Algorithm transfers visual concepts to answer out-of-vocabulary questions.
problem Leveraging off-the-shelf visual and linguistic data for out-of-vocabulary answers in visual question answering.
method Unsupervised task discovery for learning task conditional visual classifier, then transferring to visual question answering models.
result Algorithm generalizes to out-of-vocabulary answers successfully.
Improves slot key and value prediction for unseen entities.
problem Dealing with unseen slot keys and values in real-world dialogue systems.
method Leverages external knowledge bases to project slots into an attribute space and generate candidate keys and values.
result Significant improvements in F1 score and accuracy (57.7% and 82.7%, respectively) over a previous approach.
With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as only a single embedding is learned for every word in the vocabulary, the model fails to optimally re…
New neural network layer handles OOV words in NLP tasks without pre-training.
problem Handling out-of-vocabulary words in natural language processing.
method Contextual-compositional neural network layer that attends to character sequence and context.
result Improves performance on 23 languages in joint tagging tasks.
Improves E2E ASR performance on numeric sequences with additional training data and denormalization.
problem Challenges in recognizing numeric sequences out-of-vocabulary in ASR systems.
method Uses text-to-speech for additional numeric training data and a small-footprint neural network for denormalization.
result Reduction of WER by up to a factor of 8 in the longest numeric sequences.
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…
Estimator Vectors learns OOV word embeddings using subword and context clues.
problem Lack of OOV word representations in neural network models.
method Jointly learns word, subword, and context clue representations.
result Strong estimates for OOV words via combined subword and context clue embeddings.
The multilingual nature of the world makes translation a crucial requirement today. Parallel dictionaries constructed by humans are a widely-available resource, but they are limited and do not provide enough coverage for good quality translation purposes, due to out-of-vocabulary words and neologisms. This motivates th…
Improved NER in medical text with few examples.
problem Limited annotated examples for NER in medical texts.
method Layer-wise initialization, hyperparameter tuning, pre-training data, custom word embeddings, optimizing OOV words.
result F1 score improved from 69.3% to 78.87%.
Dynamic segmentation algorithm improves NMT performance by favoring character-level processing.
problem Suboptimal static segmentation choices in NMT systems.
method Adaptive Computation Time algorithm for dynamic segmentation, trainable end-to-end.
result The model prefers character-level processing when given the freedom to navigate different segmentation levels.
In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Lis…
User-specific KWS system learns new keywords on-device.
problem Out-of-vocabulary problem in traditional KWS systems.
method Query-by-example enrollment and testing, using phonetic posteriors and FST.
result Promising performance on two keywords, preserving simplicity.
Proposes MorphMine for unsupervised morpheme segmentation to improve word embeddings.
problem Lack of semantic information in word-level analysis for infrequent and out-of-vocabulary words.
method MorphMine applies a parsimony criterion to hierarchically segment words into the fewest number of morphemes.
result MorphMine segments words into human-verified morphemes and improves word embedding quality.
Greek POS Tagger and Entity Recognizer built using spaCy.
problem Developing a machine learning model for Greek language POS tagging and named entity recognition.
method Machine learning approach with spaCy platform, focusing on morphological features and token classification.
result The Greek spaCy platform improved performance in part-of-speech tagging and named entity recognition.
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.
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.
Lipper synthesizes speech from silent videos, improving over single-view methods.
problem Lipreading as text classification is limited; multi-view approach needed.
method Multi-view lipreading as a regression task, producing speech from silent videos.
result Improvement in speech reconstruction with multi-view silent videos.
Hybrid and end-to-end models compare in syllable recognition.
problem Comparing hybrid and end-to-end models for syllable recognition.
method Traditional hybrid system (kaldi) vs. end-to-end (TensorFlow) models.
result Hybrid models with explicit syllable knowledge outperform end-to-end models.
GANs improve VSR accuracy by generating unseen classes.
problem Scarcity of training data for unseen classes in VSR.
method Generative Adversarial Networks (GANs) to generate new class samples.
result Accuracy increased by 27% for unseen classes.
Unified framework for ranking-and-selection with multiple correct answers and non-answerable estimates
problem Fixed-precision ranking-and-selection in structured settings with non-unique answers and non-answerable estimates
method Unified framework based on answer-wise acceptance sets, restricted generalized likelihood ratio stopping, and answer-pitfall decomposition
result Unified recipe performs well across a broad range of pure-exploration problems
MAC Net improves natural language question answering with data-driven reasoning.
problem Natural Language Question Answering requires complex reasoning.
method MAC Net architecture separates memory and control for iterative reasoning.
result MAC Net achieves high efficiency and interpretability in NLP tasks.
New algorithm finds optimal sample complexity for pure exploration with multiple good answers.
problem Determining the optimal number of samples needed to explore multiple good answers in a bandit problem.
method Derive lower bound using game equilibrium, extend Track-and-Stop algorithm to multiple answers.
result New algorithm has asymptotic sample complexity matching the derived lower bound.
A new algorithm identifies one of several nearly optimal arms in linear bandits.
problem Identifying one arm that is close to the best arm in linear bandits.
method Developed a procedure to adapt best-arm identification algorithms for ε-best-answer identification in transductive linear stochastic bandits. result Proposed an asymptotically optimal algorithm for ε-best-answer identification. Answers a question from Eliashberg's paper.
problem A question from Eliashberg's recent paper.
method We give a partial answer.
result Provides a partial solution to a question from Eliashberg.
The paper optimizes LLM accuracy by stopping early based on consistent answers.
problem Improving LLM accuracy in math and reasoning problems.
method Bayesian stopping policy to save on sampling costs, tracking only the L-1 most frequent answer counts.
result The L=3 stopping policy is sufficient for asymptotic optimality and significantly reduces inference costs.
