Korea, Republic of

Recent works try to handle disfluency detection with unsupervised self-training, which can exploit existing large-scale unlabeled data efficiently. However, their self-training-based methods suffer from the problems of selection bias and error accumulation. To tackle these problems, we propose an adaptive unsupervised self-training method for disfluency detection. Specifically, we re-weight the importance of each training example according to its grammatical feature and prediction confidence. Experiments on the Switchboard dataset show that our method improves 2.3 points over the current SOTA unsupervised method.
Moreover, our method is competitive with the current SOTA supervised method.

COLING 2022

Adaptive Unsupervised Self-training for Disfluency Detection

disfluency detection

self-training

unsupervised learning

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes but also in industrial research departments including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!<br><br><br>

To gain access to this event page you are required to register.<br> Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

technical paper

With the ever growing scale of neural models, knowledge distillation (KD) attracts more attention as a prominent tool for neural model compression. However, there are counter intuitive observations in the literature showing some challenging limitations of KD. A case in point is that the best performing checkpoint of the teacher might not necessarily be the best teacher for training the student in KD. Therefore, one important question would be how to find the best checkpoint of the teacher for distillation? Searching through the checkpoints of the teacher would be a very tedious and computationally expensive process, which we refer to as the checkpoint-search problem. Moreover, another observation is that larger teachers might not necessarily be better teachers in KD, which is referred to as the capacity-gap problem. To address these challenging problems, in this work, we introduce our progressive knowledge distillation (Pro-KD) technique which defines a smoother training path for the student by following the training footprints of the teacher instead of solely relying on distilling from a single mature fully-trained teacher. We demonstrate that our technique is quite effective in mitigating the capacity-gap problem and the checkpoint search problem. We evaluate our technique using a comprehensive set of experiments on different tasks such as image classification (CIFAR-10 and CIFAR-100), natural language understanding tasks of the GLUE benchmark, and question answering (SQuAD 1.1 and 2.0) using BERT-based models and consistently got superior results over state-of-the-art techniques.

Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher

We present a novel collection of news articles originating from fake and real news media sources for the analysis and prediction of news virality. Unlike existing fake news datasets which either contain claims or news article headline and body, in this collection each article is supported with a Facebook engagement count which we consider as an indicator of the article virality. In addition we also provide the article description and thumbnail image with which the article was shared on Facebook. These images were automatically annotated with object tags and color attributes. Using cloud based vision analysis tools, thumbnail images were also analyzed for faces and detected faces were annotated with facial attributes. We empirically investigate the use of this collection on an example task of article virality prediction.

Evons: A Dataset for Fake and Real News Virality Analysis and Prediction

Knowledge distillation is an effective method to transfer knowledge from a large pre-trained teacher model to a compacted student model. However, in previous studies, the distilled student models are still large and remain impractical in highly speed-sensitive systems (e.g., an IR system). In this study, we aim to distill a deep pre-trained model into an extremely compacted shallow model like CNN. Specifically, we propose a novel one-teacher and multiple-student knowledge distillation approach to distill a deep pre-trained teacher model into multiple shallow student models with ensemble learning. Moreover, we leverage large-scale unlabeled data to improve the performance of students. Empirical studies on three sentiment classification tasks demonstrate that our approach achieves better results with much fewer parameters (0.9%-18%) and extremely high speedup ratios (100X-1000X).

One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification

Recycle Your Wav2Vec2 Codebook: a Speech Perceiver for Keyword Spotting

The Chinese text correction (CTC) focuses on detecting and correcting Chinese spelling errors and grammatical errors. Most existing datasets of Chinese spelling check (CSC) and Chinese grammatical error correction (GEC) are focused on a single sentence written by Chinese-as-a-second-language (CSL) learners. We find that errors caused by native speakers differ significantly from those produced by non-native speakers. These differences make it inappropriate to use the existing test sets directly to evaluate text correction systems for native speakers. Some errors also require the cross-sentence information to be identified and corrected. In this paper, we propose a cross-sentence Chinese text correction dataset for native speakers. Concretely, we manually annotated 1,500 texts written by native speakers. The dataset consists of 30,811 sentences and more than 1,000,000 Chinese characters. It contains four types of errors: spelling errors, redundant words, missing words, and word ordering errors. We also test some state-of-the-art models on the dataset. The experimental results show that even the model with the best performance is 20 points lower than humans, which indicates that there is still much room for improvement. We hope that the new dataset can fill the gap in cross-sentence text correction for native Chinese speakers.

