Search Results for author:
Found 290 papers, 134 papers with code
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.
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.
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).
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
Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding
Current systems of fine-grained entity typing use distant supervision in conjunction with existing knowledge bases to assign categories (type labels) to entity mentions.
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.
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.
CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases
We propose a novel domain-independent framework, called CoType, that runs a data-driven text segmentation algorithm to extract entity mentions, and jointly embeds entity mentions, relation mentions, text features and type labels into two low-dimensional spaces (for entity and relation mentions respectively), where, in each space, objects whose types are close will also have similar representations.
Ranked #11 on
Relation Extraction
on NYT11-HRL
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.
List-only Entity Linking
Traditional Entity Linking (EL) technologies rely on rich structures and properties in the target knowledge base (KB).
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.
Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance.
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.
Zero-Shot Transfer Learning for Event Extraction
Most previous event extraction studies have relied heavily on features derived from annotated event mentions, thus cannot be applied to new event types without annotation effort.
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.
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.
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.
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.
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.
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.
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.
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.
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).
Paper Abstract Writing through Editing Mechanism
We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract.
Ranked #1 on
Paper generation
on ACL Title and Abstract Dataset
Chengyu Cloze Test
We present a neural recommendation model for Chengyu, which is a special type of Chinese idiom.
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.
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.
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.
A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling
We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling.
Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text
Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings.
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.
Describing a Knowledge Base
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB).
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.
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.
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.
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.
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.
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.
PaperRobot: Incremental Draft Generation of Scientific Ideas
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper.
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).
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 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.
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.
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.
Reliability-aware Dynamic Feature Composition for Name Tagging
We design a set of word frequency-based reliability signals to indicate the quality of each word embedding.
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.
Low-Resource Name Tagging Learned with Weakly Labeled Data
Name tagging in low-resource languages or domains suffers from inadequate training data.
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.
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.
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.
Syntax-aware Multi-task Graph Convolutional Networks for Biomedical Relation Extraction
In this paper we tackle two unique challenges in biomedical relation extraction.
Learning to Learn Words from Visual Scenes
Language acquisition is the process of learning words from the surrounding scene.
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-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.
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.
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.
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.
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.
Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets.
Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding
Linguistic steganography studies how to hide secret messages in natural language cover texts.
A Survey of Knowledge-Enhanced Text Generation
To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models.
ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison.
Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding
Aspect-based sentiment analysis of review texts is of great value for understanding user feedback in a fine-grained manner.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Text Classification Using Label Names Only: A Language Model Self-Training Approach
In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents.
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.
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.
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.
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.
Learning from Lexical Perturbations for Consistent Visual Question Answering
Existing Visual Question Answering (VQA) models are often fragile and sensitive to input variations.
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks.
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.
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
Event coreference resolution is an important research problem with many applications.
Efficient Attentions for Long Document Summarization
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization.
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.
The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction
We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations.
Document-Level Event Argument Extraction by Conditional Generation
On the task of argument extraction, we achieve an absolute gain of 7. 6% F1 and 5. 7% F1 over the next best model on the RAMS and WikiEvents datasets respectively.
Document-level Event Extraction
Event Argument Extraction
+2
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.
Learning Shared Semantic Space for Speech-to-Text Translation
By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art.
Stage-wise Fine-tuning for Graph-to-Text Generation
Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders.
Ranked #3 on
Data-to-Text Generation
on WebNLG
(using extra training data)
Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method
Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism.
Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference
It then uses an entity linker to form a knowledge graph containing relevant background knowledge for the the entity mentions in the text.
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).
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.
Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information Extraction
The tasks of Rich Semantic Parsing, such as Abstract Meaning Representation (AMR), share similar goals with Information Extraction (IE) to convert natural language texts into structured semantic representations.
Event Time Extraction and Propagation via Graph Attention Networks
Grounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work.
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)
Separating Skills and Concepts for Novel Visual Question Answering
Generalization to out-of-distribution data has been a problem for Visual Question Answering (VQA) models.
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.
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.
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.
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.
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.
BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks
Biomedical entity linking is the task of linking entity mentions in a biomedical document to referent entities in a knowledge base.
Corpus-based Open-Domain Event Type Induction
As events of the same type could be expressed in multiple ways, we propose to represent each event type as a cluster of <predicate sense, object head> pairs.
Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base.
Chemical-Reaction-Aware Molecule Representation Learning
Molecule representation learning (MRL) methods aim to embed molecules into a real vector space.
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.
Skyformer: Remodel Self-Attention with Gaussian Kernel and Nyström Method
Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism.
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.
NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge
In this work, we present NewsClaims, a new benchmark for attribute-aware claim detection in the news domain.
MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding
Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question.
CLIP-Event: Connecting Text and Images with Event Structures
Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text.
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.
Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking
We use the profile to query the indexed search engine to retrieve candidate entities.
A Weibo Dataset for the 2022 Russo-Ukrainian Crisis
Online social networks such as Twitter and Weibo play an important role in how people stay informed and exchange reactions.
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.
Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation
Despite recent advances in detecting fake news generated by neural models, their results are not readily applicable to effective detection of human-written disinformation.
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.
Translation between Molecules and Natural Language
We present $\textbf{MolT5}$ $-$ a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings.
Ranked #4 on
Text-based de novo Molecule Generation
on ChEBI-20
Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners
The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction.
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.
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.
EA$^2$E: Improving Consistency with Event Awareness for Document-Level Argument Extraction
Events are inter-related in documents.
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
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.
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.
Incorporating Task-specific Concept Knowledge into Script Learning
In this paper, we present Tetris, a new task of Goal-Oriented Script Completion.
CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval
Given the absence of cross-lingual information retrieval datasets with claim-like queries, we train the retriever with our proposed Cross-lingual Inverse Cloze Task (X-ICT), a self-supervised algorithm that creates training instances by translating the title of a passage.
Ranked #1 on
Zero-shot Cross-lingual Fact-checking
on X-Fact
Cross-lingual Fact-checking
Cross-Lingual Information Retrieval
+4
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.
Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks
Notably, our proposed $\text{Zemi}_\text{LARGE}$ outperforms T0-3B by 16% on all seven evaluation tasks while being 3. 9x smaller in model size.
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 a Unified Multi-Dimensional Evaluator for Text Generation
We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.
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.
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models).
Weakly-Supervised Temporal Article Grounding
Specifically, given an article and a relevant video, WSAG aims to localize all ``groundable'' sentences to the video, and these sentences are possibly at different semantic scales.
Language Model Pre-Training with Sparse Latent Typing
Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks.
Ranked #6 on
Few-shot NER
on Few-NERD (INTRA)
(using extra training data)
Code4Struct: Code Generation for Few-Shot Event Structure Prediction
As a case study, we formulate Event Argument Extraction (EAE) as converting text into event-argument structures that can be represented as a class object using code.
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
A Close Look into the Calibration of Pre-trained Language Models
We observe a consistent change in calibration performance across six factors.
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.
Open-Vocabulary Argument Role Prediction for Event Extraction
Specifically, we formulate the role prediction problem as an in-filling task and construct prompts for a pre-trained language model to generate candidate roles.
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
To this end, we propose the framework CLORE (Classification by LOgical Reasoning on Explanations).
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.
Retrieval-Augmented Generative Question Answering for Event Argument Extraction
We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction.
Open Relation and Event Type Discovery with Type Abstraction
To tackle this problem, we introduce the idea of type abstraction, where the model is prompted to generalize and name the type.
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).
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.
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.
SmartBook: AI-Assisted Situation Report Generation
Further, experiments show that expert analysts tend to add more information into the SmartBook reports, with only 2. 3% of the existing tokens being deleted, meaning SmartBook can serve as a useful foundation for analysts to build upon when creating intelligence reports.
Tool Learning with Foundation Models
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
