Search Results for author:
Found 291 papers, 136 papers with code
Entity-aware Image Caption Generation
Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images.
Event Extraction with Generative Adversarial Imitation Learning
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN).
Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding
We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space to enable knowledge and resource transfer across languages.
Exploiting Task-Oriented Resources to Learn Word Embeddings for Clinical Abbreviation Expansion
In the medical domain, identifying and expanding abbreviations in clinical texts is a vital task for both better human and machine understanding.
Learning Phrase Embeddings from Paraphrases with GRUs
Learning phrase representations has been widely explored in many Natural Language Processing (NLP) tasks (e. g., Sentiment Analysis, Machine Translation) and has shown promising improvements.
Acquiring Background Knowledge to Improve Moral Value Prediction
In this paper, we address the problem of detecting expressions of moral values in tweets using content analysis.
Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures
Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities\_of\_residence) for a given entity from a large collection of source documents.
Aligning Coordinated Text Streams through Burst Information Network Construction and Decipherment
We introduce a novel Burst Information Network (BINet) representation that can display the most important information and illustrate the connections among bursty entities, events and keywords in the corpus.
Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre)
Recent research has shown great progress on fine-grained entity typing.
A Dependency-Based Neural Network for Relation Classification
Previous research on relation classification has verified the effectiveness of using dependency shortest paths or subtrees.
Ranked #5 on
Relation Classification
on SemEval 2010 Task 8
Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation
Entity Disambiguation aims to link mentions of ambiguous entities to a knowledge base (e. g., Wikipedia).
Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction
Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions.
Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition
This paper proposes to study fine-grained coordinated cross-lingual text stream alignment through a novel information network decipherment paradigm.
Incorporating Background Knowledge into Video Description Generation
We develop an approach that uses video meta-data to retrieve topically related news documents for a video and extracts the events and named entities from these documents.
Visualizing Group Dynamics based on Multiparty Meeting Understanding
Group discussions are usually aimed at sharing opinions, reaching consensus and making good decisions based on group knowledge.
Visual Attention Model for Name Tagging in Multimodal Social Media
Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram.
Platforms for Non-speakers Annotating Names in Any Language
We demonstrate two annotation platforms that allow an English speaker to annotate names for any language without knowing the language.
Multi-lingual Entity Discovery and Linking
We will then proceed to Cross-lingual EL and discuss methods that work across languages.
Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding
Integrating text and knowledge into a unified semantic space has attracted significant research interests recently.
Cross-lingual Name Tagging and Linking for 282 Languages
The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia.
List-only Entity Linking
Traditional Entity Linking (EL) technologies rely on rich structures and properties in the target knowledge base (KB).
ELISA-EDL: A Cross-lingual Entity Extraction, Linking and Localization System
We demonstrate ELISA-EDL, a state-of-the-art re-trainable system to extract entity mentions from low-resource languages, link them to external English knowledge bases, and visualize locations related to disaster topics on a world heatmap.
Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters
We study the problem of identifying the topics and sentiments and tracking their shifts from social media texts in different geographical regions during emergencies and disasters.
Creative Language Encoding under Censorship
People often create obfuscated language for online communication to avoid Internet censorship, share sensitive information, express strong sentiment or emotion, plan for secret actions, trade illegal products, or simply hold interesting conversations.
Image-Image Search for Comparable Corpora Construction
We present a novel method of comparable corpora construction.
Bitext Name Tagging for Cross-lingual Entity Annotation Projection
Instead of directly relying on word alignment results, this framework combines advantages of rule-based methods and deep learning methods by implementing two steps: First, generates a high-confidence entity annotation set on IL side with strict searching methods; Second, uses this high-confidence set to weakly supervise the model training.
Embracing Non-Traditional Linguistic Resources for Low-resource Language Name Tagging
Current supervised name tagging approaches are inadequate for most low-resource languages due to the lack of annotated data and actionable linguistic knowledge.
