Spoken language identification refers to the task of automatically predi...
Speech representation learning approaches for non-semantic tasks such as...
Data scarcity is a crucial issue for the development of highly multiling...
Salient Span Masking (SSM) has shown itself to be an effective strategy ...
Recent research has revealed undesirable biases in NLP data and models.
...
New smartphone users have difficulty engaging with it and often use only...
Despite cross-lingual generalization demonstrated by pre-trained multili...
Recent years have witnessed much interest in temporal reasoning over
kno...
Recent research has revealed undesirable biases in NLP data and models.
...
NLU systems deployed in the real world are expected to be regularly upda...
In order for NLP technology to be widely applicable and useful, it needs...
Pre-trained multilingual language models such as mBERT and XLM-R have
de...
While recent work on multilingual language models has demonstrated their...
Style transfer is the task of rewriting an input sentence into a target ...
Knowledge-intensive NLP tasks can benefit from linking natural language ...
Recent research in multilingual language models (LM) has demonstrated th...
Pre-trained multilingual language models (LMs) have achieved state-of-th...
The ability to learn from limited data, or few-shot learning, is a desir...
Temporal Knowledge Graphs (Temporal KGs) extend regular Knowledge Graphs...
India is a multilingual society with 1369 rationalized languages and dia...
Robots that can manipulate objects in unstructured environments and
coll...
The recent growth in the popularity and success of deep learning models ...
Given a sentence (e.g., "I like mangoes") and a constraint (e.g., sentim...
Efficient representation of text documents is an important building bloc...
Knowledge Graph Completion (KGC) aims at automatically predicting missin...
Graph Convolutional Networks (GCNs) have recently been shown to be quite...
Most existing knowledge graphs suffer from incompleteness, which can be
...
What is the relationship between sentence representations learned by dee...
Document date is essential for many important tasks, such as document
re...
Open Information Extraction (OpenIE) methods extract (noun phrase, relat...
Predicting properties of nodes in a graph is an important problem with
a...
Knowledge of the creation date of documents facilitates several tasks su...
Distantly-supervised Relation Extraction (RE) methods train an extractor...
Developing accurate, transferable and computationally inexpensive machin...
Recently, word embeddings have been widely adopted across several NLP
ap...
Graph-based semi-supervised learning (SSL) is an important learning prob...
Semi-supervised learning on graph structured data has received significa...
Relation extraction is the problem of classifying the relationship betwe...
Low-rank tensor completion is a well-studied problem and has application...
Distant Supervision for Relation Extraction uses heuristically aligned t...
The goal of Event Schema Induction(ESI) is to identify schemas of events...
Automatic construction of large knowledge graphs (KG) by mining web-scal...
Given a set of documents from a specific domain (e.g., medical research
...
Questions form an integral part of our everyday communication, both offl...
In many scenarios, such as emergency response or ad hoc collaboration, i...