi-lingual data distributions.
NS3: Neuro-Symbolic Semantic Code Search
We compare our model - NS3 (Neuro-Symbolic Semantic Search) - to a number of baselines, including state-of-the-art semantic code retrieval methods, and evaluate on two datasets - CodeSearchNet and Code Search and Question Answering.
On Continual Model Refinement in Out-of-Distribution Data Streams
Real-world natural language processing (NLP) models need to be continually updated to fix the prediction errors in out-of-distribution (OOD) data streams while overcoming catastrophic forgetting.
Unsupervised Cross-Task Generalization via Retrieval Augmentation
Humans can perform unseen tasks by recalling relevant skills acquired previously and then generalizing them to the target tasks, even if there is no supervision at all.
FaiRR: Faithful and Robust Deductive Reasoning over Natural Language
Recent works show that such models can also produce the reasoning steps (i. e., the proof graph) that emulate the model's logical reasoning process.
Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-modal Knowledge Transfer
Pre-trained language models are still far from human performance in tasks that need understanding of properties (e. g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such information due to reporting bias.
UNIREX: A Unified Learning Framework for Language Model Rationale Extraction
An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction.
Contextualized Scene Imagination for Generative Commonsense Reasoning
In this paper, we propose an Imagine-and-Verbalize (I&V) method, which learns to imagine a relational scene knowledge graph (SKG) with relations between the input concepts, and leverage the SKG as a constraint when generating a plausible scene description.
Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora
We evaluate PTLM's ability to adapt to new corpora while retaining learned knowledge in earlier corpora.
Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
Implicit knowledge, such as common sense, is key to fluid human conversations.
Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models
Distilling state-of-the-art transformer models into lightweight student models is an effective way to reduce computation cost at inference time.
On the Robustness of Reading Comprehension Models to Entity Renaming
We study the robustness of machine reading comprehension (MRC) models to entity renaming -- do models make more wrong predictions when the same questions are asked about an entity whose name has been changed?
Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
We also find that good demonstration can save many labeled examples and consistency in demonstration contributes to better performance.
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models
Large pre-trained vision-language (VL) models can learn a new task with a handful of examples and generalize to a new task without fine-tuning.
Ranked #4 on
Image Captioning
on Flickr30k Captions test
(SPICE metric)
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
The recent proposed Fusion-in-Decoder (FiD), which is built on top of the pretrained generative model T5, achieves the state-of-the-art performance in the reading module.
Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet.
RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
To audit the robustness of named entity recognition (NER) models, we propose RockNER, a simple yet effective method to create natural adversarial examples.
AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction
Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations.
Low Resource Named Entity Recognition
named-entity-recognition
+2
Discretized Integrated Gradients for Explaining Language Models
As a prominent attribution-based explanation algorithm, Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation.
Improving Counterfactual Generation for Fair Hate Speech Detection
By applying logit pairing to equalize outcomes on the restricted set of counterfactuals for each instance, we improve fairness metrics while preserving model performance on hate speech detection.
Do Language Models Perform Generalizable Commonsense Inference?
Inspired by evidence that pretrained language models (LMs) encode commonsense knowledge, recent work has applied LMs to automatically populate commonsense knowledge graphs (CKGs).
Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning
In addition, we also create two new datasets, X-CSQA and X-CODAH, by translating their English versions to 15 other languages, so that we can evaluate popular ML-LMs for cross-lingual commonsense reasoning.
AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding
However, this approach constrains knowledge sharing across different attributes.
TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names
Hierarchical multi-label text classification (HMTC) aims to tag each document with a set of classes from a taxonomic class hierarchy.
Multi Label Text Classification
Multi-Label Text Classification
+3
X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering
We extensively evaluate our framework on two challenging cross-lingual NLU tasks: multilingual task-oriented dialog and typologically diverse question answering.
Probing Commonsense Explanation in Dialogue Response Generation
Humans use commonsense reasoning (CSR) implicitly to produce natural and coherent responses in conversations.
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence.
SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
and fine (Which nodes/paths in the KG are useful?)
FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks
Increasing concerns and regulations about data privacy and sparsity necessitate the study of privacy-preserving, decentralized learning methods for natural language processing (NLP) tasks.
On the Influence of Masking Policies in Intermediate Pre-training
Current NLP models are predominantly trained through a two-stage "pre-train then fine-tune" pipeline.
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
Humans can learn a new language task efficiently with only few examples, by leveraging their knowledge obtained when learning prior tasks.
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation
We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch.
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation
In this paper, we present a systematic analysis that studies whether current seq2seq models, especially pre-trained language models, are good enough for preserving important input concepts and to what extent explicitly guiding generation with the concepts as lexical constraints is beneficial.
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
In addition, we analyze two downstream models that use ConceptNet as a source for commonsense knowledge and find the existence of biases in those models as well.
Refining Language Models with Compositional Explanations
However, such a regularization technique lacks flexibility and coverage, since only importance scores towards a pre-defined list of features are adjusted, while more complex human knowledge such as feature interaction and pattern generalization can hardly be incorporated.
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding
The idea aims at mimicking a teacher's modality-specific predictions by introducing auxiliary loss terms for each modality.
Learning to Generate Task-Specific Adapters from Task Description
Recent study further shows that they can learn to generalize to novel tasks, by including task descriptions as part of the source sequence and training the model with (source, target) examples.
RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge
Question: I have five fingers but I am not alive.
Efficient Learning of Less Biased Models with Transfer Learning
Prediction bias in machine learning models, referring to undesirable model behaviors that discriminates inputs mentioning or produced by certain group, has drawn increasing attention from the research community given its societal impact.
