Speech separation with large-scale self-supervised learning arxiv.org/abs/2211.05172

BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning arxiv.org/abs/2211.05610

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models arxiv.org/abs/2211.10438

L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages arxiv.org/abs/2211.11418

Acceptability Judgements via Examining the Topology of Attention Maps arxiv.org/abs/2205.09630

SKDBERT: Compressing BERT via Stochastic Knowledge Distillation arxiv.org/abs/2211.14466

An Analysis of Social Biases Present in BERT Variants Across Multiple Languages arxiv.org/abs/2211.14402

An Automatic SOAP Classification System Using Weakly Supervision And Transfer Learning arxiv.org/abs/2211.14539

Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models arxiv.org/abs/2208.11445

Lexicon-injected Semantic Parsing for Task-Oriented Dialog arxiv.org/abs/2211.14508

The distribution of syntactic dependency distances arxiv.org/abs/2211.14620

CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis arxiv.org/abs/2204.00791

GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement arxiv.org/abs/2208.08965

Towards Better Document-level Relation Extraction via Iterative Inference arxiv.org/abs/2211.14470

Improving Passage Retrieval with Zero-Shot Question Generation arxiv.org/abs/2204.07496

Bidirectional Representations for Low Resource Spoken Language Understanding arxiv.org/abs/2211.14320

Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts arxiv.org/abs/2211.14459

Lexical Complexity Controlled Sentence Generation arxiv.org/abs/2211.14540

Searching for Discriminative Words in Multidimensional Continuous Feature Space arxiv.org/abs/2211.14631

Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models arxiv.org/abs/2208.11445