Search Results for author:
Found 22 papers, 16 papers with code
A Morphology-Based Investigation of Positional Encodings
How does the importance of positional encoding in pre-trained language models (PLMs) vary across languages with different morphological complexity?
LLM Augmented LLMs: Expanding Capabilities through Composition
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains.
Self-Influence Guided Data Reweighting for Language Model Pre-training
Once the pre-training corpus has been assembled, all data samples in the corpus are treated with equal importance during LM pre-training.
Multimodal Modeling For Spoken Language Identification
Spoken language identification refers to the task of automatically predicting the spoken language in a given utterance.
MASR: Multi-label Aware Speech Representation
In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-information that is often available for a given speech recording.
Label Aware Speech Representation Learning For Language Identification
In this paper, we propose a novel framework of combining self-supervised representation learning with the language label information for the pre-training task.
Knowledge-Rich Self-Supervision for Biomedical Entity Linking
Zero-shot entity linking has emerged as a promising direction for generalizing to new entities, but it still requires example gold entity mentions during training and canonical descriptions for all entities, both of which are rarely available outside of Wikipedia.
Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network
We develop a deep convolutional network that utilizes textual entity representations and demonstrate that our model outperforms recent KG completion methods in this challenging setting.
DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues
To successfully negotiate a deal, it is not enough to communicate fluently: pragmatic planning of persuasive negotiation strategies is essential.
MedFilter: Improving Extraction of Task-relevant Utterances from Doctor-Patient Conversations through Integration of Discourse Structure and Ontological Knowledge
In this paper, we propose the novel modeling approach MedFilter, which addresses these insights in order to increase performance at identifying and categorizing task-relevant utterances, and in so doing, positively impacts performance at a downstream information extraction task.
Improving Broad-Coverage Medical Entity Linking with Semantic Type Prediction and Large-Scale Datasets
To address the dearth of annotated training data for medical entity linking, we present WikiMed and PubMedDS, two large-scale medical entity linking datasets, and demonstrate that pre-training MedType on these datasets further improves entity linking performance.
A Re-evaluation of Knowledge Graph Completion Methods
Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs.
Ranked #25 on
Link Prediction
on FB15k-237
(MR metric)
Neural Graph Embedding Methods for Natural Language Processing
Knowledge graphs are structured representations of facts in a graph, where nodes represent entities and edges represent relationships between them.
Composition-based Multi-Relational Graph Convolutional Networks
Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it.
Ranked #22 on
Link Prediction
on FB15k-237
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE.
Ranked #11 on
Link Prediction
on YAGO3-10
Attention Interpretability Across NLP Tasks
The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque.
Dating Documents using Graph Convolution Networks
While existing approaches for these tasks assume accurate knowledge of the document date, this is not always available, especially for arbitrary documents from the Web.
Ranked #1 on
Document Dating
on APW
CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information
Open Information Extraction (OpenIE) methods extract (noun phrase, relation phrase, noun phrase) triples from text, resulting in the construction of large Open Knowledge Bases (Open KBs).
Ranked #1 on
Noun Phrase Canonicalization
on Ambiguous Dataset
Confidence-based Graph Convolutional Networks for Semi-Supervised Learning
Graph-based Semi-Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds and then utilizing the graph structure to predict label scores for the rest of the nodes in the graph.
RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information
In this paper, we propose RESIDE, a distantly-supervised neural relation extraction method which utilizes additional side information from KBs for improved relation extraction.
Ranked #5 on
Relation Extraction
on NYT Corpus
Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
Word embeddings have been widely adopted across several NLP applications.
Lovasz Convolutional Networks
We analyse local and global properties of graphs and demonstrate settings where LCNs tend to work better than GCNs.