Open Relation Extraction and Grounding
Previous open Relation Extraction (open RE) approaches mainly rely on linguistic patterns and constraints to extract important relational triples from large-scale corpora.
Comparison of the Impact of Word Segmentation on Name Tagging for Chinese and Japanese
As long as (2) is ensured, the performance of word segmentation does not have appreciable impact on Chinese and Japanese name tagging.
Linguistic Resources for Entity Linking Evaluation: from Monolingual to Cross-lingual
To advance information extraction and question answering technologies toward a more realistic path, the U. S. NIST (National Institute of Standards and Technology) initiated the KBP (Knowledge Base Population) task as one of the TAC (Text Analysis Conference) evaluation tracks.
Biomedical Event Extraction based on Knowledge-driven Tree-LSTM
Event extraction for the biomedical domain is more challenging than that in the general news domain since it requires broader acquisition of domain-specific knowledge and deeper understanding of complex contexts.
Cross-lingual Multi-Level Adversarial Transfer to Enhance Low-Resource Name Tagging
We focus on improving name tagging for low-resource languages using annotations from related languages.
Multilingual Entity, Relation, Event and Human Value Extraction
This paper demonstrates a state-of-the-art end-to-end multilingual (English, Russian, and Ukrainian) knowledge extraction system that can perform entity discovery and linking, relation extraction, event extraction, and coreference.
Cross-lingual NIL Entity Clustering for Low-resource Languages
Clustering unlinkable entity mentions across documents in multiple languages (cross-lingual NIL Clustering) is an important task as part of Entity Discovery and Linking (EDL).
Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization
Transcripts of natural, multi-person meetings differ significantly from documents like news articles, which can make Natural Language Generation models for generating summaries unfocused.
Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining
Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking.
Zero-Shot Cross-lingual Name Retrieval for Low-Resource Languages
In this paper we address a challenging cross-lingual name retrieval task.
Syntax-aware Multi-task Graph Convolutional Networks for Biomedical Relation Extraction
In this paper we tackle two unique challenges in biomedical relation extraction.
Cross-lingual Structure Transfer for Relation and Event Extraction
The identification of complex semantic structures such as events and entity relations, already a challenging Information Extraction task, is doubly difficult from sources written in under-resourced and under-annotated languages.
An Attentive Fine-Grained Entity Typing Model with Latent Type Representation
In addition, we propose a two-step mention-aware attention mechanism to enable the model to focus on important words in mentions and contexts.
Training with Streaming Annotation
In this paper, we address a practical scenario where training data is released in a sequence of small-scale batches and annotation in earlier phases has lower quality than the later counterparts.
Cross-media Structured Common Space for Multimedia Event Extraction
We introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events and their arguments from multimedia documents.
Cross-lingual Structure Transfer for Zero-resource Event Extraction
Most of the current cross-lingual transfer learning methods for Information Extraction (IE) have been only applied to name tagging.
A Joint Neural Model for Information Extraction with Global Features
OneIE performs end-to-end IE in four stages: (1) Encoding a given sentence as contextualized word representations; (2) Identifying entity mentions and event triggers as nodes; (3) Computing label scores for all nodes and their pairwise links using local classifiers; (4) Searching for the globally optimal graph with a beam decoder.
GAIA: A Fine-grained Multimedia Knowledge Extraction System
We present the first comprehensive, open source multimedia knowledge extraction system that takes a massive stream of unstructured, heterogeneous multimedia data from various sources and languages as input, and creates a coherent, structured knowledge base, indexing entities, relations, and events, following a rich, fine-grained ontology.
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation
To combat COVID-19, both clinicians and scientists need to digest vast amounts of relevant biomedical knowledge in scientific literature to understand the disease mechanism and related biological functions.
Global Attention for Name Tagging
Many name tagging approaches use local contextual information with much success, but fail when the local context is ambiguous or limited.
