United States

A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (NMT) tasks.

NAACL 2021

Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

technical paper

It's an about 9 minutes presentation of the paper: Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction, which introduces the task description, motivation, methodology and experiment results briefly. The topics are the target-oriented opinion words extraction and aspect-opinion pairs extraction.

Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction

Does syntax matter for Aspect-level Sentiment Classification？ No, the RoBERTa with an MLP layer is able to achieve SOTA or near SOTA performance in this task.

Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa

Domain divergences are a tool to measure domain shifts. Given a plethora of divergence measures, In this talk, we provide a taxonomy of divergences consisting of three classes - 1) Geometric 2) Information Theoretic 3) Higher order measures. We detail their use cases in domain adaptation for 1) Data Selection 2) Learning domain invariant representations 3) Making decisions in the wild. While divergence measures have a practical use-case of predicting performance drops, it is still not clear which divergence measure is suitable for a NLP task. Also, most of the works in the literature calculate divergence measures based on simple frequency based word distributions or word embeddings. Does using contextual word representations have any advantage in predicting the drop in performance? We perform a large-scale empirical analysis consisting of more than 130 domain adaptation scenarios, 3 NLP tasks and 12 divergence measures. We find that divergences calculated using traditional word distributions still serve as strong baselines.

Domain Divergences: A Survey and Empirical Analysis

**Read the paper on the folowing link:**

https://www.aclweb.org/anthology/2021.naacl-srw.14/

**Abstract:**

0

Seed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation

For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on BART (Lewis et al., 2020), a pre-trained transformer encoderdecoder model, is trained to generate responses and recognize emotions simultaneously. Furthermore, we weight the losses for the tasks to control the update of parameters. Automatic evaluations and crowdsourced manual evaluations show that the proposed model makes generated responses more emotionally aware.

Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation

The quality and quantity of parallel sentences are known as very important training data for constructing neural machine translation (NMT) systems. However, these resources are not available for many low-resource language pairs. Many existing methods need strong supervision and hence are not suitable. Although there have been several attempts at developing unsupervised models, they ignore the language-invariant between languages. In this paper, we propose an approach based on transfer learning to mine parallel sentences in an unsupervised setting. With the help of bilingual corpora of rich-resource language pairs, we can mine parallel sentences without bilingual supervision of low-resource language pairs. Experiments show that our approach improves the performance of mined parallel sentences compared with previous methods. In particular, we achieve good results at two real-world low-resource language pairs.

Parallel sentences mining with transfer learning in an unsupervised setting

Although research on emotion classification has significantly progressed in high-resource languages, it is still infancy for resource-constrained languages like Bengali. However, unavailability of necessary language processing tools and deficiency of benchmark corpora makes the emotion classification task in Bengali more challenging and complicated. This work proposes a transformer-based technique to classify the Bengali text into one of the six basic emotions: anger, fear, disgust, sadness, joy, and surprise. A Bengali emotion corpus consists of 6243 texts is developed for the classification task. Experimentation carried out using various machine learning (LR, RF, MNB, SVM), deep neural networks (CNN, BiLSTM, CNN+BiLSTM) and transformer (Bangla-BERT, m-BERT, XLM-R) based approaches. Experimental outcomes indicate that XLM-R outdoes all other techniques by achieving the highest weighted f_1-score of 69.73% on the test data. The dataset is publicly available at https://github.com/omar-sharif03/NAACL-SRW-2021.

Emotion Classification in a Resource Constrained Language Using Transformer-based Approach

Abstractive document summarization models have been developed through the incorporation of pre-training methods.

Hie-BART: Document Summarization with Hierarchical BART

Non-autoregressive encoder-decoder models greatly improve decoding speed over autoregressive models, at the expense of generation quality. To mitigate this, iterative decoding models repeatedly infill or refine the proposal of a non-autoregressive model. However, editing at the level of output sequences limits model flexibility. We instead propose iterative realignment, which by refining latent alignments allows more flexible

Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment

Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies.

Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation

Downloads

Next from NAACL 2021

Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction

Similar lecture

Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems