Deep contextualized word representations
read the original abstract
We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.
This paper has not been read by Pith yet.
Forward citations
Cited by 40 Pith papers
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reason...
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio versions via TTS and noise, showing model-dependent performance with small text-to-voice gaps of 1.8-4.8 points on Confetti and When2Call.
-
A Hormone-inspired Emotion Layer for Transformer language models (HELT)
HormoneT5 augments T5 with a hormone-inspired block that predicts six continuous emotion values and uses them to modulate responses, reporting over 85% per-hormone accuracy and human preference for emotional quality.
-
Massive Activations in Large Language Models
Massive activations are constant large values in LLMs that function as indispensable bias terms and concentrate attention probabilities on specific tokens.
-
GraphCodeBERT: Pre-training Code Representations with Data Flow
GraphCodeBERT uses data flow graphs in pre-training to capture semantic code structure and reaches state-of-the-art results on code search, clone detection, translation, and refinement.
-
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
BART introduces a denoising pretraining method for seq2seq models that matches RoBERTa on GLUE and SQuAD while setting new state-of-the-art results on abstractive summarization, dialogue, and QA with up to 6 ROUGE gains.
-
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
T5 casts all NLP tasks as text-to-text generation, systematically explores pre-training choices, and reaches strong performance on summarization, QA, classification and other tasks via large-scale training on the Colo...
-
Fine-Tuning Language Models from Human Preferences
Language models fine-tuned via RL on 5k-60k human preference comparisons produce stylistically better text continuations and human-preferred summaries that sometimes copy input sentences.
-
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
Intra-layer model parallelism in PyTorch enables training of 8.3B-parameter transformers, achieving SOTA perplexity of 10.8 on WikiText103 and 66.5% accuracy on LAMBADA.
-
PubMedQA: A Dataset for Biomedical Research Question Answering
PubMedQA supplies 273k+ biomedical QA instances that require reasoning over research abstracts to produce yes/no/maybe answers.
-
FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
FinBERT adapts BERT to the financial domain and outperforms prior state-of-the-art methods on financial sentiment analysis tasks.
-
XLNet: Generalized Autoregressive Pretraining for Language Understanding
XLNet is a generalized autoregressive pretraining method that learns bidirectional contexts via permutation-based factorization and outperforms BERT on 20 NLP tasks.
-
Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
Introduces TableGrid Navigation (TGN) and Progressive Inference Prompting (PIP) as training-free structured prompting frameworks that improve LLM performance on table question answering over baselines on TableBench an...
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance...
-
BoolXLLM: LLM-Assisted Explainability for Boolean Models
BoolXLLM augments an existing Boolean rule learner with LLMs for feature selection, discretization thresholds, and natural-language rule translation to improve interpretability while preserving accuracy.
-
ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models
ADE scales multi-anchor word representations to transformers via Vocabulary Projection, Grouped Positional Encoding, and context-aware reweighting, achieving 98.7% fewer trainable parameters than DeBERTa-v3-base while...
-
Demystifying CLIP Data
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
A General Language Assistant as a Laboratory for Alignment
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
-
Scaling Laws for Transfer
Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.
-
Adaptive Federated Optimization
Proposes federated adaptive optimizers (FedAdagrad, FedAdam, FedYogi) with convergence analysis for non-convex objectives under data heterogeneity and reports empirical gains over FedAvg.
-
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
CodeBERT pre-trains a bimodal model on code and text pairs plus unimodal data to achieve state-of-the-art results on natural language code search and code documentation generation.
-
How Much Knowledge Can You Pack Into the Parameters of a Language Model?
Fine-tuned language models store knowledge in parameters to answer questions competitively with retrieval-based open-domain QA systems.
-
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Hugging Face releases an open-source Python library that supplies a unified API and pretrained weights for major Transformer architectures used in natural language processing.
-
CTRL: A Conditional Transformer Language Model for Controllable Generation
CTRL is a large conditional transformer language model that uses naturally occurring control codes to steer text generation style and content.
-
Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysis
Authors release a new 800-sentence gender-balanced profession dataset and use it to test occupational gender stereotypes in three sentiment analysis models.
-
Automatic Reflection Level Classification in Hungarian Student Essays
Classical machine learning models outperform Hungarian transformers slightly in overall performance (71% vs 68% average score) for classifying reflection levels in student essays, though transformers handle rare class...
-
Knowledge-aware Pronoun Coreference Resolution
A neural model with knowledge attention outperforms baselines on pronoun coreference in two domains and cross-domain by incorporating KG triplets.
-
Patent Claim Generation by Fine-Tuning OpenAI GPT-2
Fine-tunes GPT-2 on patent claims, probes training steps, analyzes conditional and unconditional sampling outputs, proposes a new sampling method, and releases an email bot for exploration.
-
Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments
Empirical comparison finds that self-supervised representations vary in capturing agent state and generalizing to new levels or textures depending on environment visuals and dynamics.
-
ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
ClinicalBERT applies BERT-style transformers to clinical notes and outperforms baselines on 30-day readmission prediction while revealing human-judged medical concept links.
-
ClinQueryAgent: A Conversational Agent for Population Health Management
The paper introduces ClinQueryAgent, a conversational agent that converts natural language queries into database queries for population health management while keeping patient data secure, and reports its use by 128 s...
-
Baichuan 2: Open Large-scale Language Models
Baichuan 2 presents 7B and 13B LLMs trained on 2.6T tokens that match or exceed similar open models on MMLU, CMMLU, GSM8K, HumanEval and excel in medicine and law.
-
Automatically Learning Construction Injury Precursors from Text
Standard NLP classifiers can surface valid injury precursors from raw construction safety reports.
-
Investigating Self-Attention Network for Chinese Word Segmentation
Self-attention networks achieve competitive results to BiLSTM-CRF on Chinese word segmentation, with BERT and word integration yielding the best reported performance on six heterogeneous domain benchmarks.
-
Neural Language Model Based Training Data Augmentation for Weakly Supervised Early Rumor Detection
Neural language model augments limited labeled rumor tweets using unlabeled event data, expanding datasets by ~200% and improving F-score by 12.1% in detection models.
-
Transfer Learning for Risk Classification of Social Media Posts: Model Evaluation Study
Finetuning GPT-1 on 150000 unlabeled Reachout.com posts then feeding the features into AutoML yields a new state-of-the-art macro F1 of 0.572 for triaging risk in 1588 labeled CLPsych 2017 posts without metadata or history.
-
SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification
SleepNet and DreamNet enrich visual features via supervised pre-trained encoders and reconstruct hidden states with encoder-decoder frameworks to outperform prior state-of-the-art classifiers.
-
Large Language Models: A Survey
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
-
Machine Reading Comprehension: a Literature Review
A 2019 survey of machine reading comprehension corpora and methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.