Linguistic calibration improves long-form text confidence.
problem LMs hallucinate, leading to suboptimal decisions.
method Defining linguistic calibration, training framework, reinforcement learning.
result Llama 2 7B is significantly more calibrated than baselines.
Preserves content while changing style in text.
problem Text style transfer often fails to preserve content.
method Leverages linguistic information in structured supervisions.
result Significant improvement in content preservation and style transfer.
The Yarowsky algorithm is a rule-based semi-supervised learning algorithm that has been successfully applied to some problems in computational linguistics. The algorithm was not mathematically well understood until (Abney 2004) which analyzed some specific variants of the algorithm, and also proposed some new algorithm…
Computational model uncovers linguistic universals.
problem Manual processing of linguistic typology by linguists is time-consuming and leaves key universals unexplored.
method Presented a computational model to identify known and new linguistic universals.
result The model successfully identifies known universals and uncovers new ones.
ATD measures language distance using neural models, recovering linguistic groupings.
problem Lack of a unified quantitative measure for cross-linguistic distance.
method Pretrained multilingual language models, attention mechanisms, optimal transport.
result ATD quantifies representational distance between languages, recovering linguistic groupings.
TX-Ray analyzes and quantifies model knowledge transfer in NLP.
problem Insufficient methods for explaining and quantifying model knowledge transfer in NLP.
method Modified computer vision explainability principle to NLP, visualizing feature preference distributions.
result TX-Ray reveals how self-supervised models learn linguistic abstractions and improves generalization.
We investigated the impact of noisy linguistic features on the performance of a Japanese speech synthesis system based on neural network that uses WaveNet vocoder. We compared an ideal system that uses manually corrected linguistic features including phoneme and prosodic information in training and test sets against a …
A new method extracts linguistic objects from text using CNNs.
problem Lack of interpretability in deep learning models for text.
method Weighted extension of Text Deconvolution Saliency (wTDS) measure.
result Extracts interpretable linguistic objects from text.
GTI network learns linguistic features for multi-task sequence tagging.
problem Improving neural model performance on multi-task sequence tagging without explicit features.
method GTI network with neural gate modules to learn relations between tasks.
result GTI network outperforms baselines on chunking and NER tasks.
Proposes a method to interpret linguistic data models using parse trees and least-squares scores.
problem Interpreting trained classification models in linguistic data sets.
method Assigns least-squares based importance scores to words in a sentence using syntactic constituency structure and relates them to the Banzhaf value in coalitional game theory.
result Demonstrates the effectiveness of the proposed method in aiding interpretability and diagnostics for language models.
The paper analyzes how CNNs interpret NLP tasks and identify linguistic features.
problem Understanding how CNNs capture linguistic features in NLP tasks.
method Visualization techniques and error analysis to interpret CNNs.
result Identified how CNNs capture different linguistic features and their impact on model performance.
Benchmark tests spoken language models for infant language learning.
problem Understanding how infants learn language from speech.
method Developed a language-acquisition-friendly benchmark.
result Benchmarking shows models' strengths and weaknesses.
The starting point of this article is the question "How to retrieve fingerprints of rhythm in written texts?" We address this problem in the case of Brazilian and European Portuguese. These two dialects of Modern Portuguese share the same lexicon and most of the sentences they produce are superficially identical. Yet t…
Study investigates how simple speech sounds can form abstract categories.
problem How do abstract categories like phonemes emerge from speech exposure?
method Used modeling techniques to test Memory-Based Learning and Error-Correction Learning.
result Error-Correction Learning models can learn abstractions, identifying phone inventory and grouping.
We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision. Specifically, we exploit the multi-scale nature of information in sequential data by formulating it explicitly within a factorized hierarchical graphical mo…
The abstract discusses parallels between Galois theory and Stone-Weierstrass theorem in various fields.
problem Connecting distinguishing power and expressive power in different fields.
method Elementary theorem connecting distinguishing power and expressive power.
result Foundational principle in linguistics linking distinguishing power and expressive power.