Sampling more can make models more confident in wrong answers, not better.
problem The modal ceiling and correlation ceiling limit the benefit of increased sampling.
method Analyzes the trade-offs between sampling more and selecting the best answer.
result Extra sampling beyond a certain point does not improve model performance and can even degrade it.
Community-based Question Answering (CQA) sites play an important role in addressing health information needs. However, a significant number of posted questions remain unanswered. Automatically answering the posted questions can provide a useful source of information for online health communities. In this study, we deve…
QAInfomax improves reading comprehension by maximizing mutual information, achieving state-of-the-art performance.
problem Distractor sentences in question answering datasets are hard to distinguish from relevant ones.
method QAInfomax regularizes reading comprehension models to learn mutual information among passages, questions, and answers.
result QAInfomax achieves state-of-the-art performance on Adversarial-SQuAD dataset.
Enhanced ontology learning from text improves question-answering systems.
problem Improving ontology learning from unstructured text for better question-answering systems.
method Heuristically modified FP-Tree with DFA for concept extraction and frequent pattern mining for ontology learning.
result Our approach significantly improves question-answering system performance, answering 80% of questions compared to 28.4% with Text2Onto.
James's octonionic Stiefel spaces questions answered partially.
problem Two fundamental questions about octonionic Stiefel spaces.
method Partial answers to James's questions about octonionic Stiefel spaces.
result Partial answers to James's questions about octonionic Stiefel spaces.
Paper recovers top-two answers and confusion probability in multi-choice crowdsourcing.
problem Recovering top-two answers and confusion probability in multi-choice crowdsourcing tasks.
method Proposes a two-stage inference algorithm based on a model quantifying task difficulty and worker reliability.
result Achieves minimax optimal convergence rate and outperforms other algorithms in synthetic and real data experiments.
A new method for private query release using Johnson-Lindenstrauss projection.
problem Private release of query answers with minimal privacy loss.
method Random projection of query answers to a lower dimension, followed by noise addition.
result Optimal worst-case sample complexity for answering a workload of k queries.
Paper analyzes biases in video QA datasets, showing models can answer 37-48% questions correctly without multimodal context.
problem Question answering biases in video QA datasets can lead to model overfitting and poor generalization.
method Analyzed popular video question answering datasets, conducted ablation studies on biases from annotators and question types.
result Pretrained language models can answer 37-48% questions correctly without multimodal context, far exceeding random guess baseline.
LSTM network aids intent classification in QA.
problem Classifying intent in question-answering.
method Used LSTM architecture for intent classification.
result Effective and efficient intent classification achieved.
CLEAR dataset for acoustic reasoning tasks.
problem Acoustic reasoning and question answering.
method Data generation from elementary sounds, functional programs for question composition.
result Validation of current state-of-the-art visual Q&A models on AQA task.
A new query embedding method improves KB performance on complex queries.
problem QE systems disagree with deductive reasoning on some queries.
method A novel QE method more faithful to deductive reasoning.
result Better performance on complex queries to incomplete KBs.
Improved QA system by re-ranking top-10 results using machine learning.
problem Enhance deployed QA systems without re-training.
method Learn similarity function using n-gram features; implement neural sentence embeddings.
result Mean reciprocal rank improves by 9.15%.
We propose a probabilistic model to aggregate the answers of respondents answering multiple-choice questions. The model does not assume that everyone has access to the same information, and so does not assume that the consensus answer is correct. Instead, it infers the most probable world state, even if only a minority…
FinanceBench benchmarks LLMs on financial QA, revealing limitations.
problem Evaluating LLMs' performance on financial question answering.
method Developed a comprehensive test suite (FinanceBench) with 10,231 questions, tested 16 models, and manually reviewed answers.
result Existing LLMs have significant limitations for financial QA, especially GPT-4-Turbo.
Visual question answering is a recently proposed artificial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for mo…
DLGNet improves dialogue response generation by leveraging transformer architecture.
problem Lack of relevance, diversity, and coherence in dialogue responses.
method Transformer-based model for dialogue response generation, incorporating long-range structures and random paddings.
result Significant improvements over state-of-the-art models on multiple datasets.
A novel method for visual question answering using scene graphs and reinforcement learning.
problem Answering free-form questions about images with deep linguistic and visual understanding.
method Context-driven, sequential reasoning based on scene graphs and reinforcement learning.
result Our method almost reaches human performance on the GQA dataset.
Unified framework for simple question answering using subgraph ranking and joint-scoring.
problem Simple question answering with knowledge graphs is challenging.
method Unified framework focusing on subgraph selection and fact selection, with novel ranking and joint-scoring methods.
result Achieved state-of-the-art accuracy of 85.44% on SimpleQuestions dataset.
Most work in machine reading focuses on question answering problems where the answer is directly expressed in the text to read. However, many real-world question answering problems require the reading of text not because it contains the literal answer, but because it contains a recipe to derive an answer together with …
New models explain image-based questions better with fewer examples.
problem Improving understanding and efficiency in visual question answering.
method Probabilistic neural-symbolic models with interpretable latent programs.
result Models generate more understandable programs with fewer examples and allow probing reasoning.
New task AQA tackles acoustic reasoning from sound scenes.
problem Promote research in acoustic reasoning.
method Generate acoustic scenes from elementary sounds and formulate questions.
result Preliminary results with models FiLM and MAC show promise.
We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a qu…
New method learns to answer questions from correct demonstrations without assuming bounded complexity of the demonstrator.
problem Learning to generate answers from correct demonstrations with multiple correct answers.
method Formalizes imitation learning in contextual bandits, relying on reward model complexity, not policy complexity.
result Achieves nearly optimal performance with sample complexity logarithmic in reward class cardinality.