We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is …
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.
168,982 papers · 148 categories
Trend · papers per month
48 results for “language pairs”
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.
Paper develops a new unsupervised scoring function for cross-lingual document alignment.
problem Aligning documents across different languages for NLP tasks.
method Uses cross-lingual sentence embeddings to compute semantic distances and guides document alignment.
result The proposed scoring function outperforms current methods by 7-22% on various language pairs.
This paper tackles rare word problem in low-resource language pairs using NMT.
problem Rare word problem in neural machine translation, especially for low-resource languages.
method Three solutions: enhanced source context, morphology learning, and wordnet synonyms.
result Significant improvements in BLEU scores (+1.0 points) on English-Vietnamese and Japanese-Vietnamese.
CCAligned creates a massive web document dataset for cross-lingual research.
problem Identifying comparable documents across different languages.
method Using URL signals to label web documents and mining Common Crawl corpus.
result Release of a dataset with over 392 million URL pairs from 8144 language pairs.
This study analyzes how one-layer transformers learn regular language recognition tasks.
problem Understanding how one-layer transformers solve regular language recognition tasks like even pairs and parity check.
method Theoretical analysis of training dynamics and gradient descent for a one-layer transformer.
result A one-layer transformer can solve even pairs directly but needs CoT for parity check. Training phases show rapid growth in attention layer followed by logarithmic growth in linear layer.
Project aims to improve coherence in language generation models.
problem Models often generate inconsistent text that diverges from the prompt.
method Trained a sentence pair coherence classifier and co-trained GPT-2 with this coherence objective.
result Fine-tuned model generates coherent paragraphs without diverging.
Geometric approach for unsupervised word embedding alignment.
problem Learning alignment between word embeddings of source and target languages.
method Formulates alignment as domain adaptation on the manifold of doubly stochastic matrices, employing Riemannian conjugate gradient algorithm.
result Empirically outperforms state-of-the-art methods on bilingual lexicon induction tasks.
Paper presents token-level explanations for NLI without annotated data.
problem Generating explanations for NLI models on sentence pairs.
method Simple LSTM architecture with LIME, Anchor, and MIL methods.
result MIL-based method faster but less accurate than black-box methods.
Model learns image-word associations from captions using contrastive learning.
problem Phrase grounding, associating image regions to caption words.
method Optimizing word-region attention to maximize mutual information, using language model guided word substitutions for negatives.
result Model achieves 76.7% accuracy on Flickr30K Entities benchmark, a 5.7% gain from weak supervision.
Introduces challenges and techniques for creating machine translation for indigenous languages.
problem Limited data for machine translation of indigenous languages.
method Introduction to challenges, concepts, and techniques for creating MT systems.
result Discussion of recent advances and open questions in NLP for these languages.
Code-switching, the alternation of languages within a conversation or utterance, is a common communicative phenomenon that occurs in multilingual communities across the world. This survey reviews computational approaches for code-switched Speech and Natural Language Processing. We motivate why processing code-switched …
In this paper, we attempt to improve Statistical Machine Translation (SMT) systems on a very diverse set of language pairs (in both directions): Czech - English, Vietnamese - English, French - English and German - English. To accomplish this, we performed translation model training, created adaptations of training sett…
We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent variable as a language agnostic representation which is encouraged to learn the meaning…
Proposes using Wasserstein barycenter for better multilingual alignment.
problem Finding word-to-word translations between multiple languages without parallel data.
method Uses Wasserstein barycenter as a more informative pivot language, minimizing pairwise transportation costs.
result Demonstrates state-of-the-art performances on standard benchmarks.
Improved unsupervised word translation using adversarial autoencoder with cycle consistency and input reconstruction.
problem Challenging language pairs and lack of parallel data for unsupervised word translation.
method Adversarial autoencoder with cycle consistency and input reconstruction regularization.
result More stable and better performance than recent approaches.
We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples learning the transformation from the source language to the target language into (a) learning rotations for language-specific embeddings to align them to a common space, …
Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…
DSE learns sentence embeddings from cross-attention models to speed up sentence-pair similarity computation.
problem Computing sentence-pair similarity is computationally expensive when candidate sentences are large.
method Distilled Sentence Embedding (DSE) based on knowledge distillation from cross-attentive models.
result DSE significantly outperforms ELMO variants and other sentence embedding methods, accelerating computation by several orders of magnitude.
JEPA fails to improve language model performance when fine-tuning.
problem Improving language model performance through latent representation learning.
method Testing various training-time auxiliaries on natural-language-to-regex generation.
result No auxiliary improves cross-entropy gradient cosine with decoder visibility.
Paper investigates multimodal contrastive learning and incorporates unpaired data.
problem Improving feature learning ability of multimodal models under noisy data.
method Initiates investigation of nonlinear loss functions for multimodal contrastive learning, analyzes performance, proposes new loss incorporating unpaired data.
result MMCL can outperform unimodal contrastive learning and robustly handle noisy data.
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.
We develop the multilingual topic model for unaligned text (MuTo), a probabilistic model of text that is designed to analyze corpora composed of documents in two languages. From these documents, MuTo uses stochastic EM to simultaneously discover both a matching between the languages and multilingual latent topics. We d…
Effective multilingual search with instance-based transfer learning.
problem Search in multilingual setting, especially next-sentence prediction and inverse cloze.
method Instance-based transfer learning, analyzing vocabulary overlaps and transitive overlaps.
result Positive transfer on all 35 target languages and two tasks, even with no vocabulary overlap.
Express improves causal attention guarantees for language models.
problem Improving causal attention guarantees for language models.
method Introducing Express, a tool for converting non-causal attention into causal with matching guarantees.
result Express improves causal attention guarantees to log^(3/2)(n)/s with minimal memory and compression overhead.