BERT captures linguistic features in separate semantic and syntactic subspaces.
problem Understanding how transformer models like BERT represent linguistic features internally.
method Qualitative and quantitative investigations of BERT's internal representations.
result Evidence of a fine-grained geometric representation of word senses and syntactic representations.
Our usage of language is not solely reliant on cognition but is arguably determined by myriad external factors leading to a global variability of linguistic patterns. This issue, which lies at the core of sociolinguistics and is backed by many small-scale studies on face-to-face communication, is addressed here by cons…
EGFC learns from streaming data to classify power quality disturbances.
problem Real-time detection and classification of power quality disturbances.
method Evolving Gaussian Fuzzy Classification (EGFC) framework with semi-supervised learning.
result Encouraging classification results from online data streams.
Study evaluates natural language models' ability to generalize across tasks.
problem Natural language models struggle with generalizing to new tasks.
method Empirical evaluation of state-of-the-art models using new metrics.
result Models require extensive in-domain training and are prone to forgetting.
ContextBench benchmarks methods for generating linguistically fluent inputs that activate specific latent features in language models.
problem Identifying inputs that trigger specific behaviours or latent features in language models.
method Context modification and benchmarking methods like Evolutionary Prompt Optimisation (EPO) with LLM-assistance and diffusion model inpainting.
result Enhanced methods achieve state-of-the-art performance in balancing elicitation effectiveness and fluency.
Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformation. In this work we propose a method for automatically establishing the credibility of user-generated medical statements and the trustworth…
Unified QuesNet learns comprehensive representations for diverse test questions.
problem Lack of labeled data for test questions in online learning systems.
method Unified framework and two-level hierarchical pre-training algorithm for unsupervised learning of heterogeneous question representations.
result QuesNet effectively learns comprehensive question representations and outperforms existing methods.
Recent research in psycholinguistics has provided increasing evidence that humans predict upcoming content. Prediction also affects perception and might be a key to robustness in human language processing. In this paper, we investigate the factors that affect human prediction by building a computational model that can …
One of the most prevalent symptoms among the elderly population, dementia, can be detected by classifiers trained on linguistic features extracted from narrative transcripts. However, these linguistic features are impacted in a similar but different fashion by the normal aging process. Aging is therefore a confounding …
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
Investigates neural TTS systems for Japanese and English.
problem Improving neural TTS systems for high-quality speech synthesis.
method Comparative study of neural sequence-to-sequence TTS vs. DNN pipeline TTS, varying model architecture, parameter size, and language.
result A neural sequence-to-sequence TTS system requires sufficient model parameters and a powerful encoder for high-quality speech synthesis.
Enhances speech quality in noisy environments using symbolic sequential modeling.
problem Improving speech quality in noisy conditions.
method Incorporates symbolic sequential modeling into speech enhancement framework.
result Significant improvement in speech quality metrics (PESQ, STOI) on TIMIT dataset.
Expanding spoken language understanding to handle complex entities and intents.
problem Handling compound entities and intents in spoken language understanding.
method Introducing a domain-agnostic shallow parser that handles linguistic coordination, learning domain-independent and slot-independent features.
result The model learns to segment conjunct boundaries of various phrasal categories and improves generalization across different slot types using adversarial training.
Qwant Research improves clinical case matching and information retrieval.
problem Matching and retrieving relevant clinical cases and discussions.
method Approach based on language models and preprocessings, information extraction system using neural networks and linguistic analysis.
result Very encouraging results in information extraction accuracy.
This paper studies users' perception regarding a controversial product, namely self-driving (autonomous) cars. To find people's opinion regarding this new technology, we used an annotated Twitter dataset, and extracted the topics in positive and negative tweets using an unsupervised, probabilistic model known as topic …
Paper proposes MMD-Sense-Analysis for detecting word sense shifts.
problem Detecting and interpreting shifts in word meanings over time.
method Leverages Maximum Mean Discrepancy (MMD) to identify and explain word sense changes.
result Demonstrates effectiveness of MMD-Sense-Analysis through empirical results.
