Search Results for author:
Found 21 papers, 9 papers with code
Opinion-based Relational Pivoting for Cross-domain Aspect Term Extraction
In this paper, we investigate and establish empirically a prior conjecture, which suggests that the linguistic relations connecting opinion terms to their aspects transfer well across domains and therefore can be leveraged for cross-domain aspect term extraction.
Exploring the Boundaries of Low-Resource BERT Distillation
We also show that the distillation of large pre-trained models is more effective in real-life scenarios where limited amounts of labeled training are available.
CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
This approach focuses the reasoning process on generating an attribution-centric output.
Optimizing Retrieval-augmented Reader Models via Token Elimination
Fusion-in-Decoder (FiD) is an effective retrieval-augmented language model applied across a variety of open-domain tasks, such as question answering, fact checking, etc.
An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs
We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large.
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM
Our quantized length-adaptive MiniLM model (QuaLA-MiniLM) is trained only once, dynamically fits any inference scenario, and achieves an accuracy-efficiency trade-off superior to any other efficient approaches per any computational budget on the SQuAD1. 1 dataset (up to x8. 8 speedup with <1% accuracy loss).
Fast DistilBERT on CPUs
In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators.
Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs
The extraction of aspect terms is a critical step in fine-grained sentiment analysis of text.
Efficient Few-Shot Learning Without Prompts
This simple framework requires no prompts or verbalizers, and achieves high accuracy with orders of magnitude less parameters than existing techniques.
TangoBERT: Reducing Inference Cost by using Cascaded Architecture
In order to reduce this computational load in inference time, we present TangoBERT, a cascaded model architecture in which instances are first processed by an efficient but less accurate first tier model, and only part of those instances are additionally processed by a less efficient but more accurate second tier model.
Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length
Additionally, a separate model must be trained for each inference scenario with its distinct computational budget.
Prune Once for All: Sparse Pre-Trained Language Models
We show how the compressed sparse pre-trained models we trained transfer their knowledge to five different downstream natural language tasks with minimal accuracy loss.
Ranked #2 on
Natural Language Inference
on MultiNLI Dev
InterpreT: An Interactive Visualization Tool for Interpreting Transformers
With the increasingly widespread use of Transformer-based models for NLU/NLP tasks, there is growing interest in understanding the inner workings of these models, why they are so effective at a wide range of tasks, and how they can be further tuned and improved.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction
A fundamental task of fine-grained sentiment analysis is aspect and opinion terms extraction.
Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models
In this work-in-progress we combined the effectiveness of transfer learning provided by pre-trained masked language models with a semi-supervised approach to train a fast and compact model using labeled and unlabeled examples.
Q8BERT: Quantized 8Bit BERT
Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks.
Ranked #13 on
Semantic Textual Similarity
on STS Benchmark
ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System
We present ABSApp, a portable system for weakly-supervised aspect-based sentiment extraction.
Multi-Context Term Embeddings: the Use Case of Corpus-based Term Set Expansion
In this paper, we present a novel algorithm that combines multi-context term embeddings using a neural classifier and we test this approach on the use case of corpus-based term set expansion.
Term Set Expansion based NLP Architect by Intel AI Lab
We present SetExpander, a corpus-based system for expanding a seed set of terms into amore complete set of terms that belong to the same semantic class.
SetExpander: End-to-end Term Set Expansion Based on Multi-Context Term Embeddings
We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class.
Term Set Expansion based on Multi-Context Term Embeddings: an End-to-end Workflow
We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class.