KompaRe: A Knowledge Graph Comparative Reasoning System
In detail, we develop KompaRe, the first of its kind prototype system that provides comparative reasoning capability over large knowledge graphs.
Connecting the Dots: Event Graph Schema Induction with Path Language Modeling
Event schemas can guide our understanding and ability to make predictions with respect to what might happen next.
Semi-supervised New Event Type Induction and Event Detection
We design a Semi-Supervised Vector Quantized Variational Autoencoder framework to automatically learn a discrete latent type representation for each seen and unseen type and optimize them using seen type event annotations.
Learning from Lexical Perturbations for Consistent Visual Question Answering
Existing Visual Question Answering (VQA) models are often fragile and sensitive to input variations.
White Paper: Challenges and Considerations for the Creation of a Large Labelled Repository of Online Videos with Questionable Content
This white paper presents a summary of the discussions regarding critical considerations to develop an extensive repository of online videos annotated with labels indicating questionable content.
Controllable and Diverse Text Generation in E-commerce
The algorithm is injected into a Conditional Variational Autoencoder (CVAE), allowing \textit{Apex} to control both (i) the order of keywords in the generated sentences (conditioned on the input keywords and their order), and (ii) the trade-off between diversity and accuracy.
Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
For example, with "add milk to my cart", a customer may refer to a certain organic product, while some customers may want to re-order products they regularly purchase.
Towards Robust Neural Retrieval Models with Synthetic Pre-Training
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems.
VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension
Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for production use.
Deep Learning on Graphs for Natural Language Processing
Due to its great power in modeling non-Euclidean data like graphs or manifolds, deep learning on graph techniques (i. e., Graph Neural Networks (GNNs)) have opened a new door to solving challenging graph-related NLP problems.
A Unified Transformer-based Framework for Duplex Text Normalization
In addition, we also create a cleaned dataset from the Spoken Wikipedia Corpora for German and report the performance of our systems on the dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Fine-Grained Chemical Entity Typing with Multimodal Knowledge Representation
Automated knowledge discovery from trending chemical literature is essential for more efficient biomedical research.
IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System
A large portion of chemistry literature focuses on new molecules and reactions between molecules.
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.
Joint Detection and Coreference Resolution of Entities and Events with Document-level Context Aggregation
The tasks performed by this system are entity and event identification, typing, and coreference resolution.
InfoSurgeon: Cross-Media Fine-grained Information Consistency Checking for Fake News Detection
To defend against machine-generated fake news, an effective mechanism is urgently needed.
Fine-grained Information Extraction from Biomedical Literature based on Knowledge-enriched Abstract Meaning Representation
In this paper, we propose a novel biomedical Information Extraction (IE) model to tackle these two challenges and extract scientific entities and events from English research papers.
Joint Multimedia Event Extraction from Video and Article
We introduce the new task of Video MultiMedia Event Extraction (Video M2E2) and propose two novel components to build the first system towards this task.
Learning Invariant Representations on Multilingual Language Models for Unsupervised Cross-Lingual Transfer
Recent advances in neural modeling have produced deep multilingual language models capable of extracting cross-lingual knowledge from unparallel texts, as evidenced by their decent zero-shot transfer performance.
Personalized Entity Resolution with Dynamic Heterogeneous KnowledgeGraph Representations
We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings.
EventKE: Event-Enhanced Knowledge Graph Embedding
Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities.
Coreference by Appearance: Visually Grounded Event Coreference Resolution
Event coreference resolution is critical to understand events in the growing number of online news with multiple modalities including text, video, speech, etc.
Semi-supervised New Event Type Induction and Description via Contrastive Loss-Enforced Batch Attention
In contrast, we present a novel approach to semi-supervised new event type induction using a masked contrastive loss, which learns similarities between event mentions by enforcing an attention mechanism over the data minibatch.
P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization
Our framework decomposes event detection into an identification task and a localization task.