We introduce Markov substitute processes, a new model at the crossroad of statistics and formal grammars, and prove its main property : Markov substitute processes with a given support form an exponential family.
Interpersonal relations are fickle, with close friendships often dissolving into enmity. In this work, we explore linguistic cues that presage such transitions by studying dyadic interactions in an online strategy game where players form alliances and break those alliances through betrayal. We characterize friendships …
Analysts use vague language in reports to convey useful information about future payoffs.
problem Lack of precise numerical forecasts in analyst reports.
method Empirical analysis of analyst reports to assess the predictive power of linguistic tone.
result The textual tone of analyst reports has predictive power for forecast errors and subsequent revisions, especially when language is vague and uncertainty is high.
Study shows mutual information can reward structure learning agents without expert systems.
problem Designing rewards for structure learning agents in natural language environments.
method Revisited Information Theory of unsupervised induction of phrase-structure grammars, using random sets of linguistic samples.
result Empirical evidence that simulated semantic structures can be distinguished from random ones by mutual information among their constituents.
Study uses social media to analyze COVID-19 impact.
problem Understanding the global impact of COVID-19.
method Machine learning and linguistic tools to analyze social media posts.
result Automatic detection of positive reports of COVID-19.
We present the Bayesian Echo Chamber, a new Bayesian generative model for social interaction data. By modeling the evolution of people's language usage over time, this model discovers latent influence relationships between them. Unlike previous work on inferring influence, which has primarily focused on simple temporal…
OT domain adaptation improves aphasia detection across languages.
problem Detecting aphasia in low-resource languages with limited data.
method Utilized OT domain adaptation to map linguistic features across multiple languages.
result OT domain adaptation significantly improved F1 scores for French and Mandarin aphasia detection.
EigenNoise provides a competitive word vector initialization scheme without pre-training data.
problem Improving word vector initialization without pre-training data.
method EigenNoise uses a dense, independent co-occurrence model to initialize word vectors.
result EigenNoise can approach GloVe performance without pre-training data.
New RL framework learns task completion without prior knowledge.
problem Learning task completion without linguistic or perceptual knowledge.
method Sequentially imagining visual goals and choosing actions.
result Framework outperforms flat and hierarchical architectures.
Develops a machine learning framework for identifying authorship in texts.
problem Identifying the author of texts, especially when authors are unknown or multiple.
method Formulates authorship identification as a text categorization problem, uses supervised machine learning with stylometric features.
result A model accurately predicts authorship with high accuracy, especially with linguistic stylometric features.
Paper predicts Indian stocks using news psycholinguistic features.
problem Predicting Indian stock market performance using financial news.
method Hybrid intelligent models using psycholinguistic variables (LIWC and TAALES) from news articles.
result GMDH and GRNN are statistically the best techniques for prediction.
New distress dictionary improves bankruptcy prediction from disclosure text.
problem Bankruptcy prediction from financial disclosures.
method Proposes a distress dictionary based on managers' sentences, quantifies linguistic features, and builds predictive models.
result Predictive models based on the distress dictionary outperform existing methods.
This paper analyzes text in financial disclosures to improve financial analysis.
problem Insufficient analysis of unstructured text in financial disclosures.
method Reviews and explores methods in computational linguistics and NLP.
result Highlights limitations of sentiment metrics and suggests future research areas.
This paper proposes a new method to connect language and physical actions in reinforcement learning.
problem Connecting linguistic representations to the physical world in embodied agents.
method Language-conditioned goal generators to decouple sensorimotor learning from language acquisition.
result Agents can demonstrate a diversity of behaviors for any given instruction.
In this paper, we propose a new kernel-based co-occurrence measure that can be applied to sparse linguistic expressions (e.g., sentences) with a very short learning time, as an alternative to pointwise mutual information (PMI). As well as deriving PMI from mutual information, we derive this new measure from the Hilbert…
Paper addresses shortcomings in pointer generator networks for summarization.
problem Extractive summaries and factual inaccuracies in generated text.
method Appends traditional linguistic information to teach networks on text structure.
result Feasibility and potential of additional cues for improved generation.