When a bilingual student learns to solve word problems in math, we expect the student to be able to solve these problem in both languages the student is fluent in,even if the math lessons were only taught in one language. However, current representations in machine learning are language dependent. In this work, we pres…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “language representation”
LORL learns object-centric representations from vision and language.
problem Learning disentangled, object-centric scene representations from vision and language.
method LORL integrates unsupervised object discovery and segmentation with language input to learn object-centric concepts.
result LORL improves unsupervised object discovery methods and aids downstream tasks.
Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of downstream tasks. Along with continuous significant performance improvement, the size an…
Data-driven models and computational tools for neurolinguistics: a language technology perspectivecs.LG
Paper reviews neurolinguistics and language technologies, emphasizing mutual enrichment.
problem Understanding brain activity during language processing.
method Brain imaging studies and natural language representations.
result Development of brain-aware natural language representations.
This work explains how linear representations in large language models arise from training objectives and gradient descent.
problem Understanding the origins of linear representations in large language models.
method A latent variable model to abstract and formalize concept dynamics, combined with analysis of the softmax cross-entropy objective and gradient descent.
result Linear representations emerge when learning from data matching the latent variable model, and this simple structure suffices to yield linear representations.
New approach decouples skill learning and language grounding for autonomous agents.
problem Autonomous acquisition of skills without external instructions and feedback.
method Language-Goal-Behavior (LGB) architecture with semantic representation.
result Decouples skill learning and language grounding, enabling diversity and strategy switching.
Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading comprehension tasks with a language representation model pre-trained on multi-lingual corp…
The paper explores linear representations in language models using counterfactuals.
problem Understanding linear representations and geometric concepts in large language models.
method Formalized linear representation in output and input spaces, identified causal inner product.
result Unified understanding of linear representations and their connection to interpretation and control.
Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this work we explore the use of autoencoder-based methods for cross-language learning …
lamBERT learns language and actions using multimodal BERT.
problem Learning language and actions in complex environments.
method Extending BERT to multimodal representation and integrating with reinforcement learning.
result lamBERT model achieved higher rewards in multitask and transfer settings.
SentenceMIM learns rich latent representations for variable-length language data.
problem Challenges in learning VAEs for variable-length language data, especially posterior collapse.
method Probabilistic auto-encoder trained with Mutual Information Machine (MIM) learning.
result SentenceMIM learns informative latent representations with high mutual information.
Extends linear representation hypothesis to categorical and hierarchical concepts in LLMs.
problem Representing concepts without natural contrasts in large language models.
method Formalizes linear representation hypothesis for categorical and hierarchical concepts, proving relationships between concept hierarchy and representation geometry.
result Validated theoretical results on large language models, estimating representations for 900+ concepts.
Geo2DR learns graph representations using substructure patterns.
problem Learning distributed representations of graphs efficiently.
method Unsupervised learning with discrete substructure patterns and neural language models.
result Geo2DR achieves high reproducibility and interoperability in graph classification.
This is a lecture note for the course DS-GA 3001 <Natural Language Understanding with Distributed Representation> at the Center for Data Science , New York University in Fall, 2015. As the name of the course suggests, this lecture note introduces readers to a neural network based approach to natural language understand…
RoBERTa model detects counterfactual statements in text.
problem Detecting and extracting counterfactual statements from text.
method Used RoBERTa language representation model for both subtasks.
result RoBERTa achieved top performance in both subtasks at SemEval-2020.
A framework uses free probability to analyze Transformer models.
problem Understanding the dynamics and complexity of Transformer-based language models.
method Formal operator-theoretic analysis using free probability theory.
result Entropy-based generalization bounds derived under freeness assumptions.
This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer model described in Dehghani et al. (2018). We further improve this model by addin…
ExpBERT uses natural language explanations to improve text interpretation.
problem Improving text interpretation for relation extraction tasks.
method Fine-tuning BERT on MultiNLI to interpret natural language explanations.
result ExpBERT matches a BERT baseline but requires less labeled data and improves performance.
Transformer models perform slower than convolutional networks in learning hierarchical language structures.
problem Understanding how neural networks learn hierarchical language structures.
method Theoretical scaling laws and empirical validation of neural network performance.
result Convolutional networks outperform transformers in learning hierarchical language structures.
A new method uses a frozen language model to improve sample efficiency in reinforcement learning.
problem Improving sample efficiency in reinforcement learning with partially observable environments.
method FROZEN Hopfield network and HELM (History Embedding Language Model) method.
result HELM achieves new state-of-the-art results on Minigrid and Procgen environments.
Recent work on learning multilingual word representations usually relies on the use of word-level alignements (e.g. infered with the help of GIZA++) between translated sentences, in order to align the word embeddings in different languages. In this workshop paper, we investigate an autoencoder model for learning multil…
Study investigates predictive coding models for phonemic learning.
problem Understanding how predictive coding models generalize to different languages and dataset sizes.
method Investigated Autoregressive Predictive Coding and Contrastive Predictive Coding models in phoneme discrimination tasks for two languages with varying dataset sizes.
result Contrastive Predictive Coding model converges rapidly and outperforms Autoregressive Predictive Coding on both languages.
The paper proves impossibilities and positive results for universal machine translation.
problem Learning shared sentence representations across multiple language pairs.
method Formal proofs and analysis of natural generative processes.
result Lower bound on translation error and positive results under natural structure.