What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys
We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge in the context of conversational surveys.
Seeded Hierarchical Clustering for Expert-Crafted Taxonomies
Practitioners from many disciplines (e. g., political science) use expert-crafted taxonomies to make sense of large, unlabeled corpora.
Schema-Guided Event Graph Completion
Existing link prediction or graph completion methods have difficulty dealing with event graphs because they are usually designed for a single large graph such as a social network or a knowledge graph, rather than multiple small dynamic event graphs.
Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging.
Event Schema Induction with Double Graph Autoencoders
To induce event schemas from historical events, previous work uses an event-by-event scheme, ignoring the global structure of the entire schema graph.
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs.
New Frontiers of Information Extraction
This tutorial targets researchers and practitioners who are interested in AI and ML technologies for structural information extraction (IE) from unstructured textual sources.
Incorporating Task-specific Concept Knowledge into Script Learning
In this paper, we present Tetris, a new task of Goal-Oriented Script Completion.
Learning to Decompose Visual Features with Latent Textual Prompts
Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations.
Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning
Research on neural IR has so far been focused primarily on standard supervised learning settings, where it outperforms traditional term matching baselines.
A Zero-Shot Claim Detection Framework Using Question Answering
In recent years, there has been an increasing interest in claim detection as an important building block for misinformation detection.
Video Event Extraction via Tracking Visual States of Arguments
Video event extraction aims to detect salient events from a video and identify the arguments for each event as well as their semantic roles.
Ensemble Transfer Learning for Multilingual Coreference Resolution
Leveraging the idea that the coreferential links naturally exist between anchor texts pointing to the same article, our method builds a sizeable distantly-supervised dataset for the target language that consists of tens of thousands of documents.
Human-in-the-Loop Schema Induction
Schema induction builds a graph representation explaining how events unfold in a scenario.
Inference-time Re-ranker Relevance Feedback for Neural Information Retrieval
Neural information retrieval often adopts a retrieve-and-rerank framework: a bi-encoder network first retrieves K (e. g., 100) candidates that are then re-ranked using a more powerful cross-encoder model to rank the better candidates higher.
RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought
To detect factual inconsistency, RCoT first asks LLMs to reconstruct the problem based on generated solutions.
LM-Switch: Lightweight Language Model Conditioning in Word Embedding Space
As pre-training and fine-tuning are costly and might negatively impact model performance, it is desired to efficiently adapt an existing model to different conditions such as styles, sentiments or narratives, when facing different audiences or scenarios.
Explaining Emergent In-Context Learning as Kernel Regression
Then, we empirically investigate the in-context behaviors of language models.
Understanding the Effect of Data Augmentation on Knowledge Distillation
However, such data augmentation methods are sub-optimal for knowledge distillation since the teacher model could provide label distributions and is more tolerant to semantic shifts.
ManiTweet: A New Benchmark for Identifying Manipulation of News on Social Media
We present a novel task, identifying manipulation of news on social media, which aims to detect manipulation in social media posts and identify manipulated or inserted information.
Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs
Building cross-model intelligence that can understand charts and communicate the salient information hidden behind them is an appealing challenge in the vision and language(V+L) community.
Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy
To evaluate and address the core challenge, we propose a new task formulation of the information updating task that only requires the provision of an unstructured updating corpus and evaluates the performance of information updating on the generalizability to question-answer pairs pertaining to the updating information.
C-PMI: Conditional Pointwise Mutual Information for Turn-level Dialogue Evaluation
Existing reference-free turn-level evaluation metrics for chatbots inadequately capture the interaction between the user and the system.
SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design
We are given a small "personalized dataset" of 10-20 drug synergy relationships in the context of specific cancer cell targets.
Mitigating the Alignment Tax of RLHF
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different reward-tax trade-offs, we propose Adaptive Model Averaging (AMA) to adaptively find various combination ratios of model layers.
