Search Results for author:
Found 29 papers, 23 papers with code
RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios
We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios.
FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback
To handle these limitations, we propose an innovative method to align modalities in LVLMs through Fine-Grained Artificial Intelligence Feedback (FGAIF), which mainly consists of three steps: AI-based Feedback Collection, Fine-grained Reward Model Training, and Reinforcement Learning with Fine-grained Reward.
Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning
Neural models, including large language models (LLMs), achieve superior performance on multi-hop question-answering.
FAITHSCORE: Evaluating Hallucinations in Large Vision-Language Models
We introduce FAITHSCORE (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs).
POE: Process of Elimination for Multiple Choice Reasoning
Language models (LMs) are capable of conducting in-context learning for multiple choice reasoning tasks, but the options in these tasks are treated equally.
Probing Representations for Document-level Event Extraction
This work is the first to apply the probing paradigm to representations learned for document-level information extraction (IE).
AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions
In this paper, we demonstrate the usefulness of this AGent pipeline by creating two sets of unanswerable questions from answerable questions in SQuAD and HotpotQA.
Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
Hypothetical induction is recognized as the main reasoning type when scientists make observations about the world and try to propose hypotheses to explain those observations.
Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
The two encoders are used to compute prototypes of image classes for classification.
PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations
Specifically, we propose the (1) peer rank (PR) algorithm that takes into account each peer LLM's pairwise preferences of all answer pairs, and outputs a final ranking of models; and (2) peer discussion (PD), where we prompt two LLMs to discuss and try to reach a mutual agreement on preferences of two answers.
Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning
A LERP is designed as a vector of probabilistic logical functions on the entity's neighboring sub-graph.
Ranked #9 on
Link Prediction
on WN18RR
Logical Reasoning over Natural Language as Knowledge Representation: A Survey
This paper provides a comprehensive overview on a new paradigm of logical reasoning, which uses natural language as knowledge representation and pretrained language models as reasoners, including philosophical definition and categorization of logical reasoning, advantages of the new paradigm, benchmarks and methods, challenges of the new paradigm, possible future directions, and relation to related NLP fields.
Language Models as Inductive Reasoners
To this end, we propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts, and create a dataset termed DEER containing 1. 2k rule-fact pairs for the task, where rules and facts are written in natural language.
Retrieval-Augmented Generative Question Answering for Event Argument Extraction
We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction.
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
To this end, we propose the framework CLORE (Classification by LOgical Reasoning on Explanations).
Dynamic Global Memory for Document-level Argument Extraction
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document.
Automatic Error Analysis for Document-level Information Extraction
Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts.
QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining
To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model.
Template Filling with Generative Transformers
Template filling is generally tackled by a pipeline of two separate supervised systems {--} one for role-filler extraction and another for template/event recognition.
Few-shot Intent Classification and Slot Filling with Retrieved Examples
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain.
Leveraging Structured Metadata for Improving Question Answering on the Web
We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking.
Improving Event Duration Prediction via Time-aware Pre-training
End-to-end models in NLP rarely encode external world knowledge about length of time.
GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction
We revisit the classic problem of document-level role-filler entity extraction (REE) for template filling.
Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding
Few works in the literature of event extraction have gone beyond individual sentences to make extraction decisions.
Event Extraction by Answering (Almost) Natural Questions
The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments.
Be Consistent! Improving Procedural Text Comprehension using Label Consistency
Our goal is procedural text comprehension, namely tracking how the properties of entities (e. g., their location) change with time given a procedural text (e. g., a paragraph about photosynthesis, a recipe).
Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia
We study the task of generating from Wikipedia articles question-answer pairs that cover content beyond a single sentence.
Identifying Where to Focus in Reading Comprehension for Neural Question Generation
A first step in the task of automatically generating questions for testing reading comprehension is to identify \textit{question-worthy} sentences, i. e. sentences in a text passage that humans find it worthwhile to ask questions about.
Learning to Ask: Neural Question Generation for Reading Comprehension
We study automatic question generation for sentences from text passages in reading comprehension.