CCTC: A Cross-Sentence Chinese Text Correction Dataset for Native Speakers

Most existing word embedding models use a vast corpus as a primary source while training, but this requires massive time and space for data prepossessing and model training. 
We propose a new model, HG2Vec, that learns word embeddings utilizing only dictionaries and thesauri.
We utilize dictionaries and thesauri as the only resources (without using any text corpus) to train word embeddings and obtain state-of-art results on several benchmarks.
We demonstrate that learning synonyms and antonyms is necessary for word embedding models, so a model can distinguish the words with opposite meanings that appear in similar contexts.
We propose a context-focused loss to boost learning in closely related contexts

HG2Vec: Improved Word Embeddings from Dictionary and Thesaurus Based Heterogeneous Graph

Recently, some span-based methods have
achieved encouraging performances for joint
aspect-sentiment analysis, which first extract
aspects (aspect extraction) by detecting aspect
boundaries and then classify the span-level
sentiments (sentiment classification). However, most existing approaches either sequentially extract task-specific features, leading to
insufficient feature interactions, or they encode aspect features and sentiment features in
a parallel manner, implying that feature representation in each task is largely independent
of each other except for input sharing. Both
of them ignore the internal correlations between the aspect extraction and sentiment classification. To solve this problem, we novelly
propose a hierarchical interactive network (HIASA) to model two-way interactions between
two tasks appropriately, where the hierarchical
interactions involve two steps: shallow-level
interaction and deep-level interaction. First,
we utilize cross-stitch mechanism to combine
the different task-specific features selectively
as the input to ensure proper two-way interactions. Second, the mutual information technique is applied to mutually constrain learning
between two tasks in the output layer, thus the
aspect input and the sentiment input are capable of encoding features of the other task
via backpropagation. Extensive experiments
on three real-world datasets demonstrate HIASA’s superiority over baselines.

A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis

Understanding textual content is critical to improving the quality of news recommendation. To achieve this goal, recent studies have proposed to apply pre-trained language models (PLMs) such as BERT for semantic-enhanced news recommendation. Despite their great success in offline evaluation, it is challenging to apply such large PLMs in real-time ranking tasks due to the stringent latency requirements in model updating and inference. To bridge this gap, we propose a plug-and-play pre-trainer, namely PREC, to learn both user and news encoders through multi-task pre-training. Instead of directly leveraging sophisticated PLMs for end-to-end inference, we focus on how to use the cached user and item representations to boost the performance of traditional ID-based models for click-through-rate prediction. This enables efficient online inference as well as compatibility to the widely-used models in industry, which would significantly ease the practical deployment. We validate the effectiveness of PREC through both offline evaluation on public datasets and online A/B testing in an industrial system.

Boosting Deep CTR Prediction with a Plug-and-Play Pre-trainer for News Recommendation

An after-visit summary (AVS) is a summary note given to patients after their clinical visit. It recaps what happened during their clinical visit and guides patients' disease self-management. Studies have shown that a majority of patients found after-visit summaries useful. However, many physicians face excessive workloads and do not have time to write clear and informative summaries. In this paper, we study the problem of automatic generation of after-visit summaries and examine whether those summaries can convey the gist of clinical visits. We report our findings on a new clinical dataset that contains a large number of electronic health record (EHR) notes and their associated summaries. Our results suggest that generation of lay language after-visit summaries remains a challenging task. Crucially, we introduce a feedback mechanism that alerts physicians when an automatic summary fails to capture the important details of the clinical notes or when it contains hallucinated facts that are potentially detrimental to the summary quality. Automatic and human evaluation demonstrates the effectiveness of our approach in providing writing feedback and supporting physicians.

Generation of Patient After-Visit Summaries to Support Physicians

Training with noisy labelled data is known to be detrimental to model performance, especially for high-capacity neural network models in low-resource domains. Our experiments suggest that standard regularisation strategies, such as weight decay and dropout, are ineffective in the face of noisy labels. We propose a simple noisy label detection method that prevents error propagation from the input layer. The approach is based on the observation that the projection of noisy labels is learned through memorisation at advanced stages of learning, and that the Pearson correlation is sensitive to outliers. Extensive experiments over real-world human-disagreement annotations as well as randomly-corrupted and data-augmented labels, across various tasks and domains, demonstrate that our method is effective, regularising noisy labels and improving generalisation performance.

Premium content

Downloads

Next from COLING 2022

Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher

Similar lecture

Disfluency Detection for Vietnamese