Parameter-Efficient Tuning Helps Language Model Alignment
To this end, prior works incorporate controllable generations for alignment to make language models learn multiple preferences and provide outputs with different preferences during inference if asked.
Enabling Language Models to Implicitly Learn Self-Improvement
Specifically, we reformulate the training objective of reinforcement learning from human feedback (RLHF) -- instead of maximizing response quality for a given input, we maximize the quality gap of the response conditioned on a reference response.
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.
Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models
The dominance of proprietary LLMs has led to restricted access and raised information privacy concerns.
Social Commonsense-Guided Search Query Generation for Open-Domain Knowledge-Powered Conversations
Open-domain dialog involves generating search queries that help obtain relevant knowledge for holding informative conversations.
Defining a New NLP Playground
The recent explosion of performance of large language models (LLMs) has changed the field of Natural Language Processing (NLP) more abruptly and seismically than any other shift in the field's 80-year history.
DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
The critique NLF identifies the strengths and weaknesses of the responses and is used to align the LVLMs with human preferences.
InfoPattern: Unveiling Information Propagation Patterns in Social Media
Social media play a significant role in shaping public opinion and influencing ideological communities through information propagation.
If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code).
Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain
In this paper, we introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method to mitigate such challenges.
Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate
Fact-checking research has extensively explored verification but less so the generation of natural-language explanations, crucial for user trust.
Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement
The increasing demand for personalized interactions with large language models (LLMs) calls for the development of methodologies capable of accurately and efficiently identifying user opinions and preferences.
LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation
In this paper, we first investigate the potential of LVLM on multimodal misinformation detection.
EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
The dynamic nature of real-world information necessitates efficient knowledge editing (KE) in large language models (LLMs) for knowledge updating.
Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models
Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease.
Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization
In addition, it is still unclear how well an OpenQA model can transfer to completely new knowledge domains.
Text-Based Reasoning About Vector Graphics
By casting an image to a text-based representation, we can leverage the power of language models to learn alignment from SVG to visual primitives and generalize to unseen question-answering tasks.
MUSE: Textual Attributes Guided Portrait Painting Generation
Experiments show that our approach can accurately illustrate 78% textual attributes, which also help MUSE capture the subject in a more creative and expressive way.
NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly
Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions.
Scientific Opinion Summarization: Meta-review Generation with Checklist-guided Iterative Introspection
Opinions in the scientific domain can be divergent, leading to controversy or consensus among reviewers.
Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting
Automatic response forecasting for news media plays a crucial role in enabling content producers to efficiently predict the impact of news releases and prevent unexpected negative outcomes such as social conflict and moral injury.
Named Entity Recognition Under Domain Shift via Metric Learning for Life Sciences
In our experiments, we observed that such a model is prone to mislabeling the source entities, which can often appear in the text, as the target entities.
Fact Checking Beyond Training Set
We then focus on the reader component and propose to train it such that it is insensitive towards the order of claims and evidence documents.
Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval
On two public IR benchmarks, we empirically show that the proposed method helps improve both the model's attention patterns and retrieval performance, including in zero-shot settings.
RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor
In this paper, we present RESIN-EDITOR, an interactive event graph visualizer and editor designed for analyzing complex events.
Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning
While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML.
COVID-19 Claim Radar: A Structured Claim Extraction and Tracking System
To tackle the challenge of accurate and timely communication regarding the COVID-19 pandemic, we present a COVID-19 Claim Radar to automatically extract supporting and refuting claims on a daily basis.
OpenPI-C: A Better Benchmark and Stronger Baseline for Open-Vocabulary State Tracking
Open-vocabulary state tracking is a more practical version of state tracking that aims to track state changes of entities throughout a process without restricting the state space and entity space.
Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction
Fine-grained few-shot entity extraction in the chemical domain faces two unique challenges.
Chengyu Cloze Test
We present a neural recommendation model for Chengyu, which is a special type of Chinese idiom.
Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
We surprisingly find that discrete text tokens coupled with a pretrained contrastive text model yields the best performance, which can even outperform state-of-the-art on the iVQA and How2QA datasets without additional training on millions of video-text data.
Ranked #1 on
Video Question Answering
on iVQA
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
To this end, we propose the framework CLORE (Classification by LOgical Reasoning on Explanations).
Improving Question Answering with External Knowledge
We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus.
Measuring the Effect of Influential Messages on Varying Personas
Our analysis shows that the best-performing models are capable of predicting responses that are consistent with the personas, and as a byproduct, the task formulation also enables many interesting applications in the analysis of social network groups and their opinions, such as the discovery of extreme opinion groups.
Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking
Pretrained large language models have revolutionized many applications but still face challenges related to cultural bias and a lack of cultural commonsense knowledge crucial for guiding cross-culture communication and interactions.
GENE: Global Event Network Embedding
Current methods for event representation ignore related events in a corpus-level global context.
Multimedia Generative Script Learning for Task Planning
Goal-oriented generative script learning aims to generate subsequent steps to reach a particular goal, which is an essential task to assist robots or humans in performing stereotypical activities.
SumREN: Summarizing Reported Speech about Events in News
A primary objective of news articles is to establish the factual record for an event, frequently achieved by conveying both the details of the specified event (i. e., the 5 Ws; Who, What, Where, When and Why regarding the event) and how people reacted to it (i. e., reported statements).
ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
We adopt a weakly-supervised approach to directly generate visual event structures from captions for ViStruct training, capitalizing on abundant image-caption pairs from the web.
A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages
We also show extrinsically that incorporating our POS tagger into a name tagger leads to state-of-the-art tagging performance in Sinhalese and Kinyarwanda, two languages with nearly no labeled POS data available.
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules.
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework
In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework.
Making Pre-trained Language Models both Task-solvers and Self-calibrators
In this work, we consider the practical scenario that we need to effectively utilize training samples to make PLMs both task-solvers and self-calibrators.
ADEPT: A DEbiasing PrompT Framework
Despite this, relatively few efforts have been made to debias PLMs by prompt tuning with continuous prompts compared to its discrete counterpart.
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
Non-Sequential Graph Script Induction via Multimedia Grounding
To automate the induction of such graph scripts for given tasks, we propose to take advantage of loosely aligned videos of people performing the tasks.
The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions
Recent progress in Large Language Models (LLMs) has produced models that exhibit remarkable performance across a variety of NLP tasks.
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction
Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts.
Ranked #1 on
Relation Extraction
on ACE 2005
(Sentence Encoder metric)
Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction
Event time is one of the most important features for event-event temporal relation extraction.
A Close Look into the Calibration of Pre-trained Language Models
We observe a consistent change in calibration performance across six factors.
GLEN: General-Purpose Event Detection for Thousands of Types
Finally, we perform error analysis and show that label noise is still the largest challenge for improving performance for this new dataset.
Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization
Motivated by how humans inspect factual inconsistency in summaries, we propose an interpretable fine-grained inconsistency detection model, FineGrainFact, which explicitly represents the facts in the documents and summaries with semantic frames extracted by semantic role labeling, and highlights the related semantic frames to predict inconsistency.
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.
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
Ranked #5 on
Link Prediction
on UMLS
Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning
With emerging online topics as a source for numerous new events, detecting unseen / rare event types presents an elusive challenge for existing event detection methods, where only limited data access is provided for training.
Lifelong Event Detection with Knowledge Transfer
We focus on lifelong event detection as an exemplar case and propose a new problem formulation that is also generalizable to other IE tasks.
Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport
Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged.
Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification
Event schemas are a form of world knowledge about the typical progression of events.
Raw-to-End Name Entity Recognition in Social Media
Our model neither requires the conversion from character sequences to word sequences, nor assumes tokenizer can correctly detect all word boundaries.
