Search Results for author:
Found 89 papers, 57 papers with code
PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to.
Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting
However, the imbalanced training dataset leads to poor performance on rare senses and zero-shot senses.
A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolution in English
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to.
Conceptual and Unbiased Reasoning in Language Models
Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition.
Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance.
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation
Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study.
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents.
Monte Carlo Tree Search in the Presence of Transition Uncertainty
We study and improve MCTS in the context where the environment model is given but imperfect.
CLOMO: Counterfactual Logical Modification with Large Language Models
In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs).
Efficient Reinforcement Learning from Partial Observability
In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for algorithms that conflate observations with state.
Partially Observable Reinforcement Learning
reinforcement-learning
AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph
Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models.
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
In response to these challenges, we introduces Chain-of-Noting (CoN), a novel approach aimed at improving the robustness of RALMs in facing noisy, irrelevant documents and in handling unknown scenarios.
A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning
In this paper, we take a closer look at the self-verification abilities of LLMs in the context of logical reasoning, focusing on their ability to identify logical fallacies accurately.
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
On the Dimensionality of Sentence Embeddings
Therefore, we propose a two-step training method for sentence representation learning models, wherein the encoder and the pooler are optimized separately to mitigate the overall performance loss in low-dimension scenarios.
StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding
Analogy-making between narratives is crucial for human reasoning.
SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation
Established reference-based evaluation metrics rely on human-annotated reasoning chains to assess the model-derived chains.
LASER: LLM Agent with State-Space Exploration for Web Navigation
We evaluate our proposed LLM Agent with State-Space ExploRation (LASER) on both the WebShop task and amazon. com.
A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
Specifically, the detection technique achieves a recall of ~88% and the mitigation technique successfully mitigates 57. 6% of the correctly detected hallucinations.
Towards Open-Domain Topic Classification
We introduce an open-domain topic classification system that accepts user-defined taxonomy in real time.
Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
However, knowledge conflicts arise when there is a mismatch between the actual temporal relations of events in the context and the prior knowledge or biases learned by the model.
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations
It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space.
PIVOINE: Instruction Tuning for Open-world Information Extraction
In particular, we construct INSTRUCTOPENWIKI, a substantial instruction tuning dataset for Open-world IE enriched with a comprehensive corpus, extensive annotations, and diverse instructions.
Open-Domain Event Graph Induction for Mitigating Framing Bias
However, none of the existing methods have explicitly addressed the issue of framing bias that is inherent in news articles.
CEO: Corpus-based Open-Domain Event Ontology Induction
Existing event-centric NLP models often only apply to the pre-defined ontology, which significantly restricts their generalization capabilities.
COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective
This paper proposes a new task to detect commonsense causation between two events in an event sequence (i. e., context), called contextualized commonsense causal reasoning.
Faithful Question Answering with Monte-Carlo Planning
In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps.
Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay
In this work, we further exploit the information in the replay memory by treating it as an empirical \emph{Replay Memory MDP (RM-MDP)}.
Global Constraints with Prompting for Zero-Shot Event Argument Classification
In this work, we propose to use global constraints with prompting to effectively tackles event argument classification without any annotation and task-specific training.
Video State-Changing Object Segmentation
Learning about object state changes in Video Object Segmentation (VOS) is crucial for understanding and interacting with the visual world.
Rethinking with Retrieval: Faithful Large Language Model Inference
To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the decomposed reasoning steps obtained from the chain-of-thought (CoT) prompting.
Ranked #2 on
Question Answering
on StrategyQA
On-the-fly Denoising for Data Augmentation in Natural Language Understanding
However, data augmentation may introduce noisy data that impairs training.
ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion
However, there has been limited research on the zero-shot KBC settings, where we need to deal with unseen entities and relations that emerge in a constantly growing knowledge base.
Build generally reusable agent-environment interaction models
This paper tackles the problem of how to pre-train a model and make it generally reusable backbones for downstream task learning.
Efficient Zero-shot Event Extraction with Context-Definition Alignment
We argue that using the static embedding of the event type name might not be enough because a single word could be ambiguous, and we need a sentence to define the type semantics accurately.
Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach
We distill several insights from our analysis on study the peer review process with the help of large LMs.
Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models
In this paper, we develop a novel semi-parametric language model architecture, Knowledge-in-Context (KiC), which empowers a parametric text-to-text language model with a knowledge-rich external memory.
Ranked #5 on
Question Answering
on StoryCloze
Salience Allocation as Guidance for Abstractive Summarization
Recent literature adds extractive summaries as guidance for abstractive summarization models to provide hints of salient content and achieves better performance.
Ranked #7 on
Abstractive Text Summarization
on CNN / Daily Mail
MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
To this end, we propose a comprehensive logical reasoning explanation form.
Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination
Large-scale pretrained language models have made significant advances in solving downstream language understanding tasks.
Ranked #2 on
Visual Commonsense Tests
on ViComTe-color
PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population
We propose PseudoReasoner, a semi-supervised learning framework for CSKB population that uses a teacher model pre-trained on CSKBs to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from.
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning.
Multilingual Word Sense Disambiguation with Unified Sense Representation
As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the lexical semantics of words under specific contexts.
SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller
In this paper, we propose a new task of sub-event generation for an unseen process to evaluate the understanding of the coherence of sub-event actions and objects.
CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
We first align commonsense tasks with relevant knowledge from commonsense knowledge bases and ask humans to annotate whether the knowledge is enough or not.
Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction
In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives.
Ranked #3 on
Temporal Relation Classification
on MATRES
Are All Steps Equally Important? Benchmarking Essentiality Detection of Events
In this paper, we address this gap by examining the extent to which current models comprehend the essentiality of step events in relation to a goal event.
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.
VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
In this paper, we propose VD-PCR, a novel framework to improve Visual Dialog understanding with Pronoun Coreference Resolution in both implicit and explicit ways.
METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation
Advances on QA explanation propose to explain the answers with entailment trees composed of multiple entailment steps.
Query2Particles: Knowledge Graph Reasoning with Particle Embeddings
The query embedding method is proposed to answer these queries by jointly encoding queries and entities to the same embedding space.
ROCK: Causal Inference Principles for Reasoning about Commonsense Causality
Commonsense causality reasoning (CCR) aims at identifying plausible causes and effects in natural language descriptions that are deemed reasonable by an average person.
A Simple Unified Framework for Anomaly Detection in Deep Reinforcement Learning
In this paper, we propose a simple yet effective anomaly detection framework for deep RL algorithms that simultaneously considers random, adversarial and out-of-distribution~(OOD) state outliers.
Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset
Experimental results show that generalizing commonsense reasoning on unseen assertions is inherently a hard task.
Learning Constraints and Descriptive Segmentation for Subevent Detection
The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes.
Exophoric Pronoun Resolution in Dialogues with Topic Regularization
Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem.
Zero-shot Event Extraction via Transfer Learning: Challenges and Insights
Event extraction has long been a challenging task, addressed mostly with supervised methods that require expensive annotation and are not extensible to new event ontologies.
Event-Centric Natural Language Processing
This tutorial targets researchers and practitioners who are interested in AI technologies that help machines understand natural language text, particularly real-world events described in the text.
Do Boat and Ocean Suggest Beach? Dialogue Summarization with External Knowledge
To evaluate the inference capability of different methods, we also propose a new evaluation metric based on CODC.
RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System
We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video).
Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema
To support this claim, we first show that the current evaluation method of WS is sub-optimal and propose a modification that uses twin sentences for evaluation.
Ranked #24 on
Coreference Resolution
on Winograd Schema Challenge
ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities
After conceptualization with Probase, a selectional preference based concept-instance relational knowledge base, our concept graph contains 15 million conceptualized eventualities and 224 million edges between them.
Joint Coreference Resolution and Character Linking for Multiparty Conversation
Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations.
DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge
On the other hand, generation models have the potential to automatically generate more knowledge.
CoCoLM: COmplex COmmonsense Enhanced Language Model with Discourse Relations
Large-scale pre-trained language models have demonstrated strong knowledge representation ability.
Unsupervised Label-aware Event Trigger and Argument Classification
Rather than relying on annotated data, our model matches the semantics of identified events with those of event type labels.
Learning Contextual Causality from Time-consecutive Images
Compared with pure text-based approaches, learning causality from the visual signal has the following advantages: (1) Causality knowledge belongs to the commonsense knowledge, which is rarely expressed in the text but rich in videos; (2) Most events in the video are naturally time-ordered, which provides a rich resource for us to mine causality knowledge from; (3) All the objects in the video can be used as context to study the contextual property of causal relations.
What Are You Trying to Do? Semantic Typing of Event Processes
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given anevent process, attempts to infer free-form typelabels describing (i) the type of action made bythe process and (ii) the type of object the pro-cess seeks to affect.
Analogous Process Structure Induction for Sub-event Sequence Prediction
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories.
Joint Constrained Learning for Event-Event Relation Extraction
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other.
"What Are You Trying to Do?" Semantic Typing of Event Processes
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given an event process, attempts to infer free-form type labels describing (i) the type of action made by the process and (ii) the type of object the process seeks to affect.
When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models
We also demonstrate that distributional methods are ideal to make up for pattern-based ones in such cases.
A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolution
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to.
Efficient Reinforcement Learning Development with RLzoo
RLzoo provides developers with (i) high-level yet flexible APIs for prototyping DRL agents, and further customising the agents for best performance, (ii) a model zoo where users can import a wide range of DRL agents and easily compare their performance, and (iii) an algorithm that can automatically construct DRL agents with custom components (which are critical to improve agent's performance in custom applications).
Enriching Large-Scale Eventuality Knowledge Graph with Entailment Relations
Computational and cognitive studies suggest that the abstraction of eventualities (activities, states, and events) is crucial for humans to understand daily eventualities.
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge
Experimental results prove that even though pre-trained language representation models have achieved promising progress on the original WSC dataset, they are still struggling at WinoWhy.
TransOMCS: From Linguistic Graphs to Commonsense Knowledge
Commonsense knowledge acquisition is a key problem for artificial intelligence.
Multiplex Word Embeddings for Selectional Preference Acquisition
Therefore, in this paper, we propose a multiplex word embedding model, which can be easily extended according to various relations among words.
What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues
To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate whether and how the visual information can help resolve pronouns in dialogues.
Multilingual and Multi-Aspect Hate Speech Analysis
Current research on hate speech analysis is typically oriented towards monolingual and single classification tasks.
Iterative Update and Unified Representation for Multi-Agent Reinforcement Learning
In this method, iterative update can greatly alleviate the nonstationarity of the environment, unified representation can speed up the interaction with environment and avoid the linear growth of memory usage.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Knowledge-aware Pronoun Coreference Resolution
Resolving pronoun coreference requires knowledge support, especially for particular domains (e. g., medicine).
Incorporating Context and External Knowledge for Pronoun Coreference Resolution
Linking pronominal expressions to the correct references requires, in many cases, better analysis of the contextual information and external knowledge.
SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition
Selectional Preference (SP) is a commonly observed language phenomenon and proved to be useful in many natural language processing tasks.
ASER: A Large-scale Eventuality Knowledge Graph
Understanding human's language requires complex world knowledge.
A Logarithmic Barrier Method For Proximal Policy Optimization
Specifically, a new surrogate objective with interior penalty method is proposed to avoid the defect arose from exterior penalty method.
