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.
Paper tackles Arabic question similarity, outperforming state-of-the-art.
Recognizing a piece of writing as a poem or prose is usually easy for the majority of people; however, only specialists can determine which meter a poem belongs to. In this paper, we build Recurrent Neural Network (RNN) models that can classify poems according to their meters from plain text. The input text is encoded …
Question semantic similarity (Q2Q) is a challenging task that is very useful in many NLP applications, such as detecting duplicate questions and question answering systems. In this paper, we present the results and findings of the shared task (Semantic Question Similarity in Arabic). The task was organized as part of t…
Despite the importance of handwritten numeral classification, a robust and effective method for a widely used language like Arabic is still due. This study focuses to overcome two major limitations of existing works: data diversity and effective learning method. Hence, the existing Arabic numeral datasets have been mer…
Author profiling is the characterization of an author through some key attributes such as gender, age, and language. In this paper, a RNN model with Attention (RNNwA) is proposed to predict the gender of a twitter user using their tweets. Both word level and tweet level attentions are utilized to learn 'where to look'.…
Sentiment analysis is a highly subjective and challenging task. Its complexity further increases when applied to the Arabic language, mainly because of the large variety of dialects that are unstandardized and widely used in the Web, especially in social media. While many datasets have been released to train sentiment …
Unified BERT model improves NER across multiple languages.
Since the events of the Arab Spring, there has been increased interest in using social media to anticipate social unrest. While efforts have been made toward automated unrest prediction, we focus on filtering the vast volume of tweets to identify tweets relevant to unrest, which can be provided to downstream users for …
We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employs a convolutional neural network (CNN) and a highway network over characters, whose output is given to a long short-term memory (LSTM) recurrent neural network language mo…
Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little exploration in this direction. Both the scarcity of annotated data and the compl…
Sentiment analysis (SA) is a task related to understanding people's feelings in written text; the starting point would be to identify the polarity level (positive, neutral or negative) of a given text, moving on to identify emotions or whether a text is humorous or not. This task has been the subject of several researc…
A hybrid K-NN and SVM technique improves classification accuracy.
The international community was caught by surprise on 5 June 2017 when Saudi Arabia, the United Arab Emirates (UAE), Bahrain and Egypt severed diplomatic ties with Qatar, accusing it of destabilizing the region. More than one year after this diplomatic rift, several questions remain unaddressed. This study focuses on t…
Dynamic time warping (DTW) can be used to compute the similarity between two sequences of generally differing length. We propose a modification to DTW that performs individual and independent pairwise alignment of feature trajectories. The modified technique, termed feature trajectory dynamic time warping (FTDTW), is a…
The current paper is a study in Recurrent Neural Networks (RNN), motivated by the lack of examples simple enough so that they can be thoroughly understood theoretically, but complex enough to be realistic. We constructed an example of structured data, motivated by problems from image-to-text conversion (OCR), which req…
I present a unified discussion of several recently published results concerning the escalation, timing and severity of violent events in human conflicts and global terrorism, and set them in the wider context of real-world and cyber-based collective violence and illicit activity. I point out how the borders distinguish…
In this paper, we propose and develop the novel idea of treating musical sheets as literary documents in the traditional text analytics parlance, to fully benefit from the vast amount of research already existing in statistical text mining and topic modelling. We specifically introduce the idea of representing any give…
This paper explores historical and philosophical aspects of angles and solid angles, inspired by Euler's work.
New ASR system handles multiple languages without needing language-specific encoding.
Study quantifies gender bias in language models across 7 languages.
Paper reviews neurolinguistics and language technologies, emphasizing mutual enrichment.
New technique reduces language biases in large language models.
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…
Paper introduces TrufLL for language model training without labeled data.
System identifies language of transliterated text.
Macroeconomic theories of growth and wealth distribution have an outsized influence on national and international social and economic policies. Yet, due to a relative lack of reliable, system wide data, many such theories remain, at best, unvalidated and, at worst, misleading. In this paper, we introduce a novel econom…
LLMs translate natural language trading intents into correct option strategies using a domain-specific language.
New findings show language models can't simultaneously avoid hallucinations and capture all language richness.
This paper proposes a new method to connect language and physical actions in reinforcement learning.
Julia accelerates machine learning in various fields with balance of efficiency and simplicity.
Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and languages. In this study, we propose a multilingual neural language model archite…
Proposes using Wasserstein barycenter for better multilingual alignment.
The paper applies math and physics to language models, introducing entropy and geometric concepts.
Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and serving by eliminating language-specific acoustic, pronunciation, and language models…
Benchmark tests spoken language models for infant language learning.
Introduces challenges and techniques for creating machine translation for indigenous languages.
Optimus pre-trains sentences in a latent space for various NLP tasks.
Work shows hallucination detection by LLMs is impossible without expert feedback.
Real-time spell checker adapts to new languages.
RPP prunes large language models without sacrificing accuracy.
Improved LID for multilingual speakers using context-aware models.
Language models learn from training data and can leak private information.
Large language models predict human sensory judgments across multiple modalities.
New model shows natural language exhibits phase transition similar to physics.
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…
We present a TTS neural network that is able to produce speech in multiple languages. The proposed network is able to transfer a voice, which was presented as a sample in a source language, into one of several target languages. Training is done without using matching or parallel data, i.e., without samples of the same …
New approach decouples skill learning and language grounding for autonomous agents.
lamBERT learns language and actions using multimodal BERT.