We introduce Courant algebroids, providing definitions, some historical notes, and some elementary properties. Next, we summarize basic properties of graded manifolds. Then, drawing on the work of Roytenberg and others, we introduce the graded or supergraded language demonstrating a cochain complex / cohomology for (ge…
Robots learn actions and language through curiosity-driven self-exploration.
problem Efficient development of actions and language in infants and robots.
method Curiosity-driven self-exploration using Q-learning to amortize active inference.
result Curiosity-driven exploration enables faster learning and compositional generalization.
MoDeGPT compresses large language models without accuracy loss, saving 98% compute costs.
problem Compression of large language models for resource-constrained devices.
method Structured compression framework using modular decomposition and matrix pair reduction.
result MoDeGPT achieves 90-95% zero-shot performance with 25-30% compression rates.
The "Law" of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired Modalitiescs.LG
The paper proves probabilistic alignment between unseen modalities using contrastive learning.
problem Aligning unseen modalities in unsupervised learning.
method Bayesian approach and direct comparison of contrastive representations.
result Direct comparison of contrastive representations recovers the same likelihood ratio as probabilistic graphical models.
We describe how to formulate Khovanov's functor-valued invariant of tangles in the language of bordered Heegaard Floer homology. We then give an alternate construction of Lawrence Roberts' Type D and Type A structures in Khovanov homology, and his algebra , in terms of Khovanov's theory of modules over …
Automates API mapping across languages with minimal manual effort.
problem Manual effort required to identify parallel program corpora and API mappings.
method Combines domain adaptation and code embedding with GANs to align vector spaces of APIs.
result Automatically identifies cross-language API mappings with less prior knowledge.
DeepSubQE estimates translation quality for subtitles, improving on existing methods.
problem Hard quality estimation for subtitle translations due to language variations.
method Proposes DeepSubQE, a hybrid network combining semantic and syntactic features.
result DeepSubQE outperforms existing methods by significant margin.
FINCH dataset enables financial Text-to-SQL tasks, improving model evaluation.
problem Lack of a large-scale financial dataset for Text-to-SQL tasks.
method Curated financial dataset (FINCH), benchmarking reasoning and language models.
result Proposed FINCH Score for more accurate financial model evaluation.
TextHide secures language understanding tasks by adding minimal encryption.
problem Mitigating privacy risks in natural language understanding tasks.
method TextHide adds a simple encryption step to prevent data recovery.
result TextHide reduces accuracy loss by only 1.9% on GLUE benchmark.
Learning a natural language interface for database tables is a challenging task that involves deep language understanding and multi-step reasoning. The task is often approached by mapping natural language queries to logical forms or programs that provide the desired response when executed on the database. To our knowle…
Paper proposes a method to learn word translations bidirectionally.
problem Word translation between languages.
method Jointly learns translations in both directions with minimal supervision.
result Improves accuracy of translations over previous methods.
RecoBERT uses a language model to recommend items from catalogs.
problem Harnessing language models for text-based item recommendations.
method RecoBERT is a BERT-based approach that learns specialized language models for item recommendations without requiring labeled data.
result RecoBERT outperforms other techniques in inferring item similarities from textual catalogs.
Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queriescs.CV
Associating image regions with text queries has been recently explored as a new way to bridge visual and linguistic representations. A few pioneering approaches have been proposed based on recurrent neural language models trained generatively (e.g., generating captions), but achieving somewhat limited localization accu…
Enhances reward specification in RL with a novel language-based approach.
problem Reward specification in RL can lead to unintended, potentially harmful behaviours.
method Developed a novel class of language-based Reward Machines using RML's built-in memory.
result Can specify non-regular, non-Markovian reward functions for complex tasks.
MGLM models all possible language channel factorizations for improved multilingual generation.
problem Generating multilingual text with flexibility and quality.
method Generative joint distribution model over language channels, marginalizing all possible factorizations.
result MGLM outperforms traditional models in multilingual generation tasks.
MLMs score better than autoregressive models without finetuning.
problem Improving language model scores without fine-tuning.
method Compute pseudo-log-likelihood scores (PLLs) by masking tokens one by one.
result PLLs outperform GPT-2 scores in various NLP tasks.
Theory predicts neural scaling exponents from language statistics.
problem No existing theory could quantitatively predict neural scaling exponents.
method Isolated two key statistical properties of language.
result Derives a simple formula predicting neural scaling exponents.
We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair encoding (BPE) compression algorithm is used to learn the dictionary of tokens that …
SSMBA generates synthetic data to improve robustness in natural language tasks.
problem Improving out-of-domain generalization of models trained on natural language data.
method SSMBA uses corruption and reconstruction functions to generate synthetic data points on the manifold assumption.
result SSMBA consistently outperforms existing methods on robustness benchmarks across multiple tasks and datasets.
Linear attention model outperforms full attention in language tasks.
problem Quadratic scaling of full attention limits model size.
method Introduced a linear attention mechanism.
result Linear attention models achieve comparable performance to full attention models.
New method improves RL/IL agents' adaptability to unseen environments.
problem Current RL/IL techniques struggle with generalizing to unseen environments.
method Zero-shot compositional policy learning with multi-modal fusion and attention mechanism.
result Language grounding enhances generalization across varied environments.
L-Cool improves image and language translation by cooling low-density samples.
problem Improving translation performance on fringe samples in unsupervised domain translation.
method Performing Langevin dynamics to move low-density samples towards high-density areas.
result L-Cool enhances state-of-the-art methods in image and language translation tasks.
This research investigates the Statistical Machine Translation approaches to translate speech in real time automatically. Such systems can be used in a pipeline with speech recognition and synthesis software in order to produce a real-time voice communication system between foreigners. We obtained three main data sets …