Learning Contextualized Knowledge Graph Structures for Commonsense Reasoning
Recently, neural-symbolic architectures have achieved success on commonsense reasoning through effectively encoding relational structures retrieved from external knowledge graphs (KGs) and obtained state-of-the-art results in tasks such as (commonsense) question answering and natural language inference.
Pre-training Text-to-Text Transformers to Write and Reason with Concepts
To augment PTLMs with common sense, we propose generative and contrastive objectives as intermediate self-supervised pre-training tasks between general pre-training and downstream task-specific fine-tuning.
Studying Strategically: Learning to Mask for Closed-book QA
Thus, our policy packs task-relevant knowledge into the parameters of a language model.
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning
While pre-trained language models (PTLMs) have achieved noticeable success on many NLP tasks, they still struggle for tasks that require event temporal reasoning, which is essential for event-centric applications.
Ranked #1 on
Question Answering
on Torque
Pre-training Text-to-Text Transformers for Concept-centric Common Sense
Pre-trained language models (PTLM) have achieved impressive results in a range of natural language understanding (NLU) and generation (NLG) tasks.
Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
Despite significant progress, state-of-the-art abstractive summarization methods are still prone to hallucinate content inconsistent with the source document.
Learning Contextualized Knowledge Structures for Commonsense Reasoning
Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks.
Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation.
On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning
Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution.
Differentiable Open-Ended Commonsense Reasoning
As a step towards making commonsense reasoning research more realistic, we propose to study open-ended commonsense reasoning (OpenCSR) -- the task of answering a commonsense question without any pre-defined choices -- using as a resource only a corpus of commonsense facts written in natural language.
Fair Hate Speech Detection through Evaluation of Social Group Counterfactuals
Counterfactual token fairness for a mentioned social group evaluates the model's predictions as to whether they are the same for (a) the actual sentence and (b) a counterfactual instance, which is generated by changing the mentioned social group in the sentence.
One-shot Learning for Temporal Knowledge Graphs
Most real-world knowledge graphs are characterized by a long-tail relation frequency distribution where a significant fraction of relations occurs only a handful of times.
Will This Idea Spread Beyond Academia? Understanding Knowledge Transfer of Scientific Concepts across Text Corpora
We extract scientific concepts (i. e., phrases) from corpora as instantiations of "research ideas", create concept-level features as motivated by literature, and then follow the trajectories of over 450, 000 new concepts (emerged from 1995-2014) to identify factors that lead only a small proportion of these ideas to be used in inventions and drug trials.
Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning
Additionally, the explicit redundancy measure in MMR helps the neural representation of the summary to better capture redundancy.
SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery
To facilitate the research on studying the interplays of these two tasks, we create the first large-scale Synonym-Enhanced Set Expansion (SE2) dataset via crowdsourcing.
Two Step Joint Model for Drug Drug Interaction Extraction
When patients need to take medicine, particularly taking more than one kind of drug simultaneously, they should be alarmed that there possibly exists drug-drug interaction.
Gradient-based Editing of Memory Examples for Online Task-free Continual Learning
We explore task-free continual learning (CL), in which a model is trained to avoid catastrophic forgetting in the absence of explicit task boundaries or identities.
Screenplay Quality Assessment: Can We Predict Who Gets Nominated?
Toward that goal, in this work, we present a method to evaluate the quality of a screenplay based on linguistic cues.
Contextualizing Hate Speech Classifiers with Post-hoc Explanation
Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like "gay" or "black" are used in offensive or prejudiced ways.
IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization
Fine-tuning pre-trained language models (PTLMs), such as BERT and its better variant RoBERTa, has been a common practice for advancing performance in natural language understanding (NLU) tasks.
Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models
Recent works show that pre-trained language models (PTLMs), such as BERT, possess certain commonsense and factual knowledge.
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
In this paper, we augment a general commonsense QA framework with a knowledgeable path generator.
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms
Pre-trained language models (PTLMs) have achieved impressive performance on commonsense inference benchmarks, but their ability to employ commonsense to make robust inferences, which is crucial for effective communications with humans, is debated.
ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
In this work, we aim to formulate a task, construct a dataset, and provide benchmarks for developing methods for event forecasting with large volumes of unstructured text data.
Visually Grounded Continual Learning of Compositional Phrases
To study this human-like language acquisition ability, we present VisCOLL, a visually grounded language learning task, which simulates the continual acquisition of compositional phrases from streaming visual scenes.
Teaching Machine Comprehension with Compositional Explanations
Advances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples.
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
Existing work on augmenting question answering (QA) models with external knowledge (e. g., knowledge graphs) either struggle to model multi-hop relations efficiently, or lack transparency into the model's prediction rationale.
Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning
Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions.
LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
Successfully training a deep neural network demands a huge corpus of labeled data.
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
In this paper, we introduce "entity triggers," an effective proxy of human explanations for facilitating label-efficient learning of NER models.
Generating Natural Language Adversarial Examples on a Large Scale with Generative Models
It can attack text classification models with a higher success rate than existing methods, and provide acceptable quality for humans in the meantime.
Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution
We show that if the information contained in the graph and the time series data are closely related, then this inter-dependence can be used to predict the time series with improved accuracy.
Mining News Events from Comparable News Corpora: A Multi-Attribute Proximity Network Modeling Approach
This proximity network captures the corpus-level co-occurence statistics for candidate event descriptors, event attributes, as well as their connections.
Improving BERT Fine-tuning with Embedding Normalization
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing.