Search Results for author:
Found 29 papers, 9 papers with code
Data Collection vs. Knowledge Graph Completion: What is Needed to Improve Coverage?
Given such estimates, WordNet’s coverage is remarkable.
Training on Lexical Resources
We propose using lexical resources (thesaurus, VAD) to fine-tune pretrained deep nets such as BERT and ERNIE.
A Gentle Introduction to Deep Nets and Opportunities for the Future
The first half of this tutorial will make deep nets more accessible to a broader audience, following “Deep Nets for Poets” and “A Gentle Introduction to Fine-Tuning.” We will also introduce GFT (general fine tuning), a little language for fine tuning deep nets with short (one line) programs that are as easy to code as regression in statistics packages such as R using glm (general linear models).
Improving Bilingual Lexicon Induction for Low Frequency Words
This paper designs a Monolingual Lexicon Induction task and observes that two factors accompany the degraded accuracy of bilingual lexicon induction for rare words.
Benchmarking: Past, Present and Future
There used to be more top-down leadership from government (and industry, in the case of systems, with benchmarks such as SPEC).
Data Augmentation for the Post-Stroke Speech Transcription (PSST) Challenge: Sometimes Less Is More
The result represents a relative error reduction of 14% over the baseline model trained without data augmentation.
Since the Scientific Literature Is Multilingual, Our Models Should Be Too
English has long been assumed the $\textit{lingua franca}$ of scientific research, and this notion is reflected in the natural language processing (NLP) research involving scientific document representation.
Data-Driven Adaptive Simultaneous Machine Translation
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency.
Efficiently Disentangle Causal Representations
This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions.
W-CTC: a Connectionist Temporal Classification Loss with Wild Cards
Standard CTC computes a loss by aggregating over all possible alignment paths, that map the entire sequence to the entire label (full alignment).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
The Role of Phonetic Units in Speech Emotion Recognition
Models of phonemes, broad phonetic classes, and syllables all significantly outperform the utterance model, demonstrating that phonetic units are helpful and should be incorporated in speech emotion recognition.
Decoupling recognition and transcription in Mandarin ASR
Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Automatic recognition of suprasegmentals in speech
This study reports our efforts to improve automatic recognition of suprasegmentals by fine-tuning wav2vec 2. 0 with CTC, a method that has been successful in automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
On Attention Redundancy: A Comprehensive Study
(What) We define and focus the study on redundancy matrices generated from pre-trained and fine-tuned BERT-base model for GLUE datasets.
Better than BERT but Worse than Baseline
This paper compares BERT-SQuAD and Ab3P on the Abbreviation Definition Identification (ADI) task.
Isotropy in the Contextual Embedding Space: Clusters and Manifolds
We hope the study in this paper could provide insights towards a better understanding of the deep language models.
Transferability of Compositionality
To our best knowledge, this is the first work to focus on the transferability of compositionality, and it is orthogonal to existing efforts of learning compositional representations in training distribution.
Gradient Descent Resists Compositionality
In this paper, we argue that gradient descent is one of the reasons that make compositionality learning hard during neural network optimization.
The Third DIHARD Diarization Challenge
DIHARD III was the third in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variability in recording equipment, noise conditions, and conversational domain.
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training
Simultaneous speech-to-speech translation is widely useful but extremely challenging, since it needs to generate target-language speech concurrently with the source-language speech, with only a few seconds delay.
Compositional Language Continual Learning
It also shows significant improvement in machine translation task.
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup.
Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework
Text-to-speech synthesis (TTS) has witnessed rapid progress in recent years, where neural methods became capable of producing audios with high naturalness.
Hubless Nearest Neighbor Search for Bilingual Lexicon Induction
Recent advances in BLI work by aligning the two word embedding spaces.
The Second DIHARD Diarization Challenge: Dataset, task, and baselines
This paper introduces the second DIHARD challenge, the second in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variation in recording equipment, noise conditions, and conversational domain.
Language Modeling at Scale
We show how Zipf's Law can be used to scale up language modeling (LM) to take advantage of more training data and more GPUs.
A Proposed Hierarchy of Deep Learning Tasks
As the pace of deep learning innovation accelerates, it becomes increasingly important to organize the space of problems by relative difficultly.