Language models are at the heart of numerous works, notably in the text mining and information retrieval communities. These statistical models aim at extracting word distributions, from simple unigram models to recurrent approaches with latent variables that capture subtle dependencies in texts. However, those models a…
NLP techniques improve drug discovery by analyzing chemical and protein text.
problem Improving drug discovery through better analysis of chemical and protein text.
method Natural language processing techniques applied to biochemical entities.
result Enhanced prediction of molecular properties and design of novel molecules.
New measure shows how LSTM models compose hierarchical representations.
problem Understanding how LSTM models capture compositional structure in language.
method Novel measure of interdependence between word meanings in LSTM internal gates.
result High interdependence can hurt generalization and reveals hierarchical structure learning.
Language models improve clinical prediction models using EHR data.
problem Limited patient data for training clinical prediction models.
method Using patient representation schemes from natural language processing.
result 3.5% mean improvement in AUROC on five prediction tasks.
Linking human whole-body motion and natural language is of great interest for the generation of semantic representations of observed human behaviors as well as for the generation of robot behaviors based on natural language input. While there has been a large body of research in this area, most approaches that exist to…
A method for disentangling text representations without supervision.
problem Challenges in learning disentangled representations of natural language.
method Information-theoretic guidance to induce independent style and content embeddings.
result High quality disentangled representations in terms of content and style preservation.
Graph neural networks help AI agents learn more complex language.
problem Understanding how AI agents learn and use language.
method Developed graph referential games to compare different AI models.
result Graph neural networks enable AI to learn more complex, compositional language.
Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we introduce Tile2Vec, an unsupervised representation learning algorithm that extends the distribution…
Global watermark for diffusion language models decouples detection from local contexts.
problem Watermarking in diffusion language models is challenging due to joint sampling of distributions over many unresolved positions.
method Proposes a global vector-valued sketch representation to control watermarking in masked diffusion language models.
result The method decouples detection from local contexts, resulting in an order-agnostic statistic and robustness.
This paper fine-tunes LLMs for stock return prediction using financial news.
problem Improving stock return forecasting accuracy using LLMs.
method Fine-tuning LLMs with text and forecasting modules, comparing encoder-only and decoder-only models, and integrating token-level representations.
result LLMs' aggregated token-level embeddings enhance return predictions for long-only and long-short portfolios.
TextNAS finds optimal text representation networks using neural architecture search.
problem Finding the optimal text representation networks is challenging.
method Proposes a novel search space for text representation and uses automatic neural architecture search.
result Automatic search discovers network architectures that outperform state-of-the-art models on text classification and natural language inference tasks.
CERT improves language understanding by contrastively learning sentence-level semantics.
problem Lack of sentence-level semantics in existing pretraining tasks.
method Contrastive self-supervised learning at the sentence level using back-translation augmentations.
result CERT outperforms BERT on 7 out of 11 GLUE benchmark tasks, achieving the same performance as BERT on 2 tasks.
New approach extracts AI model representations for steering and monitoring.
problem Understanding and steering AI models' internal knowledge representation.
method Feature learning advances for scalable linear concept representations.
result Concept representations enable steering and monitoring of AI models.
Language models exhibit low-rank structure, which can be used for generation.
problem Understanding the low-dimensional structure of large language models.
method Empirical demonstration and theoretical analysis of the approximate rank of language models' logits.
result Language models can generate responses using linear combinations of unrelated prompts.
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and un…
Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the in…
Deep models learn to parse complex language structures from local data patterns.
problem Understanding how deep models parse and represent language structures.
method Introduced tunable probabilistic context-free grammars and a learning algorithm inspired by deep networks.
result Data correlations across scales enable hierarchical language representations.
Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understandingcs.CL
Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Lang…
The study examines how language models learn to represent the world, identifying conditions for ecological veridicality.
problem Understanding when language models learn to represent the world accurately and how this learning process can fail.
method Analyzes the Bayes-optimal next-token cross-entropy decomposition and the role of training ecology in shaping model representations.
result The minimum-complexity zero-excess solution is the quotient partition by training equivalence, and this solution is not preserved in in-context learning or per-task adaptation.
APo-VAE generates text in hyperbolic space for better hierarchical representation.
problem Lack of hierarchical structure in Euclidean embeddings for natural language.
method Adversarial Poincare Variational Autoencoder (APo-VAE) in hyperbolic latent space.
result APo-VAE outperforms Euclidean VAEs in capturing latent language hierarchies.
Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters throug…
As modern deep networks become more complex, and get closer to human-like capabilities in certain domains, the question arises of how the representations and decision rules they learn compare to the ones in humans. In this work, we study representations of sentences in one such artificial system for natural language pr…
A new model tackles language generation issues by using discrete variational attention.
problem Information under-representation and posterior collapse in variational autoencoders.
method Proposes a discrete variational attention model with categorical distribution over attention mechanism.
result Enhances latent space for language generation and avoids posterior collapse.
Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learningcs.LG
The study uncovers latent capabilities of language models via causal representation learning.
problem Rigorous causal evaluations of language model capabilities are challenging due to confounding effects and computational costs.
method Proposes a causal representation learning framework to identify latent capability factors as causally interrelated after controlling for a common confounder (base model).
result Identifies a three-node linear causal structure explaining performance variations across 1500 models and six benchmarks.
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Trainingcs.LG
New method reduces bias in NLI models using ensemble adversarial training.
problem Spurious correlations between hypotheses and entailment classes in NLI datasets.
method Adversarial training with an ensemble of classifiers to reduce bias in sentence representations.
result Ensemble adversarial training produces more robust NLI models, outperforming previous